sreda, 17. januar 2024 Domen ŠOBERL: Qualitative Reasoning in Artificial Intelligence — bridging the gap between machine learning and human reasoning

torek, 12. december 2023 Sead JAHIĆ: Sentiment Analysis (SA) of the Bosnian Language (the overview of contributions to SA in Bosnian)

Tokrat izjemoma v četrtek, 14. decembra 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 14. december 2023 ob 16.00 prek Zoom-a.

------------------------------------
PREDAVATELJ: Sead JAHIĆ
------------------------------------

Sead Jahić is in the final year of his PhD. Prior to that, he pursued mathematics at the University of Tuzla (UNTZ) in Bosnia and Hercegovina. In terms of work experience, he served as a teaching assistant at UNTZ in the field of Applied Mathematics and Computer Science. Currently, he is a Teaching Assistant at UP FAMNIT, focusing on Java from introductory levels through GUI to Parallel/Concurrent and Distributed programming.

--------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Sentiment Analysis (SA) of the Bosnian Language (the overview of contributions to SA in Bosnian)
--------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

On the seminar, the contributions to Sentiment Analysis in the Bosnian language will be presented. Insights into the lexicon creation process will be provided first, followed by the discussion of ideas for annotating and ensuring lexicon coverage. The speaker will introduce the MERI (Modifying Emotion-related Intensity) equation for sentiment calculation and demonstrate how Negation clues and AnAwords (Affirmative and non-affirmative) words influence the overall sentiment value of the text through two models they developed: BoSa and BOSentiment. Additionally, a comparison of these models with other ML techniques and CNN will be presented.

Seminar bo potekal v angleškem jeziku prek Zoom-a s pričetkom ob 16:00 uri.

Povezava:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09
Meeting ID: 297 328 207
Passcode: 123456789

Vabljeni.

ponedeljek, 4. december 2023 Domen Vake: Smart Floor - Fall Detection

V ponedeljek, 4. decembra 2023, bo ob 16.00 uri izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 4. december 2023 ob 16.00 v FAMNIT-VP3.

----------------------------------------
PREDAVATELJ: Domen Vake:
----------------------------------------

Domen Vake is a third-year PhD student at UP FAMNIT under the mentorship of Assoc. Prof. Branko Kavšek and Assoc. Prof Jernej Vičič. His research interests include blockchain technologies and machine learning combining them in research of sensor network data.

-----------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Smart Floor - Fall Detection
-----------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:  The presentation will delve into the scientific and technical aspects of our newly developed smart floor system, designed for enhanced fall detection accuracy. We will detail the integration of advanced sensors and sophisticated algorithms that enable real-time monitoring and incident response. Additionally, we will discuss its potential applications in healthcare and elderly care settings, demonstrating how this technology can significantly improve safety standards.

Seminar bo potekal v angleškem jeziku v FAMNIT-VP3 s pričetkom ob 16:00 uri.

Vabljeni.

nedelja, 26. november 2023 Vanja MILESKI: A ResNet Convolutional Neural Network for Time Series data using InceptionNet paradigms

V ponedeljek, 27. novembra 2023, bo ob 16.00 uri izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 27. november 2023 ob 16.00 prek Zoom-a.

----------------------------------------
PREDAVATELJ: Vanja MILESKI
----------------------------------------

After graduating from the Faculty of Computer and Information Science at the University of Ljubljana in 2015, Vanja Mileski started working at the Jožef Stefan Institute (JSI). He was a Master's student at the International Postgraduate School Jožef Stefan and a student researcher at the JSI. After finishing his Master's studies, he applied his knowledge of data mining in the private sector as a Data Scientist in the retail, telecommunications, banking, stock market and insurance sectors.
His current research interests include time-series classification, deep learning, ResNet and Inception architectures.

-----------------------------------------------------------------------------------------------------------------------------------------
NASLOV: A ResNet Convolutional Neural Network for Time Series data using InceptionNet paradigms
-----------------------------------------------------------------------------------------------------------------------------------------

POVZETEK: 

The recent progress in Convolutional Neural Network (CNN) designs has extended their effectiveness to time series data as well. Time series features, which can be represented as one-dimensional vectors, open the door for training deeper networks using ResNet-inspired structures. Inception modules provide the capability to the network to handle objects and patterns of different sizes and capture both local details and global context. We propose an Inception-Residual CNN model tailored for time series data which will be applied on real-life data in retail.

Seminar bo potekal v angleškem jeziku prek Zoom-a s pričetkom ob 16:00 uri.

Povezava:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09
Meeting ID: 297 328 207
Passcode: 123456789

Vabljeni.

petek, 10. november 2023 Ivan Luković: Organizational Capability for Information Management – Do we Feel a Big Data Crisis?

V ponedeljek, 13. november 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 13. november 2023 ob 16.00 v FAMNIT-VP3.

-------------------------------------------------------------------
PREDAVATELJ: Ivan LUKOVIĆ
-------------------------------------------------------------------

Ivan Luković received his Ph.D. at the University of Novi Sad, Faculty of Technical Sciences in 1996. Currently, he works as a Full Professor at the Faculty of Organizational Sciences of the University of Belgrade, where he lectures in several Computer Science and Informatics courses. His research interests are related to Database Systems, Business Intelligence, Software Engineering, and Data Science. He is the author or co-author of over 200 papers, 4 books, and 30 industry projects and software solutions in the area. He supervised 12 completed Ph.D. theses. He created a new set of B.Sc. and M.Sc. study programs in Information Engineering, i.e. Data Science, at the Faculty of Technical Sciences. The programs were accredited the first time in 2015. Currently, he is a chair of Managing Board of the Computer Science and Information Systems (ComSIS) journal, and a chair of M.Sc. study program in Information Engineering at Faculty of Organizational Sciences. He is also a member of Serbian AI Society.

-------------------------------------------------------------------------------------------
NASLOV: Organizational Capability for Information Management – Do we Feel a Big Data Crisis?
-------------------------------------------------------------------------------------------

POVZETEK: Nowadays, modern business includes acquisition and storing enormous data volumes, larger than ever before. Most often, collected data are used in a shorter time frame, and then they are archived and almost not used, effectively. On the other hand, such data represent a significant value that a company can utilize so as to reach created goals and provide a sustainable development. Unfortunately, a daily practice in many companies still intensively points out to the problem of a serious gap between the identified needs for knowledge, on one hand, and inability of modern software products to address such needs in an effective way, on the other hand. Despite that massive data volumes already exist and that modern information solutions provide the excellent technology prerequisites for a development and industry implementation of high quality software applications. We can call such a phenomenon a “big data crisis”. Some of important causes of the aforementioned phenomenon are in the following: (1) Unsatisfactory level of organization maturity in regard to the: capabilities for information management, quality management, and business processes; (2) Unsatisfactory level of accumulated knowledge in a problem domain; and (3) Unsatisfactory level of accumulated knowledge in a domain of software engineering, particularly in a domain of the development and formal specification of models for software products aimed at generation of company knowledge and decision support. Alleviating the aforementioned phenomenon is a strategic and long term task, possible by simultaneous addressing all its significant causes, only.

In this talk, some of the author's research and educational efforts will be presented, trying to address the most influencing factors for information management and innovations, leading to the digital transformation process.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.

Vabljeni.

ponedeljek, 6. november 2023 Uroš SERGAŠ & Jar Žiga MARUŠIČ: The AI alignment problem and its implications for society

V ponedeljek, 6. novembra 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 6. november 2023 ob 16.00 v FAMNIT-VP2.

-------------------------------------------------------------------
PREDAVATELJA: Uroš SERGAŠ & Jar Žiga MARUŠIČ
-------------------------------------------------------------------

Uroš Sergaš is a PhD student in Computer Science at UP FAMNIT, Jar Žiga Marušič is a PhD student in Philosophy at UL FF. Both are also teaching assistants at UP FAMNIT, Uroš in the Department of Information Sciences and Technologies, Jar in the Department of Psychology. Together they are interested in the implications and uses of artificial intelligence in society. Over the summer they researched the AI alignment problem.

-------------------------------------------------------------------------------------------
NASLOV: The AI alignment problem and its implications for society
-------------------------------------------------------------------------------------------

POVZETEK:

Humanity has again found itself on the brink of a new era, as large language models (LLM) seem poised to bring about important social changes. As these models advance in complexity, the issue of AI alignment is gaining popularity in a daily conversation topic.
This research explores two contrasting viewpoints on the AI alignment problem: the Orthogonalist perspective pioneered by Nick Bostrom and the Anti-orthogonalist critique formulated by Nick Land. The former posits that an AI’s goals are independent of its intelligence, suggesting that a "friendly AI" (fully aligned to human values) is possible. The latter challenges its separation of intelligence and values from the perspective that intelligence increase leads to a greater ability for self-reflection, ultimately leading to a restructuring of its value structure to prioritize further cognitive enhancement. We discuss the implications of these ideas and highlight the current patterns seen in the developments of widely available AI tools, such as LLM.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP2 s pričetkom ob 16:00 uri.

Vabljeni.      

ponedeljek, 18. september 2023 Dani ZUGAN: Vrednotenje algoritmov za iskanje najkrajših poti v omrežju

V ponedeljek, 18. septembra 2023, bosta ob 16.00 uri izvedeni dve
predavanji v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 18. september 2023 ob 16.00 na daljavo prek ZOOM-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

--------------------------------------------------------------------------------------------------------------------------------------------------------------------------

1. predavanje:
============

------------------------------------
PREDAVATELJ: Jani SUBAN
------------------------------------

Jani Suban je študent prvega letnika magistrskega programa Računalništva in informatike na UP FAMNIT.

-------------------------------------------------------------------------------------
NASLOV: Empirična evalvacija urejenih slovarjev z ALGatorjem
-------------------------------------------------------------------------------------

POVZETEK:

Na seminarju bo predstavljena empirična evalvacija različnih implementacij abstraktne podatkovne strukture urejen slovar. Implementirane podatkovne strukture so binarno iskalno drevo, drevo AVL, rdeče-črno drevo, zip drevo, preskočni seznam in 2-3 drevo. Implementacije so bile testirane s pomočjo sistema za evalvacijo algoritmov in podatkovnih struktur ALGator. Iz rezultatov testiranja podatkovnih struktur, tako pri striktno naraščajočih, kot tudi naključnih posodobitvah in poizvedbah, je razvidno, da je časovna zahtevnost enaka pričakovani.

--------------------------------------------------------------------------------------------------------------------------------------------------------------------------

2. predavanje:
============

-------------------------------------
PREDAVATELJ: Dani ZUGAN
-------------------------------------

Dani Zugan je študent prvega letnika magistrskega programa Računalništva in informatike na UP FAMNIT.

----------------------------------------------------------------------------------------------
NASLOV: Vrednotenje algoritmov za iskanje najkrajših poti v omrežju
----------------------------------------------------------------------------------------------

POVZETEK:

V članku so ovrednoteni trije različni algoritmi za izračun paroma najkrajših poti v grafu. Primerjamo znani Floyd-Warshallov algoritem z dvema preprostima modifikacijama. Ključna razlika je v tem, da so relaksacije izvedene na pametnejši način. Algoritme ovrednotimo na treh različnih modelih grafov - uniformnem Erdős-Rényijevem, binomskem Erdős-Rényijevem in Albert-Barabásijevem. Na podlagi rezultatov lahko ugotovimo, da sta oba spremenjena modificirana algoritma boljša od algoritma Floyd-Warshall.

--------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Seminar bo potekal v slovenskem jeziku, tokrat na daljavo prek Zoom-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

Vabljeni!

sreda, 13. september 2023 Robert Scheffler: Optimal Bicycle Routes with Few Signal Stops

Tokrat izjemoma v četrtek, 14. septembra 2023, bo ob 14.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 14. september 2023 ob 14.00 v FAMNIT-MP6.

----------------------------------------------
PREDAVATELJ: Robert SCHEFFLER
----------------------------------------------

Robert Scheffler studied computer science and received his master's degree in 2017. This year he made his PhD with his thesis about vertex and edge orderings of graphs. Currently, he is a Postdoc at the Chair of Discrete Mathematics and Foundations of Computer Science at Brandenburg University of Technology in Cottbus, Germany.

---------------------------------------------------------------------------
NASLOV: Optimal Bicycle Routes with Few Signal Stops
---------------------------------------------------------------------------

POVZETEK:

With the increasing popularity of cycling as a mode of transportation, there is a growing need for efficient routing algorithms that consider the specific requirements of cyclists. We study the optimization of bicycle routes while minimizing the number of stops at traffic signals. In particular, we consider three different types of stopping strategies and three types of routes, namely paths, trails, and walks. We present hardness results as well as a pseudo-polynomial algorithm for the problem of computing an optimal route with respect to a pre-defined stop bound.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-MP6 s pričetkom ob 14:00 uri.

Vabljeni

ponedeljek, 11. september 2023 Domen VAKE: Pseudo-Random Algorithm for Sending Messages in Decentralized Networks

V ponedeljek, 11. september 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 11. avgust 2023 ob 16.00 na daljavo prek ZOOM-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

----------------------------------------
PREDAVATELJ: Domen VAKE
----------------------------------------

Domen Vake is a second-year PhD student at UP FAMNIT under mentorship of assoc. prof. Branko Kavšek and assoc. prof Jernej Vičič.  His research interests include blockchain technologies and machine learning combining them in research of sensor network data.

---------------------------------------------------------------------------------------------------------------------
NASLOV: Pseudo-Random Algorithm for Sending Messages in Decentralized Networks
---------------------------------------------------------------------------------------------------------------------

POVZETEK:

We present an algorithm for the dissemination of messages in fully decentralized networks. The motivation for research comes from the field of blockchain technology and the development of decentralized network protocols. One of the key goals of such systems is an effective spread of data through the network. The goal of good algorithms is to get every message received as soon as possible. The presented algorithm works on the principle of pseudorandomness for determining the message path from the originator of the message to every node in the network. The proposed algorithm pseudorandomly generates a path for the message through the network. Upon receiving the message, each node is able to reproduce the same path and continue the propagation of the message. The algorithm implements a by-layer checking on the successful dissemination of the message, which sharply raises the fault tolerance of the algorithm.
 

Seminar bo potekal v slovenskem jeziku, tokrat na daljavo prek Zoom-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

Vabljeni!      

petek, 18. avgust 2023 Matevž MAK: Sodobne tehnologije in arhitektura za implementacijo prototipa

V ponedeljek, 21. avgusta 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 21. avgust 2023 ob 16.00 na daljavo prek ZOOM-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

----------------------------------------
PREDAVATELJ: Matevž MAK
----------------------------------------

Matevž Mak je študent 2. letnika magistrskega študijskega programa 2. stopnje Računalništvo in informatika na UP FAMNIT. Temo bo predstavil v okviru raziskovalnega seminarja, ki ga je izdelal pod mentorstvom prof. Matjaža Kljuna.

-----------------------------------------------------------------------------------------------------
NASLOV: Sodobne tehnologije in arhitektura za implementacijo prototipa
-----------------------------------------------------------------------------------------------------

POVZETEK:

V moji predstavitvi se bomo poglobili v sodobne tehnologije, ki so ključne pri razvoju prototipov spletnih aplikacij ter osnovah oblikovanja arhitekture projekta. Osredotočili se bomo na tehnološko zbirko MEAN (MongoDB, Express, Angular in Node.JS), pri čemer bomo raziskali prednosti vsake posamezne tehnologije. Pregledali bomo tudi, kako efektivno uporabljati GitHub submodule ter njihovo vlogo v razvoju. Prikazali bomo, kako integrirati aplikacijo z Docker containerji in kako izvesti obremenitvene teste z uporabo knjižnice k6. Za konec pa se bomo posvetili vzpostavitvi replikacijskega sistema za MongoDB z uporabo clustrov in shardov, implementiranih preko Docker containerjev.

Seminar bo potekal v slovenskem jeziku, tokrat na daljavo prek Zoom-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

Vabljeni!      

sreda, 26. julij 2023 Gregor GRBEC: Ranking Football Players Using Multilevel Modeling

V ponedeljek, 31. julija 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 31. julij 2023 ob 16.00 na daljavo prek ZOOM-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

----------------------------------------
PREDAVATELJ: Gregor GRBEC
----------------------------------------

Gregor Grbec is a student who started his studies in Bioinformatics at UP FAMNIT. After graduation in 2020, he decided to pursue a master's degree in Data Science at the same faculty. His lifelong interest in football inspired him to do research on who is the best football player – one of the most frequently asked questions in football.

------------------------------------------------------------------------------------
NASLOV: Ranking Football Players Using Multilevel Modeling
------------------------------------------------------------------------------------

POVZETEK:

While football is a team sport, the question of who is the best football player is one of the most frequently asked in the footballing world. Attackers like Pele, Maradona, Cristiano Ronaldo and Lionel Messi are often mentioned as the best of all time, while players of other positions are mentioned significantly less. We believe that players of all positions are important, which is why we wanted to provide a data-backed answer to this question using advanced mathematical models that can incorporate players of all positions on a single list. Our two main objectives were to extract an individual's performance from the team's performance and to eliminate any bias that comes from the player's position. We used multilevel modeling which allowed us to control for player's team strength with data collected for all players of the top 20 clubs from the top 5 leagues from this century. The results were surprising, as Messi and Ronaldo, often believed to be two of the best of all time, ranked lower than expected.
 

Seminar bo potekal v angleškem jeziku, tokrat na daljavo prek Zoom-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

Vabljeni!      

ponedeljek, 24. julij 2023 Marina PALDAUF: Decentralised Solutions for Preserving Privacy in Group Recommender Systems

V ponedeljek, 24. julija 2023, bo ob 17.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 24. julij 2023 ob 17.00 na daljavo prek ZOOM-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

------------------------------------------------
PREDAVATELJICA: Marina PALDAUF
------------------------------------------------

Marina Paldauf is a PhD student in Computer Science in the fields of recommender systems, machine learning and distributed systems and a teaching assistant at the University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies. She is also a researcher at the HICUP Lab and a Department of Information Sciences and Technologies member.

-------------------------------------------------------------------------------------------------------------------------
NASLOV: Decentralised Solutions for Preserving Privacy in Group Recommender Systems
-------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Group Recommender Systems (GRS) combine large amounts of data from various user behaviour signals (likes, views, purchases) and contextual information to provide groups of users with accurate suggestions (e.g. rating prediction, rankings). To handle those large amounts of data, GRS can be extended to use distributed processing and storage solutions (e.g. MapReduce-like algorithms and NoSQL databases). As such, privacy has always been a core issue since most recommendation algorithms rely on user behaviour signals and contextual information that may contain sensitive information. However, existing work in this domain mostly distributes data processing tasks without addressing privacy, and the solutions that address privacy for GRS (e.g. k-anonymisation and local differential privacy) remain centralised. In this paper, we identify and analyse privacy concerns in GRS and provide guidelines on how decentralised techniques can be used to address them.

Seminar bo potekal v angleškem jeziku, tokrat na daljavo prek Zoom-a s pričetkom ob 17:00 uri
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

Vabljeni!      

petek, 14. julij 2023 Aleksandar AVDALOVIĆ: Translation of random forests to loop-free imperative programs for the purpose of formal verification

V ponedeljek, 17. julija 2023, bo ob 17.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 17. julij 2023 ob 17.00 na daljavo prek ZOOM-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

---------------------------------------------------
PREDAVATELJ: Aleksandar AVDALOVIĆ
---------------------------------------------------

Aleksandar Avdalović is a second-year student of the master's program Data Science at UP FAMNIT. He will be presenting his Master’s thesis topic that he is completing under the supervision of Prof. Mário Alberto Zenha-Rela and Prof. Raul Barbosa from University of Coimbra and co-supervision of Prof. Marko Tkalčič from UP FAMNIT.

------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Translation of random forests to loop-free imperative programs for the purpose of formal verification
------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Throughout the years of society's digitalisation and transformation, the ethics of AI/ML-dependent critical systems have been continually questioned. In the use of such systems, accuracy may not be a valid metric because machine errors can lead to devastating consequences, including the loss of human life. This thesis takes a narrow approach to the aforementioned problem, namely the formal verification of the incredibly effective and widespread supervised learning method of today, random forest. Using the first-order logic statements and algorithm developed in this study, we intend to determine if the model has acquired factually-grounded prior knowledge. In other words, we wish to confirm that the model is reliable in light of prior knowledge. The translation of the random forest algorithm into a loop-free imperative program for verification purposes provides a technical challenge for this task. The core of the thesis is the algorithm provided in response to the research question of whether an algorithm for described translation exists. We shall construct the algorithm and ensure its correctness by rigorously testing it with various datasets, including those later used for verification and artificially generated datasets with different shapes and numbers of classes. Additionally, we will evaluate its efficiency and demonstrate its application on three datasets (one dataset from Cardiology and two datasets from Rheumatology). Another research problem will be practical, examining if the model has acquired particular prior knowledge in the fields of Cardiology and Rheumatology given the data. Results demonstrate that such an algorithm can be created and is highly efficient and that it can be applied realistically in the health sector to validate ML models based on the random forest algorithm.
 

Seminar bo potekal v angleškem jeziku, tokrat na daljavo prek Zoom-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

Vabljeni!

ponedeljek, 10. julij 2023 Nuwan ATTYGALLE: Breaking Barriers in Gesture Recognition: Enhancing Accuracy through Material-Aware Training

V ponedeljek, 10. julija 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 10. julij 2023 ob 16.00 v FAMNIT-VP2.

----------------------------------------------
PREDAVATELJ: Nuwan ATTYGALLE
----------------------------------------------

Nuwan Attygalle is a PhD student at UP FAMNIT with a research focus at the intersection of signal processing, HCI, and machine learning. His interests lie in exploring innovative applications and solutions in these fields. Nuwan has also served as a visiting researcher at the COIN lab at the University of Luxembourg, further expanding his knowledge and expertise in his research areas.

----------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Breaking Barriers in Gesture Recognition: Enhancing Accuracy through Material-Aware Training
----------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Human-computer interaction is undergoing a transformative shift, moving away from traditional interfaces (screen, keyboard and mouse) and towards more intuitive and natural interaction methods. Gesture recognition plays a crucial role in this paradigm shift, enabling participants to interact with digital devices using natural hand movements and gestures. Leveraging millimetre-wave (mmWave) radar signals that penetrate materials and are immune to environmental conditions, gesture recognition can be achieved even when devices are concealed or embedded within objects. However, the impact of everyday materials on gesture recognition accuracy remains inadequately investigated. This paper investigates whether training a machine learning model with gestures sensed through materials improves overall classification accuracy. We also explore to what extent this improvement occurs and how to achieve comparable accuracy with a model trained using fewer materials. Our findings shed light on the influence of materials on gesture recognition and provide insights into optimizing training processes for enhanced performance in real-world applications.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP2.

Vabljeni!      

nedelja, 25. junij 2023 Daniil BALDOUSKI: Managing and Optimizing Container Flow in Port Logistics

Jutri, v ponedeljek, 26. junija 2023, bo ob 16.00 uri izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 26. junij 2023 ob 16.00 v FAMNIT-VP1.

--------------------------------------------
PREDAVATELJ: Daniil BALDOUSKI
--------------------------------------------

Daniil Baldouski is a first-year PhD student of Computer Science at UP FAMNIT.

--------------------------------------------------------------------------------------------
NASLOV: Managing and Optimizing Container Flow in Port Logistics
--------------------------------------------------------------------------------------------

POVZETEK: 

Efficient container management is pivotal to port logistics. In this seminar I will talk about integer linear programming and explain a method for optimizing truck scheduling within a port, using a mathematical model that facilitates concurrent tasks under specific constraints and capacity limitations. The model's efficiency will be showcased on simulated instances.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP1.

Vabljeni!

ponedeljek, 19. junij 2023 Daan LE ROUX: Digital Distraction, Online Vigilance and the Goldfish Hypothesis: Making sense of the impacts of technology on attention

V ponedeljek, 19. junija 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 19. junij 2023 ob 16.00 v FAMNIT-VP2.

----------------------------------------
PREDAVATELJ: Daan LE ROUX
----------------------------------------

Dr. Daan le Roux heads up the Cognition and Technology Research Group at Stellenbosch University in South Africa. He studies various dimensions of the interaction between humans and technology with emphasis on the cognitive and behavioural processes by which humans, both individually and collectively, adopt and adapt to technologies, and how this impacts their performance and well-being. His research is interdisciplinary in nature and has been published in outlets across various domains including Information Systems, Psychology, Business Management and Education.

----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Digital Distraction, Online Vigilance and the Goldfish Hypothesis: Making sense of the impacts of technology on attention
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Over the past two decades we have experienced the emergence of a media ecology characterized by the omnipresence of mobile computing devices that offer a rapidly expanding range of gratifying online experiences. As smartphone use volumes have steadily increased, online platforms have proliferated, creating an increasingly competitive attention economy. A growing body of both popular and academic literature have raised concerns over the potential impacts of these developments for human wellbeing. One area which has received substantial attention concerns the effects that permanent online connectedness and constant media multitasking may have on cognitive control – i.e., our capacity to direct and sustain attention. Specifically, some studies have suggested that our behavior with technology may lead to the shortening of our attention spans. In this talk the state of empirical evidence in this domain is systematically reviewed with reference to recent studies of both the short and long-term effects of digital technology use on cognitive control.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP2.

Vabljeni!      

ponedeljek, 12. junij 2023 Nedim Šišić: Class Probability Distributions of a Neural Network Classifier of Multiple Sclerosis Lesions on Quantitative Susceptibility Mapping

V ponedeljek, 12. junija 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 12. junij 2023 ob 16.00 v FAMNIT-VP2.

-------------------------------------
PREDAVATELJ: Nedim ŠIŠIĆ
-------------------------------------

Nedim Šišić is a 1st year PhD student of Computer Science at UP FAMNIT. He finished his master's studies in Computer Science at UP FAMNIT, and is now a teaching assistant at various computer science courses.

--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Class Probability Distributions of a Neural Network Classifier of Multiple Sclerosis Lesions on Quantitative Susceptibility Mapping
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Multiple sclerosis (MS) is a demyelinating disease, in which the insulating myelin covers of nerve cells are damaged. Remyelination is a repair process that forms new myelin sheaths. MS lesion types are heterogeneous regarding myelin damage and repair and iron content, and may be classified histopathologically. Recently, quantitative susceptibility mapping (QSM) MRI has been shown to classify white matter MS lesions into demyelinated and remyelinated types in vivo. Furthermore, a neural network model demonstrates potential for automatic classification of such lesions into the types based on QSM. However, the model requires further classification accuracy increase and faces the problem of handling lesions unable to be classified by medical experts. The problem represents a significant hurdle for the potential use of the model in clinical scenarios. In this work, the class probability distributions of the model on different remyelinated, demyelinated, and unclassified lesion types are analyzed, to better understand its performance and estimate its behavior on unclassified lesions. The obtained results are important for improving the model and enabling its transition into medical practice.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP2.

Vabljeni! 

ponedeljek, 5. junij 2023 Nikolaus AUGSTEN: Data Management Meets Process Mining - Scaling Trace Clustering to Large Data

Tokrat izjemoma v sredo, 7. junija 2023, bo ob 14.30 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 7. junij 2023 ob 14.30 v FAMNIT-VP3.

----------------------------------------------
PREDAVATELJ: Nikolaus AUGSTEN
----------------------------------------------

Nikolaus Augsten is a full professor in computer science at the University of Salzburg, where he heads the Database Group. He received his PhD from Aalborg University, Denmark, in 2008. His research deals with all aspects of data management. The focus is on queries over complex objects and massive data collections, data cleaning and integration, indexing techniques, query processing and optimization, distributed data management, and numerical computations in databases. His research is triggered by problems that arise in concrete applications, for example, process mining, digital humanities, or cognitive neuroscience. The results of his research have been published in the most prestigious outlets of the database field; for his work on top-k queries over tree data he received the ICDE 2010 Best Paper Award. He has served as a PC member or referee for all major database conferences and as an associate editor of the VLDB Journal.

---------------------------------------------------------------------------------------------------------------------------
NASLOV: Data Management Meets Process Mining - Scaling Trace Clustering to Large Data
---------------------------------------------------------------------------------------------------------------------------

POVZETEK:

With the broad adoption of process mining techniques in industry, process mining tools now face massive data volumes with process logs that can store hundreds of millions of activities. Process mining queries often require fast response times since the user interacts with a dashboard to gain business insights. To analyze business processes, the so-called traces of the processes are inspected. A trace is a sequence of activities observed in the process log. To facilitate the analysis, similar traces should be grouped into clusters using the well-known DBSCAN algorithm. Unfortunately, current trace clustering approaches do not scale to large collections of traces, neither in terms of runtime nor in terms of memory usage.
We present two novel techniques that solve the scalability issue of the trace clustering problem. (1) TwoL is a new, highly effective similarity index for traces. Compared to previous techniques, TwoL optimizes a cost function to gracefully adapt to different data distributions. (2) Spread is the first linear-space DBSCAN algorithm that can process data points in any user-defined order. This is required to leverage the full potential of trace indices. Previous approaches must precompute and materialize all neighborhoods of the data points, which requires quadratic space. With respect to the state of the art in trace clustering, our techniques reduce the memory complexity and achieve speedups of more than an order of magnitude.

Seminar bo potekal v angleškem jeziku s pričetkom ob 14:30 v predavalnici FAMNIT-VP3.

Vabljeni!      

petek, 2. junij 2023 Matija BIROV, Jan KANDUČ, Mojca BELAC: Risk Management at Intesa Sanpaolo Bank

V ponedeljek, 5. junija 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 5. junij 2023 ob 16.00 v predavalnici FAMNIT-VP2

--------------------------------------
PREDAVATELJI: Matija BIROV, Jan KANDUČ, Mojca BELAC
--------------------------------------

The presentation will be held by Matija Birov, Chief Risk Officer, Jan Kanduč, Director of Risk Management, and Mojca Belac, Head of Credit Risk Monitoring, Controls and Validation

----------------------------------------------------------------------------------------------
NASLOV: Risk Management at Intesa Sanpaolo Bank
----------------------------------------------------------------------------------------------

POVZETEK:

What is risk management and how does it fit into the commercial banking business? What kind of tools and skills are needed for efficient risk management? What kind of knowledge and expertise are required for development of risk measurement systems? How much do banks rely on statistical analysis for day-to-day operations? Are the business decisions driven only by future profits or is there more to the story? Are the risk parameters (probability of default, loss given default, exposure at default) the only true indicators of your credit worthiness when applying for a loan?

These and many more questions related to the banking world will be discussed at the presentation.

Seminar bo potekal v živo v angleškem jeziku.

Vabljeni! 

petek, 26. maj 2023 Arsen Matej GOLUBOVIKJ: Longitudinal Study of Preferences and Behaviour Changes in Music Streaming

V ponedeljek, 29. maja 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 29. maj 2023 ob 16.00 v FAMNIT-VP2.

------------------------------------------------------
PREDAVATELJ: Arsen Matej GOLUBOVIKJ
------------------------------------------------------

Arsen Matej Golubovikj is a 1st year PhD student of Computer Science at UP FAMNIT. He finished his master's studies in Data Science at UP FAMNIT, and is now exploring topics related to Recommender Systems and User Modeling.

-----------------------------------------------------------------------------------------------------------------------
NASLOV: Longitudinal Study of Preferences and Behaviour Changes in Music Streaming
-----------------------------------------------------------------------------------------------------------------------

POVZETEK:

The majority of research in recommender systems, being it algorithmic improvements, context-awareness, explainability, or other areas, evaluate their systems on datasets that capture the user interaction with the system in a relatively limited time span. However, recommender systems have been around for more than two decades and the way user behave might have changed through time. Although there is a wide body of research in media studies and psychology on how user preferences and behaviour change through time (especially as users age) there has been very little work done in the domain of recommender systems. In this work we explore how user preferences and behaviour change through time on a well-known dataset of LastFM users, the LFM-2B dataset. To the best of our knowledge, this is the only dataset that covers a long-enough time span (to allow longitudinal studies) and has age information about its users. Beside performing a descriptive analysis of preferences and behaviour changes we also inspect whether there are differences between generations of users. The results show important insights that can pave the way for a new line of research in recommender systems and informs future work.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP2.

Vabljeni!      

ponedeljek, 22. maj 2023 Nuno LARANJEIRO: Software Dependability Research at the University of Coimbra & Naghmeh IVAKI: Verification and Validation of U-space Services

V ponedeljek, 22. maja 2023, bosta ob 15.00 uri izvedeni dve
predavanji v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 22. maj 2023 ob 15.00 v predavalnici FAMNIT-VP2

POZOR: Seminar se prične ob 15:00 !!!

=============================================================================================================

1. predavanje:

---------------------------------------------
PREDAVATELJ: Nuno LARANJEIRO
---------------------------------------------

Nuno Laranjeiro received the PhD degree from the University of Coimbra, Portugal, where he currently is an Assistant Professor. His research focuses on dependable and secure software services and he currently leads the Software and Systems Engineering (SSE) group at the Centre for Informatics and Systems of the University of Coimbra (CISUC). His research interests include experimental dependability evaluation, fault injection, robustness of software and web services, web services interoperability, and software security. He is currently mostly involved in developing new techniques towards more reliable and secure cloud systems and microservices, in developing techniques for evaluating the reliability and security of blockchain smart contracts, and using machine learning techniques for software fault and vulnerability detection and characterization. He has contributed, as an author, reviewer and program committee member, to leading conferences and journals in the dependability and services computing areas. Nuno has been involved in the organisation of several international events, including several editions of the International Symposium on Software Reliability Engineering (ISSRE) and also the Dependable and Secure Services Workshop/Track (as main chair) jointly organised with the IEEE World Congress on Services. He participated in international research projects, including several H2020 projects (e.g., ADVANCE, DEVASSES, ATMOSPHERE, EUBrasilCloudFORUM) and FP7 projects (CRITICAL STEP, CECRIS).

-------------------------------------------------------------------------------------------------
NASLOV: Software Dependability Research at the University of Coimbra
-------------------------------------------------------------------------------------------------

POVZETEK:

The Software and Systems Engineering (SSE) group at the Centre for Informatics and Systems of the University of Coimbra (CISUC) develops disruptive research on different facets of software and systems engineering, with particular focus on dependability and security aspects. Internationally recognized contributions of SSE include new experimental approaches for dependability, resilience and security evaluation and benchmarking, including fault injection, robustness testing, vulnerability & attack injection and vulnerability detection methods. This talk overviews the SSE group research activities and discusses a fault injection case study.

=============================================================================================================

2. predavanje:

----------------------------------------------
PREDAVATELJICA: Naghmeh IVAKI
----------------------------------------------

Naghmeh Ivaki received the PhD degree from the University of Coimbra, Portugal. Currently, she is an assistant professor and a full member of Software and Systems Engineering Group (SSE) of the Center for Informatics and Systems (CISUC), Department of Informatics Engineering, University of Coimbra. She specializes in the scientific field of Informatics Engineering, with particular focus on trustworthiness, security, safety, and dependability of computer systems. In her field of specialization, she has authored about 40 peer-reviewed publications and participated in 11 national and inernational research projects.

----------------------------------------------------------------------------
NASLOV: Verification and Validation of U-space Services
----------------------------------------------------------------------------

POVZETEK:

Unmanned Aerial Vehicles (UAVs or UAS) have gained notable importance in civil airspace. To ensure their safe operation (in particular, in urban area), U-space services are being defined in Europe. U-space is a set of services that rely on a high level of digitalization and automation of functions. These services are either on board of the UAVs or are part of the ground controllers, allowing the safe and efficient operation of a large number of UAS (especially, but not only, in urban VLL (very low level)). The main safety pillar of U-space services is conflict management in both strategic and tactical levels, aiming to limit the risk of collision between UAVs and hazards to an agreed level deemed acceptable. However, the target level of safety (TLS) can be threatened by many factors like failures in UAVs (or its components and sensores like GPS), and U-space functioning and communications (e.g., can be caused by hardware failure, software failures, network failures, or security attacks), or even failures due to non-deterministic behavior of AI-based components used in these systems. Our research team aims at building a verification and validation (V&V) platform, allowing the safety assessment of UAVs and U-space services under the aforementioned conditions. By providing such V&V platform for safety assessment, we aim to ensure that the target level of safety is met and maintained.

=============================================================================================================

Obe predavanji bosta v angleškem jeziku.

Vabljeni!

četrtek, 18. maj 2023 Egon BENČIČ: Predstavitev podjetja PROJEKT IP in možnosti štipendiranja

V ponedeljek, 22. maja 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 22. maj 2023 ob 16.00 v predavalnici FAMNIT-VP2

--------------------------------------
PREDAVATELJ: Egon BENČIČ
--------------------------------------

Podjetje PROJEKT IP d.o.o. bo na seminarju predstavil Egon Benčič, ustanovitelj podjetja.

----------------------------------------------------------------------------------------------
NASLOV: Predstavitev podjetja PROJEKT IP in možnosti štipendiranja
----------------------------------------------------------------------------------------------

POVZETEK:

Podjetje PROJEKT IP d.o.o. ponuja IKT storitve manjšim, srednjim, velikim podjetjem in državni upravi na območju celotne Slovenije. Področje delovanja so sčasoma razširili na vse države bivše Jugoslavije in v države Evropske Unije. Njihova glavna usmeritev je nudenje podpore na področju informacijsko-komunikacijskih procesov, kjer pokrivajo vsa področja povezana z uporabo komunikacijskih tehnologij. Strankam pomagajo njihove želje in ideje izpeljati vse od začetne zasnove do uspešne končne izvedbe. Pri rešitvah stremijo k zanesljivosti, stabilnosti in dolgi življenjski dobi vzpostavljenih sistemov. Zelo pomembno jim je, da stranka dobi rešitev na ključ, ki presega njena pričakovanja. Trudijo se, da njihove rešitve pomenijo dodano vrednost, olajšajo poslovne procese in posledično tudi omogočijo prihranke. Na dolgi rok želijo postati najbolj prepoznavno podjetje na področju telekomunikacij v regiji.
Na seminarju bodo študenti podrobneje spoznali dejavnost podjetja in možnosti sodelovanja (študijska praksa, raziskovalne naloge, projekti ...). Ker je Projekt IP d.o.o. tudi štipenditor v okviru Štipendijskega sklada Univerza na Primorskem, bodo študenti na srečanju izvedeli tudi glede možnosti prejetja štipendije v naslednjem študijskem letu!

Več v vabilu.

Seminar bo potekal v slovenskem jeziku.

Vabljeni!      

petek, 12. maj 2023 Maja DUNDOVIĆ: Automation of modular, multipurpose mechatronic system for mechanical experimental testing using MATLAB®

V ponedeljek, 15. maja 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 15. maj 2023 ob 16.00 na daljavo prek ZOOM-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

-------------------------------------------------
PREDAVATELJICA: Maja DUNDOVIĆ
-------------------------------------------------

Maja Dundović, mag. ing. mech., obtained her MSc in Mechanical Engineering at the Faculty of Engineering of the University of Rijeka in 2011. She is currently employed as an assistant and pursuing her PhD in Mechanical Engineering at the same institution. Her teaching duties cover exercises in undergraduate and graduate courses in the fields of Engineering Graphics, Machine Elements, and Robot Elements. Her scientific research interest areas are in the field of Compliant Mechanisms, Material Behaviour Testing and Modelling.

-------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Automation of modular, multipurpose mechatronic system for mechanical experimental testing using MATLAB®
-------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

In this presentation, we'll focus on the work that was done in cooperation with the Faculty of Mathematics, Natural Sciences and Information Technologies, University of Primorska, as a part of the scientific training that is mandatory for PhD students at the University of Rijeka. First, we'll introduce compliant mechanisms, design of the mechatronic system setup for mechanical testing, and in a higher level of detail present a computer vision procedure for testing automation using MATLAB. As part of this, a pure bending test setup will be shown and test results discussed. The presentation will be concluded with a brief overview of the Faculty of Engineering, University of Rijeka, and with a discussion on the areas for possible future scientific collaboration, together with opportunities for student and staff mobility.
 

Seminar bo potekal v angleškem jeziku, tokrat na daljavo prek Zoom-a
(https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

Vabljeni!      

petek, 14. april 2023 Elham Motamedi: User and Item Modeling Using Eudaimonic and Hedonic Characteristics for Recommender Systems

V ponedeljek, 17. aprila 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 17. april 2023 ob 16.00 v FAMNIT-VP2 in na daljavo prek ZOOM-a (https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)

-------------------------------------------------
PREDAVATELJICA: Elham MOTAMEDI
-------------------------------------------------

Elham Motamedi is a PhD student in Computer Science in the fields of recommender systems, machine learning and complex networks and a teaching assistant at the University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies. She is also a researcher at the HICUP Lab and member of the Department on Information Sciences and Technologies. Before enrolling into PhD studies, she obtained a Master's degree in networked systems from the University of Tehran in Iran.

---------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: User and Item Modeling Using Eudaimonic and Hedonic Characteristics for Recommender Systems
---------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

In her PhD thesis, the presenter aims to leverage eudaimonic and hedonic characteristics to model users and items. Furthermore, she plans to investigate whether these models can be used to improve the recommendations, particularly in movie recommendation systems. During her presentation, she will outline the motivations behind her research, review relevant literature, identify gaps in current research, and present an overview of the structure of her PhD thesis.

Predavateljica bo na seminarju predstavila dispozicijo svoje doktorske disertacije, ki jo opravlja pod mentorstvom izr. prof. Marka Tkalčiča.

Seminar bo potekal v angleškem jeziku, tokrat v hibridni izvedbi v FAMNIT-VP2 ter na daljavo prek Zoom-a (https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09)!!!

Vabljeni!      

petek, 17. marec 2023 Cuauhtli Campos: Designing Interactive Paper Display by Interlacing Physical and Digital Content Using Horizontal Touchscreens

V ponedeljek, 20. marca 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 20. marec 2023 ob 16.00 v FAMNIT-VP2

---------------------------------------------
PREDAVATELJ: Cuauhtli CAMPOS
---------------------------------------------

Cuauhtli Campos is a PhD student in Computer Science in the field of Human-Computer Interaction at the University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies and an assistant researcher at the InnoRenew CoE within the Wood Modification Group. His doctoral work is at the intersection of interactive paper technologies, immersive and playful reading experiences and augmented reality.

-----------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Designing Interactive Paper Display by Interlacing Physical and Digital Content Using Horizontal Touchscreens
-----------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Ubiquitous nature, versatility, and durability enabled the paper to maintain its importance in the digital age. It is not surprising there have been numerous attempts to combine paper with digital content. Despite this, several shortcomings persist, for example: these systems still demand users to handle or wear hardware (e.g. smartphones, HMDs) especially problematic when augmenting an activity that primarily happens on the paper (e.g. augmenting reading without disrupting the reading experience per se) or when users are expected to interact with paper for a longer period of time, such as when studying. Furthermore, these applications still require elaborated setups of hardware around the user (e.g. complex projector placement), which can also occlude the augmentation preventing the system from functioning as intended. One way to overcome these limitations is to place the screen emitting digital content and supporting interactivity (e.g. tablet computer or a tabletop display) beneath the paper. The paper thus becomes ``the screen'' on which the additional content is viewed whilst the interactivity is supported using the sensing capabilities of the underlying display. However, in such setups, the paper also acts as a barrier through which light and sensing signal need to pass degrading the quality of the displayed image and input sensing capabilities. This creates an interesting area for further investigation on the characterization of light transmittance through paper and on the exploration of methods to alter such optical properties. For example, could this be done through paper perforation or the addition of commonly available paper inks? Furthermore, no research explores how the presentation of digital content could be used to improve the perceived quality of imagery when viewed through paper. For example, could the movement of digital content such as text improve its resolution of it and make it more readable? On the other hand, no research explored how the conductivity of paper would affect the touch and stylus interaction as the paper is placed on top of a touch screen surface and how to overcome such interference The goal of this thesis is to contribute to the aforementioned gaps in knowledge through the characterisation of paper and ink properties and exploration of methods that could be used to improve interactivity and perceived quality of displayed imagery. All this will lead us to the overreaching goal of designing, constructing, and evaluating a novel Interactive Paper Display in which the light source is placed beneath the paper.

Predavatelj bo na seminarju predstavil dispozicijo svoje doktorske disertacije, ki jo opravlja pod mentorstvom izr. prof. Klena Čopiča-Puciharja in somentorstvom izr. prof. Matjaža Kljuna.

Seminar bo potekal v angleškem jeziku, tokrat v živo v FAMNIT-VP2 !!!

Vabljeni!      

sobota, 11. marec 2023 Masayukija Kanbara in Taishi Sawabe - Nara Institute of Science and Technology, Japan

V ponedeljek 13. marca 2023, ob 16.00 uri v VP1 (UP FAMNIT), bo Hicup-lab gostoval profesorje z laboratorija za oblikovanje interaktivnih medijev z Inštituta za znanost in tehnologijo - Nara, iz Japonske. V sklopu ponedeljkovega seminarja bosta predstavila svoje področje izr. prof. Masayukija Kanbara in doc. Taishi Sawabe, prisoten pa bo tudi direktor laboratorija (IMBD) Hirokazu Kato. 

ČAS/PROSTOR: 13. 3. 2023, 16.00, VP1 (UP FAMNIT)

----------------------------------------------
PREDAVATELJ: Masayuki Kanbara
----------------------------------------------

Dr. Masayuki Kanbara received a Ph.D. degree in engineering from Nara Institute of Science and Technology (NAIST) in 2002. He was an assistant professor at the Information Science Department at NAIST since 2002 and a visiting researcher at University of California, Santa Barbara in 2008-2009. He has been an associate professor at NAIST since 2010. Fields of research are focused on augmented reality, computer vision and Human-Robot Interaction.

----------------------------------------------
NASLOV: Gentle Stroke with Speech by Robot for Infusing Positive Emotion
----------------------------------------------

POVZETEK:

It has been demonstrated that the action of “stroking” has a relaxing effect on the body and mind. However, while some studies have shown the importance of “Gentle stroke with speech,” it has not been clarified how human actually perform the “Gentle stroke with speech” behavior. In this study, we analyzed the “Gentle stroke with speech” behavior with the aim of modeling the “talking and stroking behavior” in a situation in which a person is caring for another person.

----------------------------------------------
PREDAVATELJ: Taishi Sawabe
----------------------------------------------

He received his B.E. adviser, Prof. Ma, from Ritsumeikan University in the field of biomimetics robots. He received a Ph.D. from Adviser Prof. Hagita at the Ambient Intelligence Laboratory at NAIST. His research interest is Biomimetics robots, Human-Robot Interaction (HRI), Human Comfort, and Autonomous Vehicles. Mini projects: TSUNDERE-Interaction, VR Live Agent-Interaction.

----------------------------------------------
NASLOV: Comfort Intelligence for Autonomous Vehicles
----------------------------------------------

POVZETEK:

In this presentation, I will introduce an intelligence system that considers passengers’ comfort inside moving autonomous vehicles, which is called Comfort Intelligence (CI). In the research, anxiety reduction is mainly targeted. Anxiety comes from a variety of stress factors. In the field of vehicles, I defined stress in autonomous vehicles as Autonomous Vehicle Stress (AVS) to estimate, classify and consider reduction methods for reducing anxiety in autonomous vehicles. Moreover, anxiety is not only about stress but also has to consider motion sickness, called Autonomous Vehicle Motion Sickness (AVMS) which is mixed with car sickness and VR sickness in the future autonomous vehicle environment. Therefore, this study explains the importance of considering comfort intelligence (CI) by looking at previous research on anxiety, as well as discussing stress and motion sickness perspectives.

Vabljeni!

petek, 17. februar 2023 Giovanni Maria Angeletti: Replication in MongoDB

V ponedeljek, 20. februarja 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 20. februar 2023 ob 16.00 v FAMNIT-VP2

---------------------------------------------------------
PREDAVATELJ: Giovanni Maria ANGELETTI
---------------------------------------------------------

Giovanni Maria Angeletti is an Erasmus student from Italy (Modena) with a Mathematical background as he graduated in Maths in bachelor (in Camerino). For his Master degree he was searching something almost new to a “young” Mathematician and he found it in a Data Science study program. With the Erasmus at the UP FAMNIT he had the possibility to go deeper in some topics of interest, learning for example the Database management systems world, from which he had the idea to elaborate this seminar.

-----------------------------------------------
NASLOV: Replication in MongoDB
-----------------------------------------------

POVZETEK:

I will present my research paper that first gives a general overview about what data replication is and how it works in DBMSs, then the focus will be on how replication is performed in MongoDB.

Seminar bo potekal v angleškem jeziku, tokrat v živo v FAMNIT-VP2 !!!

Vabljeni!      

nedelja, 15. januar 2023 Jamolbek MATTIEV: Word Game Modeling using Character-level N-grams and Statistics

petek, 11. november 2022 Andrej MALEČKAR: Slot game development case study

V ponedeljek, 14. novembra 2022, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 14. november 2022 ob 16.00 v FAMNIT-VP2

---------------------------------------------
PREDAVATELJ: Andrej MALEČKAR
---------------------------------------------

Andrej Malečkar is an experienced software development team lead in the gambling and casino industry. He was born on 04.10.1990 in Koper and graduated in 2016 from the Faculty of Mathematics, Natural Sciences and Information Technologies, University of Primorska. His current work focuses on leading a team of front-end developers and delivering state-of-the-art on-line slot and table casino games while developing a brand new game engine.

-------------------------------------------------------------
NASLOV: Slot game development case study
-------------------------------------------------------------

POVZETEK:

In this presentation, we will go through all the development phases of a modern web-based slot game from start to finish. We will take a detailed look into all the technologies and best practices a good FE development team uses to overcome all the challenges that may arise during the development phase. After the presentation, we will present visual examples and code snippets from some of GameArt’s best-performing games. The meeting will end with a quick presentation of the company, its amazing work culture, and its brand new student programme.

Seminar bo potekal v angleškem jeziku, tokrat v živo v FAMNIT-VP2 !!!

Vabljeni!      

petek, 2. september 2022 Vanja MILESKI: Deep learning for churn prediction in retail using residual networks

torek, 16. avgust 2022 Arsen Matej GOLUBOVIKJ: Imputing Missing Answers In The World Values Survey

ponedeljek, 20. junij 2022 Nedim ŠIŠIĆ: Neural Network Based Classification of Brain Lesions

ponedeljek, 13. junij 2022 Martin JAKOMIN, Blaž MRAMOR: Data science at Zemanta

petek, 20. maj 2022 prof. Amira ŠERIFOVIĆ TRBALIĆ: Applications of deep learning for the medical data analysis

ponedeljek, 16. maj 2022 Vanja MILESKI: Deep learning for time series data using Inception and ResNet paradigms

ponedeljek, 9. maj 2022 Jakob POVŠIČ: Avtentikacija z dokazi ničelnega znanja

ponedeljek, 28. marec 2022 Aleksandar TOŠIĆ: Towards a more efficient routing in P2P networks using n-ary trees

ponedeljek, 21. marec 2022 Niki HROVATIN: Simulating Sensor Networks in NS-3

V ponedeljek, 21. marca 2022, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno

predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 21. marec 2022 ob 16.00 na daljavo

-----------------------------------------
PREDAVATELJ: Niki HROVATIN
-----------------------------------------

Niki Hrovatin  was born in Trieste, Italy, in 1994. He received the M.S. degree in Computer Science from the University of Primorska in 2020.
He is currently a Teaching Assistant and Ph.D. student at UP FAMNIT, and a Research Assistant at InnoRenew CoE, Izola, Slovenija.
His current research interests include sensor networks, distributed systems, and blockchain.

---------------------------------------------------------------
NASLOV: Simulating Sensor Networks in NS-3
---------------------------------------------------------------

POVZETEK:

The Wireless Sensor Network (WSN) is a monitoring system consisting of a large number of wireless devices forming a multi-hop network without infrastructure. It is of particular concern to research communication protocols designed explicitly for WSN to preserve network resources and privacy.
PPWSim is presented, a simulator developed to study a privacy-preserving communication protocol for edge data processing in WSNs. The simulator is based on the simulation environment nsnam NS3; therefore, it can be easily extended or used as a framework for developing other WSN simulators.

---------------------------------------------------------------------------------------------------
Seminar bo potekal v angleškem jeziku v Zoom "klepetalnici" na naslovu:

https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni!

ponedeljek, 7. marec 2022 Mohamed ELSAEED: Hello Flutter!

petek, 18. februar 2022 Andrej MALEČKAR: Slot game development case study

V ponedeljek, 21. februarja 2022, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 21. februar 2022 ob 16.00 na daljavo

---------------------------------------------
PREDAVATELJ: Andrej MALEČKAR
---------------------------------------------

Andrej Malečkar is an experienced Software development team lead in the Gambling and Casino industry. He was born on 04.10.1990 in Koper and graduated in 2016 from the Faculty of Mathematics, Natural Sciences and Information Technologies, University of Primorska. His current work is focused on leading a team of front-end developers delivering state-of-the-art online slot and table casino games and developing a brand new game engine.

-------------------------------------------------------------
NASLOV: Slot game development case study
-------------------------------------------------------------

POVZETEK:

In this presentation, we will go through all development phases of a modern web-based slot game from start to finish. We will look into detail on all the technologies and best practices a good FE development team uses to overcome all the challenges during the development phase. The presentation will be followed by visual examples and code snippets from some of the best-performing games from our company's portfolio. We will finish the meeting with a quick presentation of GameArt company, its amazing work culture, and its brand new student program.

---------------------------------------------------------------------------------------------------

Seminar bo potekal v angleškem jeziku v Zoom "klepetalnici" na naslovu:

https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni! 

četrtek, 10. februar 2022 Aleksandar TOŠIĆ and Domen VAKE: Faculty Programming Competition (FTP)

četrtek, 23. december 2021 Ivan MARKOVINOVIĆ: Auditory Brain Computer Interface Speller

četrtek, 2. december 2021 Sidra ASLAM: Decentralized Data Privacy and Security for the Web of Things

petek, 12. november 2021 Matej BABIČ: Matematične in računalniške aplikacije za napovedovanje izposoje koles v GoNM

četrtek, 4. november 2021 Peter KNEES: An Overview of Music Retrieval and Recommendation: From Describing Sound to Asking What is Fair

petek, 22. oktober 2021 M.Besher MASSRI: Tracking Innovations and Technologies in Artificial Intelligence

ponedeljek, 27. september 2021 Nedim ŠIŠIĆ: A new method for polygonization of connected areas in binary images

petek, 17. september 2021 Jordan DEJA: PIANO 2.0: An Augmented Piano prototype for Personalized Music Learning

ponedeljek, 13. september 2021 Elham MOTAMEDI: Prediction of eudaimonic and hedonic movie characteristics from subtitles

petek, 3. september 2021 Nuwan T. ATTYGALLE: Interactive Web Documentaries: A Case Study of Video Viewing Behaviour on iOtok

četrtek, 26. avgust 2021 Urška GERIČ: Genetska struktura in njen vpliv na telesne mase in oplojenost mladic srnjadi v Sloveniji

ponedeljek, 23. avgust 2021 Nuwan T. ATTYGALLE: Missing Interface - Gesture Recognition on Physical Objects using Radar Sensing

ponedeljek, 16. avgust 2021 Stephanie Furlan: Interakcija med droni in človekom

V ponedeljek, 16. avgusta 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 16. avgust 2021 ob 16.00 na daljavo

--------------------------------------------------
PREDAVATELJICA: Stephanie FURLAN
--------------------------------------------------

Stephanie Furlan je študentka magistrskega študijskega programa Računalništvo in informatika na UP FAMNIT. Trenutno se ukvarja z magistrskim delom, v katerem raziskuje področje interakcije med človekom in droni.

------------------------------------------------------------
NASLOV: Interakcija med droni in človekom
------------------------------------------------------------

POVZETEK:

Nedvomno prinaša tehnološki napredek sodobni družbi mnogotere olajšave in ponuja nešteto možnosti za udejanjenje vedno bolj lagodnega življenja. Hkrati odpira uvajanje novih tehnologij celo vrsto ne le praktičnih, temveč tudi etičnih vprašanj, ki jih taka uvedba predpostavlja. Droni so brezpilotni letalniki, katerih oblika in namembnost sta se skozi čas spreminjali. Nastali so kot vojaški pripomočki; ker se njihova izvorna uporaba veže ravno na bojno polje, lahko zasledimo, da se v povprečju sodobni človek na njihovo prisotnost v svojem okolju odziva negativno: gre najbrž le za posledico, kajti večinoma ni seznanjen z dejstvom, da je lahko njihova uporaba tudi koristna za vsakodnevno življenje. Naš namen je bralcu podati nekaj ključnih informacij o številnih možnostih za uporabo dronov tudi s strani povprečnega človeka in to pri vsakodnevnih praktičnih opravilih; v raziskavi bomo dlje korenito utemeljili, kako se človek odraža na prisotnost drona v svoji bližini in z njim interagira, kateri dejavniki vplivajo na njegovo reakcijo, katere tehnične plati lahko izboljšamo ali nadgradimo za njihovo učinkovitejšo uporabnost, predvsem pa njihovo stopnjo sprejemljivosti s strani ljudi. Področje, ki raziskuje interakcijo med človekom in droni, je v znanstvenih krogih poznano s kratico HDI (human-drone interaction) in ravno tej vsebini bomo namenili našo pozornost.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni! 

ponedeljek, 9. avgust 2021 Sead Hrustanović: Recognition of eudaimonic and hedonic qualities from song lyrics

V ponedeljek, 2. avgusta 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 2. avgust 2021 ob 16.00 na daljavo

-----------------------------------------------
PREDAVATELJ: Sead HRUSTANOVIĆ
-----------------------------------------------

Sead Hrustanović is a second year student of the master programme in Data Science at UP FAMNIT. He will be presenting his Master's thesis topic that he is completing under the supervision of assoc. prof. Marko Tkalcic and assist. prof. Branko Kavšek.

------------------------------------------------------------------------------------------------------
NASLOV: Recognition of eudaimonic and hedonic qualities from song lyrics
------------------------------------------------------------------------------------------------------

POVZETEK:

There have been many studies conducted on emotion recognition based on song lyrics. These studies help recommendation systems in a way that they tend to classify the emotion that is present in a song,and based on that the system recommends a similar song to what the user is already listening to. But what happens if we dig deeper and look further than just at the specific emotion a certain song gives. We can look for the hedonic and eudaimonic qualities within songs, through the song lyrics. We are creating a machine learning  model which will be able to recognize the percentage of hedonism and eudaimonia based on song lyrics.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

ponedeljek, 9. avgust 2021 Domen VAKE: Algoritem za pošiljanje sporočil v decentraliziranih omrežjih, ki temelji na pseudo naključnosti

V ponedeljek, 9. avgusta 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 9. avgust 2021 ob 16.00 na daljavo

--------------------------------------
PREDAVATELJ: Domen VAKE
--------------------------------------

Domen Vake je študent magistrskega študijskega programa Računalništvo in informatika na UP FAMNIT. Trenutno se ukvarja z magistrskim delom, v katerem raziskuje pošiljanje sporočil v decentraliziranih omrežjih, ki temelji na pseudo naključnosti.

---------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Algoritem za pošiljanje sporočil v decentraliziranih omrežjih, ki temelji na pseudo naključnosti
---------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Predstavljen bo inovativen algoritem za diseminacijo sporočil v popolnoma decentraliziranih sistemih. Motivacija za raziskavo prihaja iz področja tehnologije veriženja blokov in razvoja decentraliziranih omrežnih protokolov. Ena izmed ključnih omejitev tovrstnih sistemov je učinkovita diseminacija sporočil, ki imajo s strani sistemskega pogleda lahko naključen izvor. Cilj dobrega algoritma je, da v čim krajšem času vsa vozlišča prejmejo sporočilo. Najbolj razširjena in enostavna implementacija je t.i "flooding algoritem", ki zagotavlja, da bodo vsa vozlišča, ki so povezana v omrežje prejela sporočilo. Algoritmi, ki temeljijo na principu poplavljanja so neučinkoviti. Učinkovitost tovrstnih algoritmov običajno ocenjujemo z mero, ki opisuje koliko krat vozlišče prejme enako sporočilo. Optimalen algoritem bi zagotavljal, da bodo ne glede na izvor sporočila vsa vozlišča zanj izvedela in ga bo vsako vozlišče prejelo natanko enkrat.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

ponedeljek, 26. julij 2021 Mateja Jovanović: Predicting the gullibility of users from their online behaviour

Danes, v ponedeljek, 26. julija 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno 
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE 
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 26. julij 2021 ob 16.00 na daljavo

-----------------------------------------------
PREDAVATELJ: Mateja JOVANOVIĆ
-----------------------------------------------

Mateja Jovanović is a MSc student of the Data Science program at the University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies. He is conducting his MSc thesis under the supervision of Assoc. Prof. Marko Tkalčič and Assist. Prof. Vida Groznik.

-------------------------------------------------------------------------------------------------
NASLOV: Predicting the gullibility of users from their online behaviour
-------------------------------------------------------------------------------------------------

POVZETEK: 

Users can become victims of online scams. Their propensity for becoming victims depends on a personal characteristic called gullibility. In this work we explore if online behaviour, Twitter in particular, depends on the gullibility of users. Furthermore, we aim at devising a machine learning-based predictive model of gullibility. 

--------------------------------------------------------------------------------------------------- 

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

nedelja, 11. julij 2021 Elham MOTAMEDI: Predicting Music Relistening Behavior Using The ACT-R Framework

V ponedeljek, 12. julija 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno 
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE 
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 12. julij 2021 ob 16.00 na daljavo

--------------------------------------------------
PREDAVATELJICA: Elham MOTAMEDI
--------------------------------------------------

Elham Motamedi is a PhD student at UP FAMNIT under the supervision of prof. Marko Tkalčič. She completed her Master's degree of networked systems at the University of Tehran, Iran and her Bachelor's degree of information technology at the Isfahan University of Technology, Iran. Her research areas include recommender systems,  machine learning and complex networks.

--------------------------------------------------------------------------------------------------------
NASLOV: Predicting Music Relistening Behavior Using The ACT-R Framework
--------------------------------------------------------------------------------------------------------

POVZETEK: 

I will present the work that has been done to model the music relistening behavior using a well-established framework from psychology that considers the retrieval process of human memories, i.e., Adaptive Control of Thought—Rational (ACT-R). This work has been carried out in collaboration with researchers from Graz University of Technology and JKU linz.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

nedelja, 13. junij 2021 Nuwan T. ATTYGALLE: Sensing through materials

V ponedeljek, 14. junija 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 14. junij 2021 ob 16.00 na daljavo

-------------------------------------------------
PREDAVATELJ: Nuwan T. ATTYGALLE
-------------------------------------------------

Nuwan Tharanga Attygalle is a PhD student in Computer Science in the field of Human-Computer interactions and a teaching assistant at the University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies. He is also a member of the HICUP Lab at the Department of Information Sciences and Technologies.

-------------------------------------------------
NASLOV: Sensing through materials
-------------------------------------------------

POVZETEK: 

Gesture recognition has received increased attention with machine learning breakthroughs and the attainability of radar chips. In the real world, it often needs sensing through materials. In this work, we are studying how the degradation of radar signals affects the performance of gesture recognition.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

sreda, 2. junij 2021 Niki Hrovatin: In-Network Convolution in grid shaped Sensor Networks

V ponedeljek, 31. maja 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 31. maj 2021 ob 16.00 na daljavo

-----------------------------------------
PREDAVATELJ: Niki HROVATIN
-----------------------------------------

Niki Hrovatin is a teaching assistant and PhD student at the University of Primorska, Department of Information Sciences and Technologies, and an Assistant Researcher at the InnoRenew CoE. His current research interests include Wireless Sensor Networks, Security and Privacy, Machine Learning, and Blockchain.

------------------------------------------------------------------------------------------
NASLOV: In-Network Convolution in grid shaped Sensor Networks
------------------------------------------------------------------------------------------

POVZETEK: 

A Sensor Network consists of spatially distributed nodes deployed in a dynamic environment for specific monitoring purposes. We present the recent development of our use-case sensor network, a smart floor designed to detect falls. The smart floor is a grid-shaped sensor network in which each sensor node is sensing the local force applied on the floor. A Convolutional Neural Network (CNN) is used to recognize if the activity occurring over the smart floor is a person that fell on the floor or just activities of daily living like walking, moving objects, etc. Furthermore, we discuss a technique applicable only to grid-shaped sensor networks for distributed processing of convolutional layers on sensor nodes.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

sreda, 2. junij 2021 Lisi QARKAXHIJA: Network based predictive modeling

V ponedeljek, 7. junija 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno 
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE 
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 7. junij 2021 ob 16.00 na daljavo

-------------------------------------------
PREDAVATELJ: Lisi QARKAXHIJA
-------------------------------------------

Lisi Qarkaxhija is a second year student of the master programme in Data Science at UP FAMNIT. He will be presenting his Master's thesis topic that he is completing under the supervision of assoc. prof. Miklós Krész and PhD candidate László Hajdu.

--------------------------------------------------------------
NASLOV: Network based predictive modeling
--------------------------------------------------------------

POVZETEK: 

Real world networks can be classified into several categories, namely social networks, information networks, technological networks, biological networks, etc. Citation networks are one of the most famous examples of information networks. Various methods have been proposed to predict the citation count of papers in the future. We propose a novel approach for predicting the citation count of papers up to 10 years in advance by extracting features of nodes (papers) from a temporal citation network. These results can be further generalized to other type of networks.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

nedelja, 23. maj 2021 Jan Škorjanc: Uporaba asociacijskih pravil za klasifikacijo

V ponedeljek, 24. maja 2021, bo ob 16.30 uri prek spletnih orodij na daljavo izvedeno 
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE 
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 24. maj 2021 ob 16.30 na daljavo

---------------------------------------
PREDAVATELJ: Jan ŠKORJANC
---------------------------------------

Jan Škorjanc je absolvent magistrskega študijskega programa Računalništvo in informatika na UP FAMNIT. Trenutno se ukvarja z magistrskim delom, v katerem raziskuje uspešnost klasifikacijskih algoritmov, ki za svoje delovanje uporabljajo asociacijska pravila.

-----------------------------------------------------------------------
NASLOV: Uporaba asociacijskih pravil za klasifikacijo
-----------------------------------------------------------------------

POVZETEK: 

Klasifikacija in iskanje asociacijskih pravil sodita med najbolj uporabljene naloge podatkovnega rudarjenja. Za klasifikacijo je značilno, da na učni množici podatkov zgradi model, s katerim napove enega izmed atributov, ki mu pravimo razred. Asociacijska pravila razrednega atributa nimajo, končna množica pravil pa je lahko izpeljana za katerikoli atribut. V seminarju bomo obe področji združili tako, da bomo analizirali delovanje klasifikatorjev, ki uporabljajo asociacijska pravila. Algoritme smo zagnali na podatkovnih zbirkah pridobljenih iz repozitorija UCI ML in pri tem sledili metodologiji CRISP-DM. Cilj raziskave je bil algoritme med seboj primerjati, jih analizirati in določiti njihovo uspešnost.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

POZOR! Seminar se tokrat začne pol ure kasneje - ob 16:30.

Vabljeni!

nedelja, 16. maj 2021 Polygonization of connected areas in binary image

Jutri, v ponedeljek, 17. maja 2021, bosta ob 16.00 uri prek spletnih orodij na daljavo izvedeni 
dve predavanji v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE 
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 17. maj 2021 ob 16.00 na daljavo

1. predstavitev:

-------------------------------------
PREDAVATELJ: Nedim ŠIŠIĆ
-------------------------------------

Nedim Šišić is a first year student of the master programme in Computer Science at UP FAMNIT. He will be presenting his Research seminar topic that he completed under the supervision of prof. Martin Milanič.

---------------------------------------------------------------------------------
NASLOV: Polygonization of connected areas in binary image
---------------------------------------------------------------------------------

POVZETEK: 

In image processing, vectorization is the conversion of raster images to vector images. A special kind of vectorization is polygonization, which deals with finding polygonal approximations. Most existing vectorization methods process entire images, which is unnecessary if we are only interested in a single part of an image. We investigate approaches to polygonizing connected areas in binary images. By restricting the scope of vectorization, we reduce its time and memory requirements.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

2. predstavitev:

----------------------------------------------
PREDAVATELJ: Albert KHAIDAROV
----------------------------------------------

Albert Khaidarov is a first year student of the master programme in Computer Science at UP FAMNIT. He will be presenting his Research seminar topic that he completed under the supervision of assist. prof. Dávid Balázs.

-------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: A Hybrid Clustering Algorithm for solving the Vehicle Routing Problem in Waste Management
-------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK: 

Proper collection of waste is important for building sustainable and livable cities, but it remains a great challenge for us. The purpose of my research is to find an effective solution approach for the Vehicle Routing Problem in waste management. My work involves the usage of the best known clustering algorithm K-Means.This method performs a single clustering of the vertex set and then determines a vehicle route on each cluster. For optimization, solutions of the clustering algorithm can be extended with different heuristic and metaheuristic methods.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

petek, 7. maj 2021 Zakaj je delodajalec Actual I.T. d.d. prava izbira za vas?

V ponedeljek, 10. maja 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 10. maj 2021 ob 16.00 na daljavo

-----------------------------------------------------------------------
PREDAVATELJA: Magda ŠTURMAN in Boštjan PETELIN
-----------------------------------------------------------------------

mag. Magda Šturman, Vodja OE Kadri, pravne in splošne zadeve v Actualu I.T. d.d. Magistrirala je na Fakulteti za družbene vede iz smeri Managmenta kadrov in delovnih razmerjih. Ima bogate delovne izkušnje na kadrovskem področju, pa tudi kot predavateljica.

mag. Boštjan Petelin, BU direktor Transport&Logistic v Actualu I.T. d.d. Magistriral je na Ekonomski fakulteti v Ljubljani. Ima bogate delovne izkušnje na področju prodaje, projektnega vodenja in poslovne informatike.

--------------------------------------------------------------------------------------
NASLOV: Zakaj je delodajalec Actual I.T. d.d. prava izbira za vas?
--------------------------------------------------------------------------------------

POVZETEK: 

Predstavili vam bomo podjetje Actual I.T. d.d., ki s FAMNIT-om odlično sodeluje že vrsto let. Actual ponuja celovite informacijske rešitve, ki so podpora poslovnim procesom na posameznih področjih poslovanja. Actual je del skupine DBA Group iz Italije. Skupina Actual je prisotna na trgih Slovenije, Hrvaške, Bosne in Hercegovine, Srbije ter Italije. Z jasnimi strateškimi usmeritvami in razvojnimi prioritetami postajamo pomemben igralec na trgih jugovzhodne Evrope, EU, Južne Amerike, Afrike in Rusije.
Na srečanju bomo kratko predstavili kdo smo, kaj delamo, kaj potrebujemo, kaj nudimo in kako je pri nas.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Predavanje je namenjeno predvsem študentom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

ponedeljek, 3. maj 2021 Matevž Mak: P2P omrežja in simulatorji

četrtek, 15. april 2021 Jordan Aiko DEJA: Adaptive Visualisations Using Spatiotemporal and Heuristic Models to Support Piano Learning

četrtek, 8. april 2021 Sidra ASLAM: Secure and Privacy-Aware Blockchain Design: Requirements, Challenges and Solutions

V ponedeljek, 12. aprila 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 12. april 2021 ob 16.00 na daljavo

-----------------------------------------
PREDAVATELJICA: Sidra ASLAM
-----------------------------------------

Sidra Aslam received her master's degree in computer science from the COMSATS University Islamabad, Pakistan in January 2017. During this period, she worked on research projects and published research papers in scholarly journals and conference proceedings. In 2015, she received the best research paper award at the National Software Engineering Conference (NSEC), IEEE in Pakistan. She is currently an Assistant Researcher at the InnoRenew CoE, a teaching assistant and a Ph.D. student at the Faculty of Mathematics, Natural Sciences and Information Technologies, University of Primorska, Slovenia. Her current research interests include information security and privacy, blockchain, and semantic web technologies.

----------------------------------------------------------------------------------------------------------------------------------
NASLOV: Secure and Privacy-Aware Blockchain Design: Requirements, Challenges and Solutions
----------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

During the last decade, distributed ledger solutions such as blockchain have gained significant attention due to their decentralized, immutable, and verifiable features. However, the public availability of data stored on the blockchain and its link to users may raise privacy and security issues. In some cases, addressing these issues requires blockchain data to be secured with mechanisms that allow on-demand (as opposed to full) disclosure. In this seminar, we give a comprehensive overview of blockchain privacy and security requirements, and detail how existing mechanisms answer them. We provide a taxonomy of current attacks together with related countermeasures. We present a thorough comparative analysis based on various parameters of state-of the-art privacy and security mechanisms, we provide recommendations to design secure and privacy-aware blockchain, and we suggest guidelines for future research.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

četrtek, 25. marec 2021 Vito JANKO: Choosing the right counter-measures to stop COVID-19 infections

V ponedeljek, 29. marca 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 29. marec 2021 ob 16.00 na daljavo

------------------------------------
PREDAVATELJ: Vito JANKO
------------------------------------

Vito Janko received his Ph.D. at the Jožef Stefan Institute in 2020, specializing in interpreting sensor data from various wearable devices -- and doing so in an energy-efficient manner. During his work for the institute he collaborated in many national and EU funded projects. He also participated in various data-science competitions: being the first author for the winning submission at the SHL competition, as well as winning the Cooking recognition challenge. He was recently a part of the team that achieved second place in the XPRIZE: Pandemic Response Challenge. In addition, he is active in the Slovenian Artificial Intelligence Society, where he acts as a member of the executive board.

------------------------------------------------------------------------------------------------------
NASLOV: Choosing the right counter-measures to stop COVID-19 infections
------------------------------------------------------------------------------------------------------

POVZETEK: 

A team from Jožef Stefan recently achieved second place in the prestigious international competition -- XPRIZE: Pandemic Response Challenge, and doing so, won half of the 500000$ prize fund. The competition was focused on answering very topical questions, such as how different counter-measures (e.g. lockdowns, school closing, etc.) affect the spread of COVID-19 infections and which of them to choose to best fight the pandemic. A member of the winning team will present their solution of using a novel combination of epidemiological models, machine learning and evolutionary algorithms to create one of the world’s best performing models.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

sreda, 17. marec 2021 Matej FILIPOVIĆ: Spletno orodje za svetovanje pri Scrum-u

V ponedeljek, 22. marca 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 22. marec 2021 ob 16.00 na daljavo

------------------------------------------
PREDAVATELJ: Matej FILIPOVIĆ
------------------------------------------

Matej Filipović je študent magistrskega programa 2. stopnje Računalništvo in informatika na UP FAMNIT. Z delom kot razvijalec spletnih strani, sistemski analitik, lastnik izdelka in strokovnjak za tehnične rešitve v agilnih in tradicionalnih podjetjih je imel priložnost razumeti kako deluje razvoj iz različnih zornih kotov. Le-to mu pomaga razumeti širšo sliko in s tem položaj različnih zaposlenih na različnih položajih znotraj podjetij. Pri delu z različnimi Scrum ekipami se je soočil z veliko nepravilne uporabe Scrum ogrodja. Večinoma vodstvo in zaposleni niso razumeli smiselnost uporabe privzete Scrum strukture in so po svoji presoji spreminjali Scrum brez razumevanja posledic. Prav zato se sedaj posveča predstavitvi posledic in predlogom za izboljšave, da bi več ljudi bolje razumelo kaj se lahko zgodi, če posamezen del Scrum ogrodja prilagodijo.

---------------------------------------------------------------------
NASLOV: Spletno orodje za svetovanje pri Scrum-u
---------------------------------------------------------------------
POVZETEK: 

Scrum je agilna metodologija, ki se vse bolj uporablja v poslovnem svetu. Večinoma se uporablja na področju razvoja programske opreme, ki vsebuje zelo kompleksne procese, veliko različnih možnosti implementacije, veliko usklajevanja z različnimi interesnimi skupinami in veliko razumevanja končnega uporabnika. Za uspešno uporabo Scruma je potrebno imeti prilagojeno strukturo organizacije in pravilno postavljene Scrum procese, ki omogočajo tekoče delo na projektih. Veliko podjetij želi uporabljati Scrum, pri tem pa ne upoštevajo vseh dejavnikov in ne prilagodijo okolja ter se zaradi tega lahko uspešnost projektov zmanjša pri uvedbi Scruma. Naš cilj je izdelava spletne strani z integriranim vprašalnikom. Z odgovori iz vprašalnika bomo ugotovili na katerih področjih podjetje nepravilno uporablja Scrum in jim bomo predstavili za specifična področja posledice nepravilne uporabe in predloge za izboljšavo.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

četrtek, 11. marec 2021 Sead JAHIĆ: Annotated lexicon for sentiment analysis in Bosnian

V ponedeljek, 15. marca 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 15. marec 2021 ob 16.00 na daljavo

------------------------------------------
PREDAVATELJ: Sead JAHIĆ
------------------------------------------

Sead Jahić is a 3rd year PhD student of computer science at UP FAMNIT. His main research focus is on Language Technologies and Sentiment Analysis. He is also a teaching assistant at University of Primorska, Department of Information Sciences and Technologies.

-------------------------------------------------------------------------------------
NASLOV: Annotated lexicon for sentiment analysis in Bosnian
-------------------------------------------------------------------------------------
POVZETEK: 

The talk presents the first sentiment annotated lexicon of Bosnian language. The language coverage of the lexicon is evaluated using two corpora. The usability of the lexicon was already proven on a Tweeter-based comparison.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

petek, 5. marec 2021 Raziskovalna infrastruktura CLARIN.SI

V ponedeljek, 8. marca 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 8. marec 2021 ob 16.00 na daljavo

------------------------------------------
PREDAVATELJ: Tomaž ERJAVEC
------------------------------------------

Tomaž Erjavec je zaposlen na Odseku za tehnologije znanja Instituta Jožef Stefan, kjer se ukvarja s področji jezikovnih tehnologij, standardov zapisa jezikovnih virov in digitalne humanistike. Zaposlen je bil tudi na Univerzi v Edinburgu in na Tokijski univerzi ter poučeval na Mednarodni podiplomski šoli Jožefa Stefana, na Univerzi v Gradcu in Univerzi v Novi Gorici. Je nacionalni član odbora ISO TC37 SC4 "Language resource management" in nacionalni koordinator raziskovalne infrastrukture CLARIN.SI.

-----------------------------------------------------------------
NASLOV: Raziskovalna infrastruktura CLARIN.SI
-----------------------------------------------------------------
POVZETEK: 

V predavanju bo predstavljena raziskovalna infrastruktura za jezikovne vire in tehnologije CLARIN.SI, del evropske infrastrukture CLARIN. Na kratko bo povzet organizacijski okvir CLARIN(.SI), nato pa storitve, ki jih nudi raziskovalcem in študentom s področij računalniškega jezikoslovja in digitalne humanistike. Bolj nadrobno bomo obravnavali CTS certificirani repozitorij CLARIN.SI, s katerega je mogoče prevzeti raznovrstne jeziko(slo)vne podatkovne množice, kot tudi arhivirati lastne, s čimer prispevamo k uresničevanju koncepta odprte znanosti.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

nedelja, 28. februar 2021 Jamolbek MATTIEV: The effect of distance metric "directness" on class association rules

V ponedeljek, 1. marca 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 1. marec 2021 ob 16.00 na daljavo

----------------------------------------------
PREDAVATELJ: Jamolbek MATTIEV
----------------------------------------------

Jamolbek Mattiev obtained his PhD degree in Computer Science at UP FAMNIT. He got his Master degree in Computer Science from National University of Uzbekistan and was awarded with first degree diploma at “the best Master Dissertation Work of Uzbekistan” competition in his master studies. He also studied at Turin Polytechnic University (Italy) in his master study as an exchange student. He is doing his research in the field of Data Mining. His research fields include Artificial Intelligence, Data Mining, Machine Learning. In particular, the sub-fields of Supervised and Unsupervised Learning, Frequent Pattern Discovery, Association Rule Learning, Classification and Clustering.

----------------------------------------------------------------------------------------------------------
NASLOV: The effect of distance metric "directness" on class association rules
----------------------------------------------------------------------------------------------------------
POVZETEK: 

Huge amounts of data are being collected and analyzed nowadays. By using the popular rule-learning algorithms, the number of rules discovered on those big datasets can easily exceed thousands. To produce compact and accurate classifiers, such rules have to be grouped and pruned. To group the rules, we need appropriate distance metrics, because distance metrics are very important in clustering applications. To solve the above-mentioned problem, we present new methods (use different distance metrics) that are able to reduce the number of class association rules produced by classical class association rule classifiers, while maintaining an accurate classification model that is comparable to the ones generated by state-of-the-art classification algorithms. We also present how distance metrics are affecting the clustering of class association rules.
Experimental results performed on selected datasets from the UCI ML repository show that our methods are able to learn classifiers containing significantly less rules than state-of-the-art rule learning algorithms on datasets with larger number of examples. On the other hand, classification accuracies of the newly developed methods are not significantly different from state-of-the-art rule-learners on most of the datasets.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://upr-si.zoom.us/j/297328207

Vabljeni!

četrtek, 18. februar 2021 Marko NOVAK: Potisna obvestila in njihova uporaba v sodobnih sistemih obveščanja

V ponedeljek, 22. februarja 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 22. februar 2021 ob 16.00 na daljavo

----------------------------------------
PREDAVATELJ: Marko NOVAK
----------------------------------------

Marko Novak je študent magistrskega študijskega programa Računalništvo in informatika na UP FAMNIT. Trenutno se, poleg rednega dela na področju menedžmenta v gostinstvu in turizmu ter projektnega vodenja, ukvarja z magistrskim delom, v katerem skuša razviti mobilno aplikacijo za pametno obveščanje strank o prostih terminih.

----------------------------------------------------------------------------------------------------------
NASLOV: Potisna obvestila in njihova uporaba v sodobnih sistemih obveščanja
----------------------------------------------------------------------------------------------------------

POVZETEK:

Sodobni informacijski sistemi nudijo uporabnikom vse več in več koristnih informacij na vseh področjih. Prav zaradi tako velike količine podatkov so sistemi obveščanja ključni za učinkovito komunikacijo z uporabniki. Vsi si želimo, da bi podatki, ki jih prejemamo bili kar se da uporabni in pravočasni, hkrati pa tudi nemoteči. Na seminarju bodo predstavljena potisna obvestila, kot eden od možnih načinov obveščanja v sodobnih informacijskih sistemih.

---------------------------------------------------------------------------------------------------

Predstavitev v okviru Ponedeljkovega seminarja računalništva in informatike se šteje kot del obveznosti pri predmetu Raziskovalni seminar II.

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave: https://upr-si.zoom.us/j/297328207

Vabljeni! 

sreda, 13. januar 2021 Vida GROZNIK: Osnove priporočilnih sistemov

Tokrat izjemoma v petek, 15. januarja 2021, bo ob 9.30 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 15. januar 2021 ob 9.30 na daljavo

--------------------------------------------
PREDAVATELJICA: Vida GROZNIK
--------------------------------------------

Vida Groznik je asistentka za računalništvo na Fakulteti za matematiko, naravoslovje in informacijske tehnologije na Univerzi na Primorskem ter raziskovalka v Laboratoriju za umetno inteligenco na Fakulteti za računalništvo in informatiko Univerze v Ljubljani. Doktorirala je leta 2018 z delom, ki je tesno povezovalo umetno inteligenco in nevrologijo. Je (so)avtorica več raziskovalnih člankov in poglavij v knjigah s področja umetne inteligence v medicini. Pridobila in delala je na več projektih financiranih s programov EU, Ministrstva za izobraževanje, znanost in šport ter Slovenskega podjetniškega sklada.

-------------------------------------------------------
NASLOV: Osnove priporočilnih sistemov
-------------------------------------------------------

POVZETEK:
Priporočilni sistemi so v zadnjem desetletju doživeli razcvet in so čedalje bolj prisotni tudi v našem vsakdanjem življenju. Z uporabo priporočilnih sistemov nam ponudniki določenih storitev lahko prikazujejo vsebine, ki bodo za nas še posebej zanimive, predvsem učinkovito pa pristope priporočilnih sistemov izkoriščajo (spletni) trgovci in ponudniki multimedijskih vsebin (npr. Netflix). Pogledali si bomo osnove priporočilnih sistemov, kaj so, kako delujejo in kakšne so njihove koristi. Pogledali si bomo tudi eno izmed tehnik skupinskega filtriranja.

---------------------------------------------------------------------------------------------------

Seminar bo hkrati preizkusno predavanje za prvo izvolitev v pedagoški naziv visokošolska učiteljica - docentka za področje »Računalništvo in informatika«.

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave: https://upr-si.zoom.us/j/89812476390?pwd=bkVwZG5Rc2RMKzZLTlhDNDVYcU9oZz09

Vabljeni!

sreda, 6. januar 2021 Daring creativity: about the new project LOOSE CELLS – Innovating at the Crossfield of Art and Science and how to become part of it

V ponedeljek, 11. januarja 2021, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 11. januar 2021 ob 16.00 na daljavo

------------------------------------------------------------------------------------------------------------------------
PREDAVATELJA:
Peter PURG (uvodna predstavitev) in Črtomir TAVZES (kratka predstavitev laboratorijev InnoRenew CoE)
------------------------------------------------------------------------------------------------------------------------

Peter Purg currently leads the New Media module in the Digital//Media Arts and Practices graduate//postgraduate programme at the School of Arts, University of Nova Gorica, where he acts as Associate Professor, projects coordinator as well as expert across realms of digital culture and media. Having obtained a PhD in media art, communication science and literature from the University of Erfurt (Germany), his scientific inquiries now include media arts pedagogy, interdisciplinary collaboration and innovation, media art and media ecology. His artistic interests range from (lecture) performances and intermedia installations to public-space interventions as well as participatory creative processes. He is active in the field of cultural and higher education policymaking, assessment and quality assurance. Peter Purg currently leads the interdisciplinary MAST – Module in Art, Science and Technology project (DG Connect) – as well as School of Arts' teams in projects such as KONS - Platform for Investigative Arts (EU Cohesion), DIVA - Art:Biz Innovation Ecosystem (Interreg SI-IT), EmindS (Erasmus+) and TV Free Europe (Creative Europe). He curated the 20th international media/contemporary art festival Pixxelpoint 2019. Full CV at http://au.ung.si/peterpurg.

Dr. Črtomir Tavzes is a researcher at the InnoRenew CoE, an assistant research scientist at the University of Primorska, and conservation restoration adviser at the Institute for the Protection of Cultural Heritage of Slovenia. He earned his PhD in biotechnology in 2003 from the University of Ljubljana, Slovenia. In the following two years, he was a postdoctoral fellow at the Metropolitan Museum of Art in New York, where he continued working until 2008. Upon the return to Slovenia, he also served as the director of the Institute of Wood Science and Technology, and Sustainable Development (until 2014). His research experience spans from enzymatic wood degradation and wood liquefaction through wood pest control to the immunological detection of material substance of cultural heritage objects.

------------------------------------------------------------------------------------------------------------------------
NASLOV:
Daring creativity: about the new project LOOSE CELLS – Innovating at the Crossfield of Art and Science and how to become part of it
------------------------------------------------------------------------------------------------------------------------

POVZETEK:
The project LOOSE CELLS – Innovating at the Crossfield of Art and Science is dedicated to creation and innovation based on the blending of science, art and technology. In this way, it joins those intersectoral collaborations, which have already aroused a lot of international interest, as they can inspire the development of social and economic innovations. Innovation is also the goal of the project. The main activity will be the co-creation of an “art-science object”, which will be designed and created by students of diverse levels and backgrounds. It will be realised under the mentorship of Assoc. Prof. Peter Purg, PhD from School of Arts at University of Nova Gorica, with the advices of InnoRenew CoE experts and with the support of Assoc. Prof. Tilen Žbona, PhD from the Faculty of Education as well as the artists, producers and technicians within the PiNA association or the RUK network. In the seminar, you will learn more about the programme of the project and how to become part of. You will be also invited to discuss any questions with the representatives of the project.

------------------------------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.

Do predavanja dostopate tako, da se povežete prek sledeče povezave: https://us02web.zoom.us/j/297328207

Vabljeni!

torek, 5. januar 2021 Maheshya WEERASINGHE: Instructional Guidance in Extended Reality for Learning

V ponedeljek, 21. decembra 2020, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 21. december 2020 ob 16.00 na daljavo

-----------------------------------------------------------
PREDAVATELJICA: Maheshya WEERASINGHE
-----------------------------------------------------------

Maheshya Weerasinghe, Computer Science (PhD 3rd Year) HICUP Lab, International joint degree program with University of St.Andrews, UK, Research Areas: Human-Computer Interaction, Extended Realities, e-Learning and Cognitive Augmentation.

---------------------------------------------------------------------------------------------
NASLOV: Instructional Guidance in Extended Reality for Learning
---------------------------------------------------------------------------------------------
POVZETEK: 

Experiential learning refers to the process of learning through experience or more specifically "learning through reflection on doing". These experiences can also be simulated in Extended Reality (XR) – interactive environments generated by computer technology combining real and virtual worlds. Such systems have proved in the past as excellent tools for providing guidance to teach different skills and activities. However, there are still many questions that remain to be answered, for instance: How to improve instructional guidance through "personalisation"? How to adapt the guidance to facilitate learners move from one stage to another in the experiential learning cycle? How to design and implement guidance in adaptive learning environments where the learning system needs to take over all or some of the tasks commonly conduct by educators and overall, how personalisation of instructional guidance influence the outcomes of an experiential learning task. To contribute to the above research questions we aim to introduce a comprehensive design space grounded in (i) XR technology, and (ii) theoretical underpinnings of learning and guidance. Then use these dimensions to describe key design decisions in prior work and elucidate existing gaps. Besides, following the design space, we intend to build an adaptive, personalised instructional guidance system to facilitate learners to move spontaneously from one stage to another in the experiential learning cycle.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://us02web.zoom.us/j/297328207

Vabljeni!

sobota, 28. november 2020 Challenges for Data Mining in Distributed Sensor Networks

V ponedeljek, 30. novembra 2020, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 7. december 2020 ob 16.00 na daljavo

-----------------------------------------
PREDAVATELJ: Branko KAVŠEK
-----------------------------------------

Branko Kavšek has a PhD in Computer Science from the University of Ljubljana. He is an assistant professor at the University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies, a researcher at the Department of Information Sciences and Technologies and member of the Artificial Intelligence Laboratory at the Jozef Stefan Institute in Ljubljana. His research fields include Artificial Intelligence, Data Mining, Machine Learning. In particular, the sub-fields of Supervised and Unsupervised Learning, Frequent Pattern Discovery and Association Rule Learning, Learning Probabilistic Models and Bayesian Networks Learning, Clustering, and Data Mining applied to Big Data.

---------------------------------------------------------------------------------------------
NASLOV: Challenges for Data Mining in Distributed Sensor Networks
---------------------------------------------------------------------------------------------

POVZETEK: 

In this seminar we will present an overview of Distributed Sensor Networks (DSNs) with particular emphasis on Wireless Sensor Networks (WSNs) and the use of Data Mining (DM) to analyze the data collected by WSNs. We will start by giving an overview of the history of sensor networks, stressing the technological issues, distributed data management and distributed hypothesis formation. In the second part we will present the application of simple DM methods on data collected during the ARRS project "Autonomic edge computing for air quality monitoring". The last part of the seminar will be devoted to presenting evolution opportunities and challenges.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://us02web.zoom.us/j/297328207

Vabljeni!

četrtek, 29. oktober 2020 Đorđe KLISURA: Analyzing Global Terrorism Database with R

V ponedeljek, 2. novembra 2020, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 2. november 2020 ob 16.00 na daljavo

-----------------------------------------
PREDAVATELJ: Đorđe KLISURA
-----------------------------------------

Đorđe Klisura comes from Serbia. He is a first-year student of Data
Science program at UP FAMNIT. He graduated from UP FAMNIT and received
Bachelor’s degree in Computer Science.

-------------------------------------------------------------------------
NASLOV: Analyzing Global Terrorism Database with R
-------------------------------------------------------------------------

POVZETEK:
 With the increase of terrorist activity around the world, it has become
more important than ever to analyze and understand these activities over
time. Although the data on terrorist activities are detailed and
relevant, the complexity of the data has rendered the understanding and
analysis difficult. We present a visual analytical approach to
effectively identify related entities. We will be working with The
Global Terrorism Database (GTD), that is an open-source database
including information on domestic and international terrorist attacks
around the world from 1970 through 2017, and now includes more than
180,000 cases.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://us02web.zoom.us/j/297328207

Vabljeni! 

petek, 25. september 2020 Sead JAHIĆ: Handling tweet opinion by using weighted lexicon and lexicon-based approach

V ponedeljek, 28. septembra 2020, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 28. september 2020 ob 16.00 na daljavo

-----------------------------------
PREDAVATELJ: Sead JAHIĆ
-----------------------------------

Sead Jahić is a teaching assistant at University of Primorska, Department of Information Sciences and Technologies.
After receiving High School diploma, he went to University of Tuzla (UNTZ), where in 2012 he graduated as Mathematician (Math Teacher).
His first working experience was teaching assistant at UNTZ, in the field of Applied Mathematics and Computer Science.
The main topic of his research is Sentiment Analysis of languages, where the focus is on developing overall sentiment analysis for West Balkan languages from the same West Slavic group.
The idea is to use different Machine Learning and Deep Learning techniques in sentiment analysis with those languages, and show huge connectivity between them.

-----------------------------------------------------------------------------------------------------------------------
NASLOV: Handling tweet opinion by using weighted lexicon and lexicon-based approach
-----------------------------------------------------------------------------------------------------------------------

POVZETEK:

In this seminar, we will present an introduction to creating a lexicon with weight values of words from our database. Given that the lexicon is made in such a way that the amount / number of positive and negative words affects the final outcome, we come to the conclusion that at some point, especially in neutral sentiment, we have words whose power can change the polarity of neutral to positive / negative. Therefore, when calculating sentiment, we relied on the weight lexicon created for a given amount of data.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://us02web.zoom.us/j/297328207

Vabljeni! 

torek, 22. september 2020 Patrik KOCJANČIČ: Primerjava vnosa besedila v virtualnem okolju na različnih postavitvah tipkovnice

Tokrat, izjemoma v četrtek, 24. septembra 2020, bo ob 10.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 24. september 2020 ob 10:00 na daljavo

--------------------------------------------
PREDAVATELJ: Patrik KOCJANČIČ
--------------------------------------------

Patrik Kocjančič je študent magistrskega študijskega programa Računalništvo in informatika na UP-FAMNIT. Trenutno se ukvarja z magistrskim delom, v katerem skuša najti optimalno rešitev (postavitev tipkovnice) za vnos besedila v virtualnem okolju.

------------------------------------------------------------------------------------------------------------------------------
NASLOV: Primerjava vnosa besedila v virtualnem okolju na različnih postavitvah tipkovnice
------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Vnos besedila je precej raziskano področje tako v realnem svetu kot tudi v virtualnem svetu. Raziskovalci preučujejo različne načine vnosa besedila bodisi tip vnosa bodisi vnos na različnih postavitvah tipkovnice.  V tem seminarju bomo predstavili področje tehnologije VR, pripravo virtualnega okolja, študijo, ki je potekala v okviru magistrskega dela  ter rezultate le-te. Cilj študije je bil preizkusiti različne postavitve tipkovnice in le-te primerjati s standardom QWERTZ. Testirali smo 4 različne postavitve tipkovnice, to so: QWERTZ, DVORAK, OPTI in CIRCLE. Na koncu bo potekala še krajša razprava o rezultatih in kakšna možna izboljšava oz. predlogi pri izvedbi nadaljnjih študij.

---------------------------------------------------------------------------------------------------

Predavatelj bo svoj prispevek predstavil v okviru Raziskovalnega seminarja na magistrskem študijskem programu Računalništvo in informatika.

Predavanje bo potekalo v slovenskem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://us02web.zoom.us/j/297328207

Vabljeni! 

sobota, 19. september 2020 Jordan Aiko DEJA: Revisiting AR Piano Projection

petek, 11. september 2020 Jamolbek MATTIEV: Distance based Clustering of Class Association Rules to Build a Compact, Accurate and Descriptive Classifier

sreda, 9. september 2020 Sead JAHIĆ: Determining sentiment of tweets using first Bosnian lexicon and (AnA)-affirmative and non-affirmative words

sreda, 26. avgust 2020 Niki HROVATIN: Naivni Bayes in umetna konvolucijska nevronska mreža za identifikacijo padcev s pomočjo pametnih tal

nedelja, 5. julij 2020 Cuauhtli CAMPOS: Pinhole Paper: Making Static Objects Perceptually Dynamic with Rear Projection on Perforated Paper

nedelja, 31. maj 2020 Nuwan ATTYGALLE: Pandemic era app development

nedelja, 24. maj 2020 Jamolbek MATTIEV: Clustering class association rules to form a Compact and Meaningful Associative Classifier

petek, 15. maj 2020 Cuauhtli CAMPOS: Interactive paper with back print illumination and rear-projection

V ponedeljek, 18. maja 2020, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 18. maj 2020 ob 16.00 na daljavo

------------------------------------------
PREDAVATELJ: Cuauhtli CAMPOS
------------------------------------------

Cuauhtli Campos is a PhD student in Computer Science in the field of Human-Computer Interaction at the University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies.

-------------------------------------------------------------------------------------------------------------------------
NASLOV: Interactive paper with back print illumination and rear-projection
-------------------------------------------------------------------------------------------------------------------------

POVZETEK:

We live in an era where our society remains to be heavily dependent on paper. The simplicity, sensory richness and versatility enabled the paper to maintain its importance in this digital age. However despite these obvious advantages of paper our lives are becoming more and more digital. This introduces a need for new solutions that will integrate digital technology with paper whilst maintaining its unique aforementioned properties. This talk presents the findings of a study of rear projection and back print illumination using paper as screen material. 

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.

Do predavanja dostopate tako, da se povežete prek sledeče povezave: https://us02web.zoom.us/j/297328207

Vabljeni! 

nedelja, 10. maj 2020 Elham MOTAMEDI: User-centric multimedia characteristics: A Survey

nedelja, 3. maj 2020 Vladimir BATAGELJ: NetsJSON - part 2

nedelja, 19. april 2020 Sidra ASLAM: Personal Information Management on Distributed Ledger Technology

V ponedeljek, 20. aprila 2020, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 20. april 2020 ob 16.00 na daljavo

-----------------------------------------
PREDAVATELJICA: Sidra ASLAM
-----------------------------------------

Sidra Aslam is a PhD student at the University of Primorska. She did her Master in Computer Science from COMSATS University, Pakistan. She followed a complementary Master in 2019 at the University of Saarland, Germany. Her research interests include information security and privacy, blockchain, and semantic web technologies.

-----------------------------------------------------------------------------------------------------------
NASLOV: Personal Information Management on Distributed Ledger Technology
-----------------------------------------------------------------------------------------------------------

POVZETEK:

In wood supply chain environments, stakeholders need full traceability of individual products, and at the same time, they need protection from disclosure of their global activity. Existing solutions rely on centralized system to manage privacy-sensitive data and suffer from single point of failure, lack of trust, and performance issues. Distributed ledger technology ensures data security, however, user-sensitive information remains publicly available, which leads to privacy issues. In our research, we explore how to protect sensitive information over distributed ledger technology while providing product traceability through the supply chain.
In this presentation, we will illustrate our research problem with a use case scenario inspired from a wood supply chain. Then, we will give a brief overview of the state of the art, before describing open issues and discussing possible solutions that we are currently exploring.

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.
Do predavanja dostopate tako, da se povežete prek sledeče povezave:

https://us02web.zoom.us/j/297328207

Vabljeni!

petek, 27. marec 2020 András BÓTA: Network-based framework for estimating the risk factors of epidemic spreading

V ponedeljek, 30. marca 2020, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 30. marec 2020 ob 16.00 na daljavo

------------------------------------------
PREDAVATELJ: András BÓTA
------------------------------------------

András Bóta finished his postgraduate studies in Computer Science at the University of Szeged under the supervision of Dr. Miklós Krész and Dr. András Pluhár in 2015, then worked as a Research Associate at the University of New South Wales with Dr. Lauren Gardner for two years. Following that, he worked as a postdoctoral fellow at Umeå University. His main research interests lie in the fields of complex network analysis and artificial intelligence.

-------------------------------------------------------------------------------------------------------------------------
NASLOV: Network-based framework for estimating the risk factors of epidemic spreading
-------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Network-based adaptations of traditional compartmental infection models such as SIR or SEIR can be used to model the spreading of diseases between cities, countries or other geographical regions. One of the common challenges arising in these applications is the lack of available transmission probabilities between these geographical units. The task of inverse infection is the systematic estimation of these values. Several methods have been proposed recently for solving this task. One of them is the Generalized Inverse Infection Model (GIIM) [1]. GIIM offers a large amount of modeling flexibility and allows transmission probabilities to be defined as a function of known attributes, or risk factors in an epidemic context. In this presentation we will see how GIIM works in two specific real-life outbreaks.
Both examples are embedded in a geographical and temporal setting. The first one considers the 2015-2016 Zika virus outbreak in the Americas, where the countries and overseas territories of the continent form the nodes of the network and air travel routes define the links [2]. The second application models the 2009 H1N1 outbreak between the municipalities of Sweden, with links between the municipalities indicating frequent travel routes.
Our first goal in both of these studies is to discover the relationship between the transmission risk between geographical units and a variety of travel, environmental, meteorological and socioeconomic risk factors. Our second goal is to estimate the risk of exportation and importation of the diseases for the territories involved in these studies. We will show that the GIIM model is able to identify the most critical risk factors in both scenarios, and in the influenza study, it is able make predictions about future outbreaks with good accuracy.

REFERENCE:
1. A. Bóta, L. M. Gardner: A generalized framework for the estimation of edge infection probabilities. arXiv:1706.07532 (2017)
2. L. M. Gardner, A. Bóta, N. D. Grubaugh, K. Gangavarapu, M. U. G. Kramer: Inferring the risk factors behind the geographical spread and transmission of Zika in the Americas.PLoS Neglected Tropical Diseases. http://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0006194

---------------------------------------------------------------------------------------------------

Predavanje bo potekalo v angleškem jeziku prek spletnega orodja Zoom.

Do predavanja dostopate tako, da se povežete prek sledeče povezave: https://zoom.us/j/297328207

Vabljeni! 

sobota, 14. marec 2020 Jordan Aiko DEJA: Using EEG for Emotion Experience Design in TV Commercials

petek, 6. marec 2020 Aleš MAVER: Big data and the human genome

V ponedeljek, 9. marca 2020, bo ob 16.00 uri v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem, Glagoljaška 8, Koper predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 9. marec 2020 ob 16.00 v FAMNIT-VP2

---------------------------------------

PREDAVATELJ: dr. Aleš MAVER

Dr. Aleš Maver has been working in the field of human genetics since 2002, and in his work he focuses on research of complex diseases, bioinformatics and diagnostics of rare genetic disorders. After graduating from medical school in 2011, he continued with his PhD work on rare genetic variations in familial multiple sclerosis using sequence analysis of the complete set of genes in the human genome (exome sequencing). Since then, he's been dealing with the use of big genomic data to diagnose patients with rare diseases. To that end, in 2013, he participated in the establishment of the Centre for Mendelian Genomics, which now functions as a center that offers state-of-the-art technology and bioinformatics to diagnose genetic diseases and is involved in global genome-wide sequencing data initiatives. Today his main interests include identifying new genes for genetic diseases, improving the interpretation of genetic variants at the genomic level and improving the exchange of genomic data in Slovenia and Europe.

---------------------------------------

NASLOV: Big data and the human genome

---------------------------------------

POVZETEK:

New genomic technologies have, in the recent years, provided unimaginable opportunities for human genome investigations, and thus significant advances in disease diagnosis and the discovery of new genes and disease mechanisms. With new approaches, especially through next-generation sequencing, sequencing of the entire human genome has become significantly cheaper, faster and more accessible. At the same time, we require novel bioinformatic approaches and significantly greater computational capacity to process the large amounts of data generated using novel genetic technologies. In my talk, I would like to present how we are facing the new challenges of big data in the time of genomic medicine, how we use big data of genomic sequencing in the discovery of new genes for human hereditary diseases, and how the analysis of such data has become the basis of modern genetic diagnostics in Slovenia today.

---------------------------------------

Predavanje bo potekalo v angleškem jeziku.

Vabljeni!

petek, 28. februar 2020 Julie DUCASSE: Interactive web documentary: audience reception and user engagement. A case study: iOtok.

V ponedeljek, 2. marca 2020, bo ob 16.00 uri v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem, Glagoljaška 8, Koper predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 2. marec 2020 ob 16.00 v FAMNIT-VP2

---------------------------------------

PREDAVATELJICA: Julie DUCASSE

Julie Ducasse holds a PhD in Human-Computer Interaction. She studied in France at The University of Toulouse. Since September 2018, she is a post-doctoral researcher at UP FAMNIT and works for the HICUP Lab.

---------------------------------------

NASLOV: Interactive web documentary: audience reception and user engagement. A case study: iOtok.

---------------------------------------

POVZETEK:

iOtok is an interactive web documentary directed by Miha Čelar, a Slovene documentary filmmaker. The documentary was distributed over 13 weeks in Slovenia and Croatia. Data were collected to better understand how people interacted and engaged with the documentary: Was interactivity efficient in engaging users? Were the social media successful in promoting the web-doc? In this seminar, we will present the key findings of the analysis of 20 000 sessions in terms of audience reception and user engagement.

---------------------------------------

Predavanje bo potekalo v angleškem jeziku.

Vabljeni!

petek, 21. februar 2020 Peter ROGELJ: Parenchima: Magnetic resonance imaging biomarkers for chronic kidney disease

V ponedeljek, 24. februarja 2020, bo ob 16.00 uri v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem, Glagoljaška 8, Koper predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 24. februar 2020 ob 16.00 v FAMNIT-VP2

---------------------------------------

PREDAVATELJ: Peter ROGELJ

Peter Rogelj is an assistant professor at the Faculty of Mathematics, Natural Sciences and Information Technologies (FAMNIT) at the University of Primorska in Koper, Slovenia. His research includes medical image processing with a special interest in medical image registration. His goal here is to achieve the speed and accuracy of image processing algorithms that are required for use in medical practice. The most important strategies for achieving this goal are the application of prior knowledge, the use of artificial intelligence and the rigorous evaluation of algorithms.

---------------------------------------

NASLOV: Parenchima: Magnetic resonance imaging biomarkers for chronic kidney disease

---------------------------------------

POVZETEK:

In this seminar, we will present the COST action Parenchima and the activities related to the forthcoming meeting of its workgroup 2(WG2) that will take place in Koper on 3-4 March. The WG2 focuses on establishing a database of renal magnetic resonance imaging (MRI) data and on software algorithms for data processing. First, we will present a data storage solution provided by Quibim and problems that needed to be solved to enable the population of the database. Second, the software evaluation initiative will be presented focusing on the evaluation of renal dynamic MRI registration algorithms. Further information about the Parenchima action can be found on its homepage: https://renalmri.org/.

---------------------------------------

Predavanje bo potekalo v angleškem jeziku.

Vabljeni!

sobota, 15. februar 2020 Domen ŠOBERL: Decentralized computation of homology in wireless sensor networks using spanning trees

V ponedeljek, 17. februarja 2020, bo ob 16.00  v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem (Glagoljaška 8, Koper) predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 17. februar 2020 ob 16.00 v FAMNIT-VP2

-----------------------------------------------

PREDAVATELJ: Domen ŠOBERL

Domen Šoberl is a teaching assistant at UP FAMNIT and is currently finishing his PhD thesis at the Faculty of Computer and Information Science in Ljubljana. Research interests: artificial intelligence, agent learning and planning, computational topology.

-------------------------------------------------------------------------------------------------------------

NASLOV: Decentralized computation of homology in wireless sensor networks using spanning trees

POVZETEK:

Wireless Sensor Networks (WSN) are computer networks of small inexpensive sensor nodes with a limited computational power and often without positioning capabilities. They are deployed over an area of interest to perform some measuring tasks and communicate the results. When deployed arbitrarily, the information on signal coverage is crucial to asses the quality of deployment. A homological criteria has been proposed to guarantee a full coverage using only the connectivity data.
In this seminar I will present our decentralized algorithm to verify homology-based WSN coverage criteria. Individual nodes examine the homology of their immediate neighborhood. They organize themselves in a spanning tree formation and merge their local information up the tree. During the process, a simplicial complex known as Vietoris-Rips complex is constructed, which encodes certain information on the shape of the WSN coverage. The algorithm works in arbitrary network topology and its communication demands are suitable for low-bandwidth wireless sensor networks.

Predavanje bo potekalo v angleškem jeziku.

Vabljeni!

petek, 31. januar 2020 Maheshya WEERASINGHE: Investigating the impact of different techniques towards project users themselves in a new environment using their cognitive, emotional and actionable responses

četrtek, 12. december 2019 Marko TKALČIČ: Behavioural and Cognitive Modeling in Recommender Systems

V ponedeljek, 16. decembra 2019, bo ob 16.00  v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem (Glagoljaška 8, Koper) predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 16. december 2019 ob 16.00 v FAMNIT-VP2

-----------------------------------------------

PREDAVATELJ: Marko TKALČIČ

Marko Tkalčič is associate professor at the Faculty of Mathematics, Natural Sciences and Information Technologies (FAMNIT) at the University of Primorska in Koper, Slovenia. He aims at improving personalized services (e.g. recommender systems) through the usage of psychological models in personalization algorithms. To achieve this, he uses diverse research methodologies, including data mining, machine learning, and user studies.

-------------------------------------------------------------------------------------------------------------

NASLOV: Behavioural and Cognitive Modeling in Recommender Systems

POVZETEK:

Recommender systems are systems that help users in decision making situations where there is an abundance of choices. We can find them in our everyday lives, for example in online shops. State-of-the-art research  in recommender systems has shown the benefits of behavioural modeling. Behavioural modeling means that we use past ratings, purchases, clicks etc. to model the user preferences. However, behavioural modeling is not able to capture certain aspects of the user preferences. In this talk I will show how the usage of complementary research in cognitive models, such as personality and emotions, can benefit recommender systems.

Predavanje bo potekalo v angleškem jeziku.

petek, 29. november 2019 Raffaele DE AMICIS: Human Centric Immersive Environments.Challenges and perspectives.

V ponedeljek, 2. decembra 2019, bo ob 16.00 v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem (Glagoljaška 8, Koper) predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 2. december 2019 ob 16.00 v FAMNIT-VP2

-----------------------------------------------
PREDAVATELJ: Raffaele DE AMICIS

Raffaele De Amicis is an Associate Professor, at the School of Electrical Engineering & Computer Science at Oregon State University. He received his Ph.D. in Design and Methods of Industrial Engineering at the Faculty of Engineering, University of Bologna, Italy. From 1999 to 2003, he was a research fellow at the Fraunhofer Institute for Computer Graphics in Darmstadt, Germany and senior researcher at the at the Technical University of Darmstadt. Before arriving at Oregon State University, he was the Managing Director of GraphiTech, Center for Advanced Computer Graphics Technologies in Trento, Italy, where he was recognized for leadership in science, technology, and innovation. Dr. De Amicis’ research focuses on the possibilities provided by Mixed Reality technologies in the area of design, creativity, and analytics. He has managed and delivered complex research projects, applied immature technologies, and mitigate associated risks. He has been the PI of several multidisciplinary projects contracted or funded by the European Commission, the North Atlantic Treaty Organization, governmental agencies and industry with an overall budget of 47 million Euros. As Vice-President of the Board of Directors at GraphicsMedia.net, Dr. De Amicis has developed strong competencies in how to build and manage successful multinational organizations. In this context, he has established strong linkages to diverse Academic and Research Institutes, both at the national and international level. During his career, he has developed strong academic outreach and collaborations with leading universities, industry, and community partners.

-------------------------------------------------------------------------------------------------------------
NASLOV: Human Centric Immersive Environments. Challenges and perspectives.

POVZETEK:

Over the last few years, disciplines such as Virtual & Augmented Reality, Computer Aided Design, and Human Factors, have undergone a profound evolution essentially driven by ever-increasing computational power and by availability of new hardware and software technologies.  Arbitrary shaped non‐flat displays, portable augmented reality glasses, micro-projection units, portable marker-less gesture tracking systems, increasingly accurate biometric sensors, and brain-machine interfaces are becoming commodities. Previously, these technologies, were only available in “Big” research labs, but are now entering the mainstream market causing a profound paradigm shift for the general public level. This means not only adapting old interaction schemas but it will call for the development of brand new interaction mechanisms that can account for complex technological ecosystem issues.
In his talk, Dr. De Amicis will present his research on how users perceive, understand, and interact with real and digital objects during an immersive experience. First, he will discuss some of the results achieved concerning the design of a multimodal experience combining sketches, gestures, and speech, to accomplish design tasks in different contexts, ranging from lightweight near-to-the-eye displays, to large-scale displays and immersive environments. He will also present his research on the design of geo-intelligent complex visualization systems and products and related services, addressing aspects such as interactive spatial data infrastructure, context awareness, and highly dynamic interaction. The second part of his talk will be devoted, to describing his current and future research plan on how Mixed Reality, allows the interaction with hybrid space with varying degrees of interaction allowing the user to enter a highly effective information environment which heightens data awareness and understanding.

Predavanje bo v angleškem jeziku.

petek, 22. november 2019 Nevena PIVAČ: On the Graph Search Trees

V ponedeljek, 25. novembra 2019, bo ob 16.00 uri v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem, Glagoljaška 8, Koper
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS in PROSTOR:  25. november 2019 ob 16.00 v FAMNIT-VP2

---------------------------------------------
PREDAVATELJICA: Nevena PIVAČ
---------------------------------------------

Nevena Pivač is a student of two study programs: MSc in Computer Science and PhD in Mathematics, at UP FAMNIT. She is doing PhD under the supervision of full professor Martin Milanič and is employed as a young researcher at Institute Andrej Marušič. Her research topics include structural and algorithmic graph theory, combinatorial optimization, and mathematical modeling using integer linear programing.

--------------------------------------------------
NASLOV: On the Graph Search Trees
--------------------------------------------------

POVZETEK:

Graph searches and the corresponding search trees can exhibit important structural properties and are used in various graph algorithms. We present various graph search algorithms, such as breadth first search (BFS), depth first search (DFS), their lexicographic versions (LBFS, LDFS), maximal neighborhood search (MNS) and maximum cardinality search (MCS). The problem of deciding whether a given spanning tree of a graph is a search tree of a particular search on this graph was introduced by Hagerup and Nowak in 1985, and independently by Korach and Ostfeld in 1989 where the authors showed that this problem is efficiently solvable for DFS trees. We show that the search tree problem is polynomial-time solvable for LDFS, in contrast to LBFS, MCS, and MNS, where we show the NP-completeness.
Joint work with Jesse Beisegel, Carolin Denkert, Ekkehard Kohler, Matjaž Krnc, Robert Scheffler, and Martin Strehler.

Predavanje bo potekalo v angleškem jeziku.