Ponedeljkov seminar računalništva in informatike - Arhiv
| 2025 | 2024 | 2023 | 2022 | 2021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 |
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 |
ponedeljek, 25. avgust 2025 Marija Rakić: Prediction and Validation of the Temperature Factors of Protein Structures
V ponedeljek, 25. avgusta 2025, 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: 25. avgust 2025 ob 16.00 prek Zoom-a (https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09).
--------------------------------------------
PREDAVATELJICA: Marija RAKIĆ
--------------------------------------------
Marija Rakić is a 2nd-year Data Science master’s student at UP FAMNIT, writing her master thesis under the supervision of Assoc. Prof. Jure Pražnikar, PhD. She is also working at UP FAMNIT, as part of the pilot project GDI UP.
------------------------------------------------------------------------------------------------------------------
NASLOV: Prediction and Validation of the Temperature Factors of Protein Structures
------------------------------------------------------------------------------------------------------------------
POVZETEK:
Experimental B-factors, while routinely deposited in crystallographic models, are often inconsistent, resolution-dependent, or entirely missing in predicted structures. To overcome these limitations, we employed a model for the goal of predicting and validating protein B-factors. The model is based on graphlet degree vectors (GDVs), which capture the local topological environment of each atom within a protein structure. The model was used on a dataset of nearly 69,000 protein structures from the Protein Data Bank (PDB), where GDVs were used as features in a multiple linear regression framework. We showed that this approach enables the prediction of B-factors without relying on resolution-specific parameters or refinement metadata. Evaluation of model performance shows strong agreement between predicted and experimental values, with a mean Spearman correlation of 0.72 across the dataset and consistent performance across resolution groups. As a key outcome, a web-based tool named ProtWeb was developed. It allows users to upload protein structures in PDB format and receive two modified files: predicted.pdb, containing normalized B-factor predictions, and rescaled.pdb, where predicted values are scaled to match the experimental distribution.
Seminar bo potekal v angleškem jeziku.
Seminar bo izveden online prek Zoom-a na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09
Meeting ID: 297 328 207
Passcode: 123456789
Vabljeni!
ponedeljek, 18. avgust 2025 Daniil Baldouski: An open-shop scheduling problem with operations batching
V ponedeljek, 18. avgusta 2025, 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: 18. avgust 2025 ob 16.00 prek Zoom-a (https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09).
--------------------------------------------
PREDAVATELJ: Daniil BALDOUSKI
--------------------------------------------
Daniil Baldouski is a third-year PhD student of Computer Science at UP FAMNIT.
-----------------------------------------------------------------------------------------------
NASLOV: An open-shop scheduling problem with operations batching
-----------------------------------------------------------------------------------------------
POVZETEK:
This work generalizes the open-shop and batch scheduling problems by considering merging of operations. We propose an efficient two-phase heuristic, which combines a graph-based optimal merging algorithm with a mixed-integer linear programming (MILP) model for the open-shop scheduling part of the problem. We introduce a benchmark instance set to validate our methodology.
Seminar bo potekal v angleškem jeziku.
Seminar bo izveden online prek Zoom-a na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09
Meeting ID: 297 328 207
Passcode: 123456789
Vabljeni!
četrtek, 7. avgust 2025 Nedim ŠIŠIĆ: Deep learning in whole brain MRI segmentation: A Review
V ponedeljek, 11. avgusta 2025, 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 2025 ob 16.00 prek Zoom-a (https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09).
------------------------------------
PREDAVATELJ: Nedim ŠIŠIĆ
------------------------------------
Nedim Šišić is a PhD student at UP FAMNIT under the supervision of Assoc. Prof. Peter Rogelj. His research focuses on segmentation of T1-weighted human brain MRI using deep learning models. His broader interests include natural language processing and artificial general intelligence.
---------------------------------------------------------------------------------------------
NASLOV: Deep learning in whole brain MRI segmentation: A Review
---------------------------------------------------------------------------------------------
POVZETEK:
Whole brain MRI segmentation plays a crucial role in neuroimaging studies and clinical trials by enabling precise localization and quantification of brain tissues and structures. The advent of deep learning has transformed the field, offering accurate and fast tools for MRI segmentation. In this review, we provide a comprehensive analysis of developments in deep learning-based segmentation of whole brain MRI of adults into tissues, structures, or regions of interest. We explore key factors influencing segmentation performance, including architectural design and choice of input size and model dimensionality. We also address validation practices, which are particularly important given the scarcity of manual annotations, and identify limitations in current methodologies. We present an extensive compilation of existing segmentation works and highlight emerging trends and key results. Finally, we discuss the challenges and potential future directions in the field.
Seminar bo potekal v angleškem jeziku.
Seminar bo izveden online prek Zoom-a na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09
Meeting ID: 297 328 207
Passcode: 123456789
Vabljeni!
