Univerza na Primorskem Fakulteta za matematiko, naravoslovje in informacijske tehnologije
-->
SI | EN

Ponedeljkov seminar računalništva in informatike - Arhiv

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, 7. oktober 2024 dr. Tina B. Kregar: Predstavitev podjetniškega izbora »Eno morje idej 2024«

V ponedeljek, 7. oktobra 2024, 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: 7. oktober 2024 ob 16.00 v predavalnici FAMNIT-VP2.

------------------------------------------------
PREDAVATELJICA: dr. Tina B. Kregar
------------------------------------------------

Dr. Tina B. Kregar v okviru Javnega zavoda za spodbujanje podjetništva in razvojne projekte Občine Izola (JZP Izola) vodi projekt  vzpostavitve Podjetniškega inkubatorja Morje v Izoli. Njeno delo se osredotoča na krepitev podjetniških kompetenc, spodbujanje inovativnosti, pospeševanje podjetniške rasti ter uvajanje trajnostnih poslovnih praks v lokalno okolje. Na predavanju bo predstavila podjetniški izbor »Eno morje idej 2024«, ki ga Občina Izola v sodelovanju z JZP Izola letos prvič organizira z namenom spodbujanja podjetništva in inovativnosti v Izoli.

-------------------------------------------------------------------------------------------
NASLOV: Predstavitev podjetniškega izbora »Eno morje idej 2024«
-------------------------------------------------------------------------------------------

POVZETEK:

Občina Izola v sodelovanju z Javnim zavodom za spodbujanje podjetništva in razvojne projekte Občine Izola letos prvič organizira izbor za najperspektivnejše podjetniške ideje »ENO MORJE IDEJ 2024«. Izbor je namenjen spodbujanju inovativnosti in podjetnosti v občini Izola ter širše, preko izbire najperspektivnejših podjetniških idej, ki bodo pomembno prispevale k razvoju novih projektov, ustanovitvi podjetij in povezovanju. V okviru predavanja bodo študenti seznanjeni z vsebino izbora, načinom prijave in pogoji za sodelovanje.

Seminar bo potekal v živo, s pričetkom ob 16:00 uri v prostorih UP FAMNIT - predavalnica VP2 (prvo nadstropje).

Vabljeni.


ponedeljek, 23. september 2024 Jan JOVAN: ChatGPT in ostali jezikovni modeli | Milan NIKOLIĆ: Primer Optimizacije stroškov v Kubernetes Cluster-ju na Amazon AWS

Danes, v ponedeljek, 23. septembra 2024, 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: 23. september 2024 ob 16.00 na daljavo prek Zoom-a.

1. predavanje:

-------------------------------------
PREDAVATELJ: Jan JOVAN
-------------------------------------

Jan Jovan je študent magistrskega programa Računalništvo in informatika ter razvojni inženir v podjetju Smart Com d.o.o.. Specializira se za integracijo velikih jezikovnih modelov (LLM), kar mu omogoča, da prispeva k razvoju naprednih rešitev v podjetju. Njegovo delo vključuje raziskovanje in implementacijo LLM tehnologij ter iskanje novih načinov za izboljšanje njihove uporabnosti v različnih aplikacijah.

------------------------------------------------------------
NASLOV: ChatGPT in ostali jezikovni modeli
------------------------------------------------------------

POVZETEK:

Veliki jezikovni modeli (LLM) so revolucionirali obdelavo naravnega jezika z izkoriščanjem obsežnih podatkovnih nizov in arhitektur  globokega učenja za generiranje besedila, odgovarjanje na vprašanja in izvajanje kompleksnega sklepanja. Ta seminar raziskuje osnovne mehanizme LLM, vključno z njihovo arhitekturo in metodami usposabljanja, pri čemer izpostavlja njihove naraščajoče primere na različnih področjih. Konkretno se obravnavajo aplikacije LLM v medicini za pomoč pri diagnozi in generiranje medicinske literature, v robotiki za izboljšanje interakcije med človekom in robotom ter v kodiranju za avtomatizacijo razvoja programske opreme. Poudarjeni so tudi izzivi, povezani z ocenjevanjem modelov, vključno z obsegom znanja in razširljivostjo, ter potencialne prihodnje smeri za izboljšanje zmogljivosti LLM.

***************************************************************************************************************************************

2. predavanje:

----------------------------------------
PREDAVATELJ: Milan NIKOLIĆ
----------------------------------------

Milan Nikolić, 2. letnik magistrskega programa Računalništvo in Informatika, trenutno v Pragi na Erasmus izmenjavi na Karlovi univerzi. Kar zadeva delovne izkušnje, zadnjih 5 let kot študent dela na oddelku za raziskave in razvoj GEN-I, kjer se ukvarja z infrastrukturo, IoT napravami ter front-end in back-end razvojem.

------------------------------------------------------------------------------------------------------------
NASLOV: Primer Optimizacije stroškov v Kubernetes Cluster-ju na Amazon AWS
------------------------------------------------------------------------------------------------------------

POVZETEK:

Seminar je raziskovanje strategij za izboljšanje stroškovne učinkovitosti v okviru deployment-a Kubernetes na platformi Amazon AWS. Vsebuje pregled osnove Kubernetes-a in AWS, analizo praks zaračunavanja AWS, s poudarkom na izzivih pri preglednosti stroškov. Nazadnje bosta predstavljeni dve specializirani orodji za spremljanje in optimizacijo stroškov, ki omogočata informirano odločanje za zmanjšanje nepotrebnih stroškov.

Seminarja bosta potekala v slovenskem jeziku prek Zoom-a ob 16:00 uri na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni.      


ponedeljek, 9. september 2024 Vanja MILESKI: Time Series transformations for churn prediction with CNNs

Jutri, v ponedeljek, 9. septembra 2024, 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: 9. september 2024 ob 16.00 na daljavo 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 as well as LLMs.

-----------------------------------------------------------------------------------------------
NASLOV: Time Series transformations for churn prediction with CNNs
-----------------------------------------------------------------------------------------------

POVZETEK:

Churn prediction represents a pivotal task in the retail sector, focusing on identifying customers with a high risk of attrition. We analyze a multi-year dataset from a large Slovenian retailer, encompassing detailed customer demographics, purchasing behaviors, and transaction records. To assess model performance, we employ a rolling-window cross-validation approach on temporally ordered data. Convolutional Neural Networks (CNNs) have been utilized for Time Series forecasting in this context. The model's performance is evaluated using rolling-window cross-validation on the chronologically structured data. We hypothesize that applying various Time Series transformations, such as downsampling, smoothing and other manipulations, can enhance the predictive accuracy of CNN models compared to raw time series inputs.

Seminar bo potekal na daljavo, s pričetkom ob 16:00 uri prek Zoom-a na sledeči povezavi:

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

Vabljeni.


ponedeljek, 2. september 2024 Vladimir BATAGELJ: OpenAlex

V ponedeljek, 2. septembra 2024, 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: 2. september 2024 ob 16.00 v predavalnici FAMNIT-VP3.

---------------------------------------------
PREDAVATELJ: Vladimir BATAGELJ
---------------------------------------------

Vladimir Batagelj je slovenski matematik in informatik, znan predvsem po svojih prispevkih na področju teorije omrežij, analize velikih omrežij in družbenih omrežij. Je zaslužni profesor na Fakulteti za matematiko in fiziko Univerze v Ljubljani, član Inštituta za matematiko, fiziko in mehaniko ter Oddelka za informacijske znanosti in tehnologije na UP FAMNIT. Je tudi avtor številnih znanstvenih člankov in knjig, ki obravnavajo teme, kot so analiza omrežij, algoritmi za obdelavo velikih podatkovnih zbirk in vizualizacija omrežij. Velja za enega vodilnih svetovnih strokovnjakov za analizo omrežij, njegovo delo pa ima širok vpliv tako na znanstvene raziskave kot na praktične aplikacije.

---------------------------
NASLOV: OpenAlex
---------------------------

POVZETEK:

OpenAlex (https://docs.openalex.org/) je popolnoma odprt katalog svetovnih raziskovalnih objav. Zaživel je januarja 2022. Poimenovan je po starodavni Aleksandrijski knjižnici. Ustvarila ga je neprofitna organizacija OurResearch, ki ga tudi vzdržuje.
OpenAlex indeksira več kot dvakrat več znanstvenih del kot vodilni tržni izdelki (Web of Science, Scopus). Celotno omrežje znanja in njegova izvorna koda sta odprta in prosto dostopna prek podatkovnih posnetkov, API-ja, ki je enostaven za uporabo, in spletnega
uporabniškega vmesnika. Poleg brezplačnega dostopa omogoča tudi dostop iz uporabniških programov in s tem zahtevnejše bibliografske analize.
Na seminarju bom najprej predstavil storitev OpenAlex in v nadaljevanju razvoj programske knjižnice OpenAlex2Pajek (v R-ju) za izgradnjo bibliografskih omrežij. Več na https://github.com/bavla/OpenAlex.

Seminar bo potekal v živo ob 16:00 uri v prostorih UP FAMNIT - predavalnica VP3 (drugo nadstropje).

Vabljeni.


ponedeljek, 2. september 2024 Vid JEROVŠEK: Oblikovanje domenskih informacij za natančno nastavitev asistentov s podporo UI, primer uporabe: podpora študentom

V ponedeljek, 2. septembra 2024, bo okrog 17.00 ure (takoj po 1. seminarju) izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 2. september 2024 okrog 17.00 v predavalnici FAMNIT-VP3.

---------------------------------------
PREDAVATELJ: Vid JEROVŠEK
---------------------------------------

Vid Jerovšek je absolvent magistrskega programa Računalništvo in informatika na
UP FAMNIT.

--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Oblikovanje domenskih informacij za natančno nastavitev asistentov s podporo UI, primer uporabe: podpora študentom
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Cilj te raziskave je ustvariti protokol za oblikovanje informacij, potrebnih za natančno nastavitev (fine-tuning) asistentov s podporo umetne inteligence (UI). Pri samem protokolu oblikovanja podatkov je zelo pomemben del anonimizacija, saj so podatki običajno občutljive narave. Največji izziv pri tem je ohraniti informacije, skrite v podatkih, hkrati pa zagotavljati anonimnost.

Seminar bo potekal v živo (v okviru Raziskovalnega semianrja), takoj po 1. seminarju, okrog 17:00 ure v prostorih UP FAMNIT - predavalnica VP3 (drugo nadstropje).

Vabljeni.


torek, 20. avgust 2024 Niki HROVATIN: Wireless Sensor Networks Today: Trends and Technologies

Tokrat izjemoma v sredo, 21. avgusta 2024, bo ob 10.00 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 2024 ob 10.00 na daljavo prek Zoom-a.

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

Niki Hrovatin is a Computer Science PhD, currently a Teaching Assistant at University of Primorska, and a Research Assistant at InnoRenew CoE, Izola, Slovenija. His current research interests include sensor networks, machine learning, distributed systems, and blockchain.

---------------------------------------------------------------------------------------------
NASLOV: Wireless Sensor Networks Today: Trends and Technologies
---------------------------------------------------------------------------------------------

POVZETEK:

This presentation provides an overview of Wireless Sensor Networks (WSNs), focusing on their core components, operational challenges, and recent advancements. It covers key trends and technologies shaping the future of WSNs, including energy management, routing, and communication protocols.

Seminar bo potekal v angleškem jeziku prek Zoom-a ob 10:00 uri na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Naš gost na Ponedeljkovem seminarju računalništva in informatike bo jutrišnje predavanje izvedel kot svoje Preizkusno predavanje pri izvolitvi v pedagoški naziv.

Vabljeni.


ponedeljek, 19. avgust 2024 Domen Vake: Predictive Modeling of Indoor Occupancy through Air Quality Data Analysis

V ponedeljek, 19. avgusta 2024, 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. avgust 2024 ob 16.00 na daljavo prek Zoom-a.

---------------------------------------
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 and projects mostly concern machine learning.

--------------------------------------------------------------------------------------------------------------------
NASLOV: Predictive Modeling of Indoor Occupancy through Air Quality Data Analysis
--------------------------------------------------------------------------------------------------------------------

POVZETEK:

This presentation will provide an overview of indoor air quality (IAQ) monitoring using sensor networks, focusing on the architecture, capabilities, and underlying technologies that power these systems. We will then explore a practical application through a case study conducted in a Slovenian elementary school, where a machine learning model was developed to predict classroom occupancy based on IAQ data. The talk will highlight the implementation challenges, the integration of multiple data sources (IAQ sensors, school schedules, and weather data), and the privacy concerns associated with the ability to infer sensitive information from seemingly safe data.

Seminar bo potekal v angleškem jeziku prek Zoom-a ob 16:00 uri na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni.


ponedeljek, 12. avgust 2024 Maheshya Weerasinghe: Development of Extended Reality (XR) Environments

Tokrat izjemoma v torek, 13. avgusta 2024, bo ob 10.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 13. avgust 2024 ob 10.00 na daljavo prek Zoom-a.

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

Maheshya Weerasinghe successfully completed her PhD in Computer Science at the International joint degree program with University of St. Andrews, UK. She is a member of the HICUP Lab. Her research areas include Human-Computer Interaction, Extended Realities, e-Learning and Cognitive Augmentation.

-------------------------------------------------------------------------------------
NASLOV: Development of Extended Reality (XR) Environments
-------------------------------------------------------------------------------------

POVZETEK:

Extended reality (XR) encompasses various immersive technologies including virtual reality (VR), augmented reality (AR), and mixed reality (MR). These environments enhance or simulate the physical world through digital means, providing users with immersive experiences ranging from completely virtual spaces to enhanced views of the real world. Creating XR environments requires specific hardware and software. Hardware includes VR headsets, AR glasses, sensors, and controllers, which allow users to interact with virtual elements. On the software side, development platforms and engines, such as Unity 3D, play a crucial role in building and running XR applications.
Unity 3D is a powerful and widely-used game development platform that supports the creation of 2D, 3D, VR, and AR applications. It provides a comprehensive set of tools for designing, coding, and deploying interactive experiences. Vuforia, integrated with Unity 3D, is a popular framework for developing AR applications. It allows developers to create applications that recognise and track real-world images and objects, overlaying digital content onto the physical environment. The process involves importing the Vuforia SDK into Unity, setting up AR camera and image targets, and scripting interactions to provide rich, interactive AR experiences.

Seminar bo potekal v angleškem jeziku prek Zoom-a ob 10:00 uri na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Naša gostja na Ponedeljkovem seminarju računalništva in informatike bo jutrišnje predavanje izvedla kot svoje Preizkusno predavanje pri izvolitvi v pedagoški naziv, zato prilagam tudi Dekanovo uradno vabilo na dogodek.

Vabljeni.


ponedeljek, 5. avgust 2024 2 predavanji: Dani ZUGAN & Kaja PRAPROTNIK: Empirična primerjava algoritmov za iskanje najkrajših poti v omrežju & Iskanje po nestrukturiranih podatkih senzorskih omrežij s pomočjo jezikovnih modelov

V ponedeljek, 5. avgusta 2024, 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: 5. avgust 2024 ob 16.00 na daljavo prek Zoom-a.

1. predavanje:

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

Dani Zugan je študent 2. letnika magistrskega programa Računalništvo in informatika na UP FAMNIT.

----------------------------------------------------------------------------------------------------------
NASLOV: Empirična primerjava algoritmov za iskanje najkrajših poti v omrežju
----------------------------------------------------------------------------------------------------------

POVZETEK:

Na seminarju bo predstavljena tema magistrskega dela, ki se osredotoča na različico problema iskanja najkrajših poti med vsemi pari vozlišč (APSP). Empirično bodo ovrednoteni različni algoritmi na usmerjenih grafih, kjer je število povezav manjše ali enako številu vozlišč.

2. predavanje:

-------------------------------------------------
PREDAVATELJICA: Kaja PRAPROTNIK
-------------------------------------------------

Kaja Praprotnik je študentka 2. letnika magistrskega programa Podatkovna znanost na UP FAMNIT.

-----------------------------------------------------------------------------------------------------------------------------------
NASLOV: Iskanje po nestrukturiranih podatkih senzorskih omrežij s pomočjo jezikovnih modelov
-----------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Sodobni tehnološki napredki na področju NLP (Natural language processing) so bistveno spremenili način interpretacije in obdelave podatkov. Dober primer tega so Veliki Jezikovni Modeli, ki se jih primarno uporablja za ustvarjanje in  obdelavo besedil na podlagi velikih količin vhodnih podatkov. V okviru ponedeljkovega seminarja bomo predstavili temo magistrske naloge o uporabi Velikih Jezikovnih modelov za interpretacijo neobdelanih podatkov iz različnih virov.

Seminarja bosta potekala v slovenskem jeziku prek Zoom-a ob 16:00 uri na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni.


četrtek, 25. julij 2024 Daniil BALDOUSKI: Improving container handling in port operations

V ponedeljek, 29. julija 2024, bosta 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. julij 2024 ob 16.00 na daljavo prek Zoom-a.

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

Daniil Baldouski is a second-year PhD student of Computer Science and teaching assistant at UP FAMNIT.

-------------------------------------------------------------------------------
NASLOV: Improving container handling in port operations
-------------------------------------------------------------------------------

POVZETEK:

In this seminar we will examine a method aimed at improving the handling of containers in ports. We will present a truck scheduling mathematical model designed to operate within the constraints and limitations typical of port environments. The model is structured to handle concurrent tasks and is tested through simulations to evaluate its performance in realistic settings.

Seminar bo potekal v angleškem jeziku prek Zoom-a ob 16:00 uri na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni.


petek, 19. julij 2024 2 predavanji: Karolina TRAJKOVSKA & Milan MILIVOJČEVIĆ: Addressing Name and Face Recall Cognitive Failure Using Visualisation-Based Mnemonics & A multi-echelon vehicle routing problem for waste wood collection and processing

V ponedeljek, 22. julija 2024, 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: 22. julij 2024 ob 16.00 na daljavo prek Zoom-a.

1. predavanje:

-----------------------------------------------------
PREDAVATELJICA: Karolina TRAJKOVSKA
-----------------------------------------------------

Karolina Trajkovska is a second-year Computer Science master's student at UP FAMNIT and a member of the HICUP Lab.

-----------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Addressing Name and Face Recall Cognitive Failure Using Visualisation-Based Mnemonics
-----------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

This research addresses the everyday cognitive failure of recalling names and faces by leveraging visualisation-based mnemonics. Despite the advancement in technology, enhancing human cognitive performance remains challenging, especially in everyday tasks like remembering names. Current research lacks a strategy-based digital training system to improve semantic memory for face-name associations. We take the first step towards developing such a system by creating a prototype to evaluate the visualisation-based link mnemonic method that could be used by the training system. This prototype augments faces in videos with keywords and visualisations, aiming to enhance face-name recall. We present the prototype and propose a research method to evaluate different modes of the system, focusing on the impact of animated visualisations on recall effectiveness and mental effort.

2. predavanje:

------------------------------------------------
PREDAVATELJ: Milan MILIVOJČEVIĆ
------------------------------------------------

Milan Milivojčević is a second-year Computer Science master's student at UP FAMNIT. He previously obtained a Computer Science bachelor's degree at UP FAMNIT.

-----------------------------------------------------------------------------------------------------------------------------
NASLOV: A multi-echelon vehicle routing problem for waste wood collection and processing
-----------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Wood waste from construction and demolition sites or industrial processing can be recovered and transformed into valuable products. However, since this waste comes from various sources, it requires certain pre-processing steps before actual remanufacturing. The first step is the collection and transport of the waste from collection points, construction sites and industrial facilities to the processing facilities. Once there, the material has to undergo pre-processing steps (sorting, cleaning/decontamination) before it can be manufactured into a new product. Finally, the finished products are transported to their final destination, such as customers.
This presentation focuses on the problem of optimizing collection and transport of wood waste to pre-processing and processing facilities, as well as the distribution of final products to customers. The above optimization question will be modelled as a vehicle routing problem (VRP) with multiple echelons.

Seminarja bosta potekala v angleškem jeziku prek Zoom-a ob 16:00 uri na sledeči povezavi:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni.


ponedeljek, 8. julij 2024 Žan Peternelj: Razvoj spletne aplikacije za nadomestitev in nadgradnjo obstoječe namizne različice

V ponedeljek, 8. julija 2024, 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: 8. julij 2024 ob 16.00 na daljavo prek Zoom-a.

-----------------------------------------
PREDAVATELJ: Žan PETERNELJ
-----------------------------------------

Žan Peternelj je absolvent magistrskega programa Računalništva in informatike na UP FAMNIT.

-------------------------------------------------------------------------------------------------------------------------------
NASLOV: Razvoj spletne aplikacije za nadomestitev in nadgradnjo obstoječe namizne različice
-------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Zaradi nenehnega napredka tehnologij in življenjskega cikla programske opreme je nujno, da se programske rešitve nadgrajujejo ali ponovno razvijajo, da bi ustrezale najnovejšim standardom in specifikacijam. V okviru ponedeljkovega seminarja bomo predstavili temo magistrske naloge o prenovi obstoječe aplikacije podjetja Magas d.o.o. za pomoč pri vodenju bolnikov na antikoagulacijskem zdravljenju s prehodom iz namiznega v spletno okolje.

Seminar bo potekal v slovenskem jeziku prek Zoom-a s pričetkom ob 16:00 uri na sledeči povezavi:

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

Vabljeni.


sobota, 22. junij 2024 Jani SUBAN: Kompaktna priponska drevesa

V ponedeljek, 24. junija 2024, 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: 24. junij 2024 ob 16.00 v FAMNIT-VP1.

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

Jani Suban je študent drugega letnika magistrskega programa Računalništva in informatike na UP FAMNIT. Predstavitev bo potekala v okviru raziskovalnega seminarja.

-------------------------------------------------------
NASLOV: Kompaktna priponska drevesa
-------------------------------------------------------

POVZETEK: 

Pogosti problem v bioinformatiki in procesiranju naravnih jezikov je iskanje vzorcev v besedilu. Če želimo ugotoviti ali zgolj en vzorec obstaja v besedilo, lahko le to storimo z uporabo Knuth–Morris–Pratt algoritma. Če pa želi najti vse ponovitve vzorca ali poiskati prisotno več vzorcev potrebujem indeks nad besedilom. V tem seminarju bo predstavljena podatkovna struktura priponsko drevo, ki je pogosto uporabljeno za indeksiranje besedila. Poleg priponskega drevesa bo predstavljena tudi kompaktna predstavitev priponskega drevesa.

Seminar bo potekal v slovenskem jeziku v FAMNIT-VP1 s pričetkom ob 16:00 uri.

Vabljeni.


ponedeljek, 10. junij 2024 ODPOVEDANO: Milan NIKOLIĆ: Primer Optimizacije stroškov v Kubernetes Cluster-ju na Amazon AWS

Današnji seminar je odpovedan. O ponovnem terminu boste obveščeni naknadno.

V ponedeljek, 10. junija 2024, 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. junij 2024 ob 16.00 v FAMNIT-VP1.

----------------------------------------
PREDAVATELJ: Milan NIKOLIĆ
----------------------------------------

Milan Nikolić obiskuje 2. letnik magistrskega programa Računalništvo in Informatika. Trenutno je v Pragi na Erasmus izmenjavi na Karlovi univerzi. Kar zadeva delovne izkušnje, zadnjih 5 let kot študent dela na oddelku za raziskave in razvoj GEN-I, kjer se ukvarja z infrastrukturo, IoT napravami ter front-end in back-end razvojem.

------------------------------------------------------------------------------------------------------------
NASLOV: Primer Optimizacije stroškov v Kubernetes Cluster-ju na Amazon AWS
------------------------------------------------------------------------------------------------------------

POVZETEK: 

Seminar je raziskovanje strategij za izboljšanje stroškovne učinkovitosti v okviru deployment-a Kubernetes na platformi Amazon AWS. Vsebuje pregled osnove Kubernetes-a in AWS, analizo praks zaračunavanja AWS, s poudarkom na izzivih pri preglednosti stroškov. Nazadnje bosta predstavljeni dve specializirani orodji za spremljanje in optimizacijo stroškov, ki omogočata informirano odločanje za zmanjšanje nepotrebnih stroškov.

Seminar bo potekal v slovenskem jeziku v FAMNIT-VP1 s pričetkom ob 16:00 uri.

Vabljeni.


ponedeljek, 3. junij 2024 2 predavanji: Karolina TRAJKOVSKA & Milan MILIVOJČEVIĆ: Harnessing Deep Neural Networks for Area of Interest Annotation in Eye Tracking Research & Star-Forest Decompositions of Complete Graphs

V ponedeljek, 3. junija 2024, 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: 3. junij 2024 ob 16.00 v FAMNIT-VP1.

1. predavanje:

-----------------------------------------------------
PREDAVATELJICA: Karolina TRAJKOVSKA
-----------------------------------------------------

Karolina Trajkovska is a second-year Computer Science master's student at UP FAMNIT and a member of the HICUP Lab.

-----------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Harnessing Deep Neural Networks for Area of Interest Annotation in Eye Tracking Research
-----------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Eye gaze is widely recognised as an important indicator for understanding and predicting user behaviour, as well as directing their attention across various domains including advertisement design, human-computer interaction and film viewing. We present a novel method to enhance the analysis of user behaviour and attention by (i) augmenting video streams with automatically annotated and labelled areas of interest (AOIs), and (ii) integrating AOIs with collected gaze and fixation data. The tool provides key features such as time to first fixation, dwell time, and frequency of AOI revisits. Using the capabilities of the YOLOv8 object tracking algorithm, the tools supports over 600 different object classes, providing a comprehensive set for a variety of video streams. This tool will be made available as open-source software, thereby contributing to broader research and development efforts in the field.

2. predavanje:

------------------------------------------------
PREDAVATELJ: Milan MILIVOJČEVIĆ
------------------------------------------------

Milan Milivojčević is a second-year Computer Science master's student at UP FAMNIT. He previously obtained a Computer Science bachelor's degree at UP FAMNIT. He will be presenting the work that was done on his study exchange at the Charles University in Prague together with colleagues Todor Antić and Jelena Glišić. This work was published on the 40th European Workshop on Computational Geometry (EuroCG) and on the International Workshop on Combinatorial Algorithms (IWOCA) 2024.

-------------------------------------------------------------------------------
NASLOV: Star-Forest Decompositions of Complete Graphs
-------------------------------------------------------------------------------

POVZETEK:

This work deals with the problem of decomposing a complete geometric graph into plane star-forests. In particular, we disprove a recent conjecture by Pach, Saghafian and Schnider by constructing for each n a complete geometric graph on n vertices which can be decomposed into ⌈n/2⌉ +1 plane star-forests. Additionally we prove that for even n, every decomposition of complete abstract graph on n vertices into n/2 +1 star-forests is composed of a perfect matching and n/2 star-forests with two edge-balanced components, which we call broken double stars.

Seminarja bosta potekala v angleškem jeziku v FAMNIT-VP1 s pričetkom ob 16:00 uri.

Vabljeni.


ponedeljek, 27. maj 2024 Nedim ŠIŠIĆ: Comparison of brain MRI segmentation pipelines

V ponedeljek, 27. maja 2024, 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. maj 2024 ob 16.00 v FAMNIT-VP2.

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

Nedim Šišić is a second-year PhD student at UP FAMNIT under the mentorship of Assist. Prof. Peter Rogelj. His PhD research concerns neural networks in medical imaging, specifically in segmentation of brain MRI.

---------------------------------------------------------------------------------
NASLOV: Comparison of brain MRI segmentation pipelines
---------------------------------------------------------------------------------

POVZETEK:

Magnetic resonance imaging (MRI) is frequently used in clinical trials to estimate longitudinal brain volume changes in order to asses treatment effect in neurological disorders such as Alzheimer's Disease and Multiple Sclerosis. A standard pre-processing step in volume estimation involves segmentation of MRI into distinct brain structures, and a large number of automated brain segmentation tools/pipelines have thus been developed. The seminar will present a comparison of six segmentation pipelines frequently used in clinical trials: FreeSurfer, SamSeg, FastSurfer, SIENAX, SPM12, and CAT12 on healthy controls and patients with Alzheimer’s disease and multiple sclerosis. The project was conducted as part of an internship at F. Hoffmann-La Roche, a pharmaceutical company currently developing drugs for various neurological diseases.

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

Vabljeni.


petek, 17. maj 2024 Zorica STANIMIROVIĆ: A GVNS-based solution approach to the Uncapacitated Single Allocation p-hub Maximal Covering Problem

V ponedeljek, 20. maja 2024, 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. maj 2024 ob 16.00 v FAMNIT-VP2.

-----------------------------------------------------
PREDAVATELJICA: Zorica STANIMIROVIĆ
-----------------------------------------------------

Zorica Stanimirović PhD, is a Full Professor at the Department for Numerical Mathematics and Optimization, Faculty of Mathematics, University of Belgrade and Coordinator for International Cooperation of the same institution. She graduated from the Faculty of Mathematics in 2000, received a master's degree in 2004, and PhD in 2007 at the same institution. She has been the local coordinator for several international projects and a member of program or organizational boards of several national and international conferences. From 2010 to 2015, she was Vice-Dean for Science and Research at the Faculty of Mathematics. Her research areas include Mathematical Modeling, Combinatorial Optimization, Metaheuristics, and Hybrid Optimization Methods. Up to now, she has published over 120 publications that have been cited 1182 times, her h-index is 19 and her i10 index is 32. More information and a list of publications are available at http://www.matf.bg.ac.rs/p/zoricast/pocetna/.

-------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: A GVNS-based solution approach to the Uncapacitated Single Allocation p-hub Maximal Covering Problem
-------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Hub covering problems represent extensions of classical covering location problems and they are widely studied in the literature, due to their theoretical and practical importance in location science. This study considers the Uncapacitated Single Allocation p-hub Maximal Covering Problem (USApHMCP) with binary coverage criterion. The USApHMCP considers a complete symmetric graph G=(N,E), where N represents a set of nodes, while E denotes a set of edges. Transportation costs per unit of flow and the flow demand for each origin-destination (O-D) pair i-j are given (i,j ϵ N). The goal of USApHMCP is to choose locations of p hubs from the set H ⊆ N, and to allocate non-hub nodes to hubs, such that the total covered flow between O-D pairs is maximized. The flow between an O-D pair is considered "covered" if the transportation costs are within the given maximum service distance (coverage radius). Each non-hub node is assigned to exactly one hub and the incoming and outgoing flows are sent only through that hub (single allocation scheme). A mixed integer formulation of the USApHMCP is presented and used within the framework of CPLEX solver on hub instances from the literature. As USApHMCP belongs to the class of NP-hard optimization problems, a solution approach based on General Variable Neighborhood Search (GVNS) heuristic is developed to tackle instances of larger problem dimensions. Two variants of GVNS heuristics are proposed, which use different procedures in the solution improvement phase: Sequential Variable Neighborhood Descent and Nested Variable Neighborhood Descent. The impact of these two procedures on overall GVNS performance is investigated through extensive computational experiments on standard hub instances from the literature. The obtained results indicate the efficiency of both GVNS variants, however, the one with Nested Variable Neighborhood Descent procedure was more successful with respect to both solution quality and running times. The results of GVNS on large-scale problem instances are also presented, showing the potential of GVNS when solving USApHMCP on realistic-size hub networks.

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

Vabljeni.


ponedeljek, 6. maj 2024 Domen VAKE: URŠKA - Univerzitetne rešitve: Študentski Komunikacijski Agent

V ponedeljek, 6. maja 2024, 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. maj 2024 ob 16.00 v FAMNIT-VP2.

---------------------------------------
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 and projects mostly concern machine learning, more specifically natural language processing with large language models.

----------------------------------------------------------------------------------------------------
NASLOV: URŠKA - Univerzitetne rešitve: Študentski Komunikacijski Agent
----------------------------------------------------------------------------------------------------

POVZETEK:

This presentation will provide an overview of large language models (LLMs), focusing on their architecture, capabilities, and the underlying technologies that power them. We will then explore a practical application of these models through a case study on URŠKA, a Retrieval-Augmented Generation (RAG) based communication agent. URŠKA is designed to assist university students by answering frequently asked questions about deadlines, academic policies, and more. The talk will highlight the implementation challenges, the integration of RAG with URŠKA, and its plans.

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

Vabljeni.


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

V ponedeljek, 22. januarja 2024, 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. januar 2024 ob 16.00 v FAMNIT-VP3.

------------------------------------------
PREDAVATELJ: Domen ŠOBERL
------------------------------------------

Domen Šoberl received his PhD in computer science in 2021 from University of Ljubljana, Faculty of Computer and Information Science. He is currently employed as a teaching assistant at UP FAMNIT. His current research interests lie in various areas of artificial intelligence, including deep learning, generative adversarial networks, reinforcement learning, and qualitative reasoning.

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Qualitative Reasoning in Artificial Intelligence — bridging the gap between machine learning and human reasoning
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK: 

A fundamental difference between the way conventional methods of Artificial Intelligence (AI) make decisions and the way humans think and reason is that humans reason qualitatively, while AI typically makes decisions based on numerical computations. The gap between the two worlds — the human and the machine — becomes apparent when it comes to exchanging learned knowledge. Traditional numerical models usually consist of a large number of numerical parameters that convey little or no information to a human on why a particular decision or action was taken. On the other hand, it is very difficult for a human to describe their intuitive knowledge of how a particular mechanism works to an AI algorithm in a way that the algorithm can utilize in planning and decision-making. Qualitative Reasoning (QR) is a branch within AI research that focuses on how AI can reason about processes qualitatively, and present the findings in a form that approximates human intuition. I will present the historical origins of Qualitative Reasoning (QR) in AI, its later developments, and the current state of the art. I will focus on the area of agent learning and planning in continuous domains with numerical sensory and actuation systems. We will explore the full cycle of automated abstraction of qualitative representations from numerical observations, the search for symbolic solutions through qualitative reasoning, and the implementation of the found solutions in the original numerical domain. I will explain the foundations of qualitative physics and qualitative simulation, which is the basis for qualitative planning, and thus for predicting possible future behaviors in a symbolic and explainable way. I will present the results of experiments with different robot problems, such as learning to walk, learning to push objects, and learning to swing up and balance a pole.

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

Vabljeni.