Pozývame Vás na dva doktorandské semináre, ktoré sa uskutočnia v utorok 28.05.2024 na ÚI SAV v zasadačke č.102:

Program: Jay Kejriwal, MA (odd. M. Rusko, Š. Beňuš)
Alignment in human-human and human-machine spoken interaction

Abstract:
Entrainment is the tendency of a speaker to adjust some properties of a speaker’s features to match the interlocutor’s characteristics. It affects various linguistic dimensions and correlates with positive social attributes, allowing for rich human-machine interaction (HMI) applications. This thesis primarily focuses on improving spoken dialogue systems (SDS) by gaining an in-depth understanding of entrainment behavior in Human-Human interaction (HHI) and then applying this understanding to improve Human-Machine interaction (HMI). The thesis has three primary goals. First, a deep learning framework is presented to develop an entrainment detection system that identifies entrainment in four linguistic dimensions. The second primary goal is to understand cross-linguistic differences in entrainment across various linguistic dimensions in different languages. Lastly, the relationship between entrainment and non-verbal social cues and emotions was examined using different datasets. To sum up, the thesis contributed to a better understanding of entrainment in HHI and HMI that can be useful in developing entrainment functionality in existing SDS.

Program: Ing. Sepideh Hassankhani Dolatabadi (odd. J. Zelenka, I. Budinská)
APPLYING MACHINE LEARNING ALGORITHMS IN PREDICTIVE MAINTENANCE (ANOMALY PREDICTION)

Abstract:
In today’s manufacturing landscape, optimizing operational efficiency and ensuring machinery’s
uninterrupted performance are critical objectives. This research embarks on a journey to develop an intelligent Predictive Maintenance System (PMS) for a major low-grade hematite iron ore processing plant. Focused on the principles of Industry 4.0, our work leverages real-world data collected from sensors and repair logs, serving as a foundational dataset for comprehensive analysis and predictive modeling. The study begins by addressing the challenge of missing data, employing sophisticated imputation algorithms to bridge temporal data gaps effectively. Subsequently, our work delves into predicting potential machinery malfunctions based on advanced maintenance strategies guided by machine learning algorithms. As a central theme, our methodology involves data collection, preprocessing, feature engineering, labeling, and model training. We validate and verify the proposed methods through rigorous model evaluation and hyperparameter tuning. Additionally, our research paves the way for the development of a novel approach for developing a maintenance dashboard in the context of predictive maintenance. This dashboard is designed to deploy, monitor, and manage alerts and actions efficiently, creating a seamless feedback loop for continuous improvement.

Pozývame Vás na SEMINÁR Ústavu informatiky SAV, v. v. i.
ktorý sa bude konať v utorok 27. 2. 2024 o 13.30 hod.
v zasadačke ÚI SAV č. 102.

Program:
RNDr. Mária Bardošová, CSc. (odd. R.Andok)

„Smart Wound Monitoring Restorative Dressings“

Abstract:
The goal is to explore various materials combinations based on chitosan IPNs that will have the ability to protect the wound bed area and assist in healing while at the same time the built- in sensors in the dressing will be capable of producing a visual response if an active infection develops.

In addition, the dressing materials will also be capable of releasing antibacterial agents and therapeutics such as antibiotics to promote healing and/or in direct response to detrimental changes in the status of the wound. Dressings of this type will produce significant health and societal benefits. In particular they will:

• meet a well-established need, because chronic wounds and/or burns present a specific cause for concern in an aging society
• present an opportunity for an established dressing manufacturer to bring to the market a new product.

In addition, the proposed work is supposed to:

• advance basic knowledge in the area of nano-materials
• reveal hidden contexts and show emerging trends in chronic wound treatment via the application of the complex network approach to the analysis of research literature.

Tešíme sa na stretnutie s Vami pri šálke kávy alebo čaju.
Ing. Mgr. Robert Andok, PhD.
riaditeľ

Pozývame Vás na SEMINÁR Ústavu informatiky SAV, v. v. i.

ktorý sa bude konať vo štvrtok 25. 1. 2024 o 14. 00 hod.

v zasadačke ÚI SAV č. 102

1. Program:
   Design of Sunlight-guiding Microstructure and Development of Large-area UV Imprin. Tzu-Yu Huang (Ph.D. Candidate) Department of Power Mechanical Engineering, National Tsing Hua University, TAIWAN
2. Study on Growing Carbon Nanotube Arrays Based on Laser Welding of Dissimilar Materials. Dr. Yi-Hung Chen Department of Power Mechanical Engineering National Tsing Hua University, Hsinchu, TAIWAN

Pozývame Vás na SEMINÁR Ústavu informatiky SAV, v. v. i.
ktorý sa bude konať vo štvrtok 23.11. 2023 o 10.00 hod. v zasadačke č. 102

On-line link (Zoom)

Program:
Peter Malík, Štefan Krištofík
HYPERSPECTRAL DEEP LEARNING TREE SPECIES CLASSIFICATION

Introduction of AI models is becoming necessity for many companies. This seminar is going to show an example of AI introduction by a large Slovak company to automate monitoring of vegetation near high voltage power lines. Specifically, the development of an AI algorithm to classify tree species from hyperspectral visual data collected from Sverepec locations by flying platform is going to be presented. Real data are always unbalanced with long-tailed distribution. The classification performance with it is skewed towards the most numerous classes which results in typical bad classification performance of the least numerous classes.
Our results are going to show that near ideal classification performance of all classes, including the least numerous, can be reached when special algorithms to balance a dataset are used.

Tešíme sa na stretnutie s Vami pri šálke kávy alebo čaju.
Ing. Mgr. Robert Andok, PhD.
riaditeľ

Pozývame Vás na SEMINÁR Ústavu informatiky SAV, v. v. i. ktorý sa bude konať

v utorok 12. 9. 2023 o 14.30 hod. v zasadačke č. 102

Program: Ontologická reprezentácia pre bezpečnosť informačných systémoch (ORBIS)
(odd. I.Budinská)

Prezentujúci:

1. Štefan Balogh, FEI STU: Úvod do projektu ORBIS.
2. Peter Švec / Martin Homola, FEI STU / FMPH UK: Ontologická reprezentácia, reasoning, konceptuálne učenie.
3. Ján Mojžiš, ÚI SAV: Interpretovateľné pravidlá a jednoduchá dátová reprezentácia s klasickým strojovým učením.

Abstrakt
Doména kybernetickej bezpečnosti patrila medzi priority vlády v roku 2019, v čase podania projektu a aj v súčasnosti je táto oblasť aktuálna. Projekt ORBIS navrhuje nové prístupy v oblasti zdieľania poznatkov o bezpečnostných incidentoch a indikátoroch. Počiatok riešenia projektu sa sústreďoval na vytvorenie základnej ontológie, ktorá sémanticky integruje rôzne prístupy na popis hrozieb a útokov a tým umožňuje integráciu rôznych nezávislých štandardov a databáz poznatkov. Na tento účel boli použité nástroje na reprezentáciu a spracovanie ontológií. V ďalšej fáze riešenia sa projekt sústreďuje na aplikáciu reasoningu a metód konceptuálneho učenia s cieľom odvodiť nové pravidlá, resp. znalosti z ontologickej reprezentácie dát. Bolo použité klasické strojové učenie pre vytvorenie pravidiel.

link pre online-formu: https://meet.google.com/ker-thut-qpt

Tešíme sa na stretnutie s Vami pri šálke kávy alebo čaju.

Ing. Mgr. Robert Andok, PhD., riaditeľ