Grzegorz J. Nalepa is the coordinator of JAHCAI activities genrally involved in all the working groups.

Recently has also been directly involved in leading the XPM project, organizing AIRA seminars, as well as the SEDAMI workshop.

Bio

Grzegorz J. Nalepa (GJN.re) is a full professor in the Jagiellonian University, formerly at the AGH University of Science and Technology, in Kraków, Poland.

He has been actively working as an AI expert with IT companies and startups in Poland.He is an engineer with degrees in computer science - artificial intelligence, and philosophy.

He co-authored over a hundred research papers in international conferences and journals. He authored a book "Modeling with Rules using Semantic Knowledge Engineering" (Springer 2018).

He have been organizing number of international workshops, recently including
the AfCAI workshop on affective computing and context awareness, as well as the XAILA workshop on explainable AI and law on the JURIX conference.

Publications

1. Bobek S., Nalepa G.J. (2021). Augmenting Automatic Clustering with Expert Knowledge and Explanations. In: Paszynski M., Kranzlmüller D., Krzhizhanovskaya V.V., Dongarra J.J., Sloot P.M. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science, vol 12745. Springer, Cham. DOI: https://doi.org/10.1007/978-3-030-77970-2_48.
2. Bobek S., Bałaga P., Nalepa G.J. (2021). Towards Model-Agnostic Ensemble Explanations. In: Paszynski M., Kranzlmüller D., Krzhizhanovskaya V.V., Dongarra J.J., Sloot P.M. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science(), vol 12745. Springer, Cham. DOI: https://doi.org/10.1007/978-3-030-77970-2_4.
3. Bobek S., Mozolewski M., Nalepa G.J. (2021). Explanation-Driven Model Stacking. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science, vol 12747. Springer, Cham. DOI: https://doi.org/10.1007/978-3-030-77980-1_28.
4. Bobek S., Nalepa G.J. (2021). Introducing Uncertainty into Explainable AI Methods. In: Paszynski M., Kranzlmüller D., Krzhizhanovskaya V.V., Dongarra J.J., Sloot P.M.A. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science, vol 12747. Springer, Cham. DOI: https://doi.org/10.1007/978-3-030-77980-1_34.
5. Jakubowski J., Stanisz P., Bobek S., Nalepa G.J. Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations. Sensors. 2022; 22(1):291. DOI: https://doi.org/10.3390/s22010291.
6. Kutt K., Drążyk D., Bobek S., Nalepa G.J. Personality-Based Affective Adaptation Methods for Intelligent Systems. Sensors. 2021; 21(1):163. DOI: https://doi.org/10.3390/s21010163.
7. Kutt K., Nowara P., Szczur R., Barnowska G., and Nalepa G.J., Smart Data for Goods and Vehicle Monitoring – Practical Considerations on Data Semantization. in 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI), Nov. 2021, pp. 1216–1220. DOI: https://doi.org/10.1109/ICTAI52525.2021.00192.
8.  Kutt K., Żuchowska L., Bobek S., and Nalepa G.J., People in the Context – an Analysis of Game-based Experimental Protocol. in Twelfth International Workshop Modelling and Reasoning in Context (MRC) @IJCAI 2021, 2021, pp. 46–50. http://ceur-ws.org/Vol-2995/paper6.pdf.
9. Kutt K., Skoczeń S., and Nalepa G.J., A Voice-Based Travel Recommendation System Using Linked Open Data in Computational Science. ICCS 2021, Part III, 2021, pp. 370–377. DOI: https://doi.org/10.1007/978-3-030-77967-2_31.
10. Nalepa G.J., Bobek S., Kutt K., Atzmueller M. Semantic Data Mining in Ubiquitous Sensing: A Survey. Sensors. 2021; 21(13):4322. DOI: https://doi.org/10.3390/s21134322.
11.  Żuchowska L., Kutt K., and Nalepa G.J., Bartle Taxonomy-based Game for Affective and Personality Computing Research. in Twelfth International Workshop Modelling and Reasoning in Context (MRC) @IJCAI 2021, 2021, pp. 51–55. http://ceur-ws.org/Vol-2995/paper7.pdf.

The XPM project

XPM project (eXplainable Predictive Maintenance) was funded by CHIST-ERA [[https://www.chistera.eu]] in the Call Topic: Explainable Machine Learning-based Artificial Intelligence (XAI).

The project lasts 24 months till 2023 and has a budget of 604 236 €. It includes partners from Sweden Portugal, Polandm and France. Grzegorz J. Nalepa is the leader of the Polish part.

The XPM project aims to integrate explanations into Artificial Intelligence (AI) solutions within the area of Predictive Maintenance (PM) in the area of Industry 4.0.
Real-world applications of PM are increasingly complex, with intricate interactions of many components. AI solutions are a very popular technique in this domain, and especially the black-box models based on deep learning approaches are showing very promising results in terms of predictive accuracy and capability of modelling complex systems.

In the XPM project, we will develop several different types of explanations (anything from visual analytics through prototypical examples to deductive argumentative systems) and demonstrate their usefulness in four selected case studies: electric vehicles, metro trains, steel plant and wind farms. In each of them, we will demonstrate how the right explanations of decisions made by AI systems lead to better results across several dimensions, including identifying the component or part of the process where the problem has occurred; understanding the severity and future consequences of detected deviations; choosing the optimal repair and maintenance plan from several alternatives created based on different priorities; and understanding the reasons why the problem has occurred in the first place as a way to improve system design for the future.

Other activities

AIRA [[https://aira.geist.re]] is a seminar of Artificial Intelligence in Research and Applications. Numerous talks on AIRA are related to activities of JAHCAI.

The Semantic Data Mining workshop (SEDAMI) [[http://sedami.geist.re]] aims to get an insight into the current status of research in this area. We focus mainly on methods that allow include/utilize/exploit semantic information and domain knowledge in the context of machine learning and data mining, focusing on domains and research questions that have not been deeply investigated so far and to improve solutions to classic tasks.