KEYNOTE SPEAKERS keyboard_voice

Speaker: Prof. Ioannis Pitas

Aristotle University of Thessaloniki, Greece

Biography

Ioannis Pitas (IEEE fellow, IEEE Distinguished Lecturer, EURASIP fellow) received the Diploma and PhD degree in Electrical Engineering, both from the Aristotle University of Thessaloniki (AUTH), Greece. In the period 1994-2025, he has been a Professor at the Department of Informatics of AUTH. He has been Director of the Artificial Intelligence and Information Analysis (AIIA) lab (1999-2025). He has served as a Visiting Professor at several Universities. He is Principal Researcher in AUTH and CERTH/ITI.

His current interests are in the areas of computer vision, machine learning, autonomous systems, intelligent digital media, image/video processing, human-centred computing, affective computing, 3D imaging and biomedical imaging. He has published over 980 papers, contributed to 48 books in his areas of interest and edited or (co-)authored another 16 books. He has also been member of the program committee of many scientific conferences and workshops. In the past he served as Associate Editor or co-Editor of 23 international journals and General or Technical Chair of 5 international conferences. He delivered 171 keynote/invited speeches worldwide. He co-organized 38 conferences and participated in technical committees of 291 conferences. He participated in 75+ R&D projects, primarily funded by the European Union and is/was principal investigator in 47 such projects. He is the coordinator of the Horizon Europe R&D project TEMA ( https://tema-project.eu/).

Title: Decentralized DNN Architectures for Visual Data Analysis

Abstract

This lecture overviews decentralized and distributed DNN architectures and their implementation in cloud/edge environments. Big data analysis can be greatly facilitated if decentralized/distributed DNN architectures are employed that interact with each other for DNN training and/or inference using the human Teacher-Student education paradigm. A novel Learning-by-Education Node Community (LENC) framework is presented that facilitates communication and knowledge exchange among diverse Deep Neural Networks (DNN) agents, undertaking the role of a student or teacher DNN by offering or absorbing knowledge respectively. The framework enables efficient and effective knowledge transfer among participating DNN agents while enhancing their learning capabilities and fostering their collaboration among diverse networks. The proposed framework addresses the challenges of handling diverse training data distributions and the limitations of individual DNN agent learning abilities. The LENC framework ensures the exploitation of the best available teacher knowledge upon learning a new task and protects the DNN agents from catastrophic forgetting. The experiments demonstrate the LENC framework functionalities on multiple teacher-student learning techniques and their integration with lifelong learning. Our experiments manifest the LEMA framework’s ability to maximize the accuracy of all participating DNN agents in classification tasks by leveraging the collaborative knowledge of the framework. A LENC framework implementation in cloud/edge environments is also overviewed. Applications are presented in big visual data analysis tasks for Natural Disaster Management.

Speaker: Prof. Begoña García-Zapirain

University of Deusto, Spain

Biography

Begoña García-Zapirain was born in San Sebastian (Spain) in 1970. She graduated in Communications Engineering, specializing in Telematics at the Basque Country University, Bilbao (Spain) in 1994.
In 2004, she defended her doctoral thesis in biomedical signal processing research area. After four years of working for ZIV Company, in 1997, Prof. García-Zapirain joined the University of Deusto as a lecturer in signal theory and electronics at the Engineering School. She was the head of the Telecommunication Department at the University of Deusto from 2002-2008 and head of DeustoTech-LIFE Department from 2008-2018 and nowadays is leading the Biomedical Engineering program. In 2001 she created eVIDA research group (evida.deusto.es).

She has participated in more than 120 research projects on international, national and regional levels, published more than 150 papers in international scientific ISI indexed journals, and presented more than 160 papers in international and national scientific conferences.
She has been supervising 20 defended theses and has ongoing 5 PhD students. She has strong collaborations with research labs in USA, UK, France, Ireland, Belgium, Finland and Poland among others. She has 6 research awards at national level.

Title: Artificial Intelligence Applications in Environmental Health: Insights from the MOUNTADAPT Project

Abstract

Climate change is increasingly recognised as a key determinant of population health, with particularly pronounced impacts in mountainous regions, where environmental, climatic, and sociodemographic vulnerabilities intersect. Rising temperatures, the increasing frequency of extreme weather events, and ecosystem disruptions are intensifying health risks associated with heat waves, cardiovascular and respiratory diseases, vector-borne viral diseases—transmitted by mosquitoes or ticks—and the safety and sustainability of food systems, thereby placing growing pressure on healthcare and public health systems. In this context, these challenges can be addressed through the design, co-creation, and piloting of climate change adaptation strategies tailored to health systems in European mountain regions, with a scientific focus on the role of artificial intelligence (AI) as an enabling technology. AI is used to integrate heterogeneous data sources—including climatic, environmental, epidemiological, and socio-economic data—in order to model and predict the health impacts of climate change. In particular, predictive models are developed to assess risks related to the emergence and spread of vector-borne diseases and to anticipate the effects of heat exposure and air quality deterioration on cardiovascular and respiratory health within a changing environmental context. These predictive capabilities support the development of early warning systems and targeted prevention strategies, which are especially critical during extreme events such as prolonged heat waves.