Title
Authorized metaheuristics in action
Abstract
Several years ago I participated in a fine lecture by Kenneth Sorensen about flaws and misuse of metaheuristics. It is impossible to blame the speaker for anyting, there are many of us running headlong into mimicking new species of animals in an algorithm, treating the process of creation of new metaheuristics as the only valuable goal of the research. In the course of this lecture I would like to remind about the most important theses of Sorensen, refer to the true motivation for using the metaheuristics and point out several features of the existing metaheuristics which make them especially useful for realization of optimization of hard problems. I will refer to theoretical background, naturalness of some methods, implementation-related features and hybridization. The goal of the lecture is to build onto what my predecessor said, paving the way for "authorized" development of metaheuristics which will be truly functional and make sense from scientific point of view.
Biodata
Aleksander Byrski (Ph.D. 2007, D.Sc. 2013 - AGH University of Science and Technology, Full Professor Title - President of Poland) works at the AGH University of Science and Technology in Krakow, the biggest Technical University in Poland. He is interested mainly in metaheuristic-based optimization, in particular novel techniquest related to agent-oriented inspirations, efficient and efficacious implementation of metaheuristics, novel ideas for metaheuristics inspirations. He holds a position of Deputy Director of the Institute of Computer Science AGH and V-ce Chairman of the Polish Academy of Sciences Computer Science Committee.
Title
The Future of Transparent AI in Healthcare and Assistive Technology
Abstract
This talk highlights the gap between AI advancements and long-term healthcare support, while presenting our vision for the future of AI in Health Supporting Systems. Focusing on chronic conditions, particularly spinal cord injuries (SCI), our research group explores transparent AI models that integrate medical staff in decision-making.
I will present our vision of modeling the human body using biosignals and behavioral responses for disease onset detection, emphasizing interpretable models and graphical model based learning.
Specifically, I will focus on the importance of interpretable models and demonstrate how graphical models and explainable regressions and classifications are fundamental for understanding of disease progression and treatment effects.
By addressing these key areas of research, we aim to bridge the gap between AI advancements and long-term healthcare support, ultimately paving the way for a future where AI plays a pivotal role in health prevention, disease prediction, and personalized treatment strategies.
Moreover, I will explore our vision of sensor fusion, encompassing both body and environmental data, to enhance life for individuals with mobility impairments in a seamless unobtrusive manner that complement their life to.
Biodata
Dr. Paez is the Head of the SCAI Lab at ETH Zürich and Swiss Paraplegic Research (SPF) in Switzerland. With a focus on personalized healthcare, his lab utilizes advanced machine learning techniques and wearable sensing to develop assistive decision-making systems that model disease onset and develop digital biomarkers.
Passionate about enhancing healthcare, Dr. Paez is dedicated to creating patient digital twins and leveraging them to develop preventive technologies that support healthcare workers and caregivers. His diverse research interests span human modeling, human-robot interaction control, explainable models for machine learning in healthcare applications, and biosignal processing.
Dr. Paez holds a PhD in Bioengineering and Robotics from Tohoku University, Japan, and has contributed his expertise to renowned research institutions including the University of Tsukuba and EPFL, Switzerland. Additionally, he holds a visiting faculty position at the Cybernetics Research Institute in Japan.
Driven by his research and patent achievements, Dr. Paez has co-founded Qolo Inc., a startup based in Japan specializing in personal mobility and rehabilitation devices, as well as DAAV, a Swiss company focusing on assistive robotics for mobility.