KEYNOTE SPEAKER
Václav Snášel (Rector of VSB-TechnicalUniversity of Ostrava)
Vaclav Snasel (Senior Member, IEEE) received a Master's degree in numerical mathematics from the Faculty of Science, Palacky University, Olomouc, Czech Republic, in 1981, and the Ph.D. degree in algebra and number theory from Masaryk University, Brno, Czech Republic, in 1991. He is currently a Full Professor with the VSB - Technical University of Ostrava, Ostrava, Czech Republic. His research and development experience includes more than 30 years in the industry and academia. He works in a multidisciplinary environment involving artificial intelligence, social networks, conceptual lattice, information retrieval, semantic web, knowledge management, data compression, machine intelligence, and nature and bio-inspired computing applied to various real-world problems. He has authored or co-authored several refereed journal/conference papers, books, and book chapters. Prof. Sn\'a\v{s}el is the Chair of the IEEE International Conference on Systems, Man, and Cybernetics, Czechoslovak Chapter. He also served as an Editor/Guest Editor for several journals, such as Engineering Applications of Artificial Intelligence (Elsevier), Neurocomputing (Elsevier), and Journal of Applied Logic (Elsevier).
KEYNOTE
Title :
Metaheuristic optimization in Hyperbolic space.
Abstract :
Hyperbolic spaces have recently achieved acceleration in the context of machine learning of their high capacity and tree-likeliness structures, taxonomies, text, and graphs. With the same dimension, a hyperbolic vector can represent richer information than a Euclidean vector. In this paper, we propose Metaheuristic optimization algorithms in hyperbolic space. Considering that the most popular optimization tools have not been generalized in hyperbolic space, we design optimization algorithms according to the specific property of the hyperbolic manifold.
However, a major bottleneck here is the obscurity of hyperbolic space and a better comprehension of its gyrovector operations. We aim to introduce researchers and practitioners in the metaheuristic community to the hyperbolic equivariant of the Euclidean operations necessary to tackle their application to Metaheuristic optimization.
We conduct experiments on various metaheuristic algorithms in hyperbolic space.
Ingela Nyström (Professor of Uppsala University)
Professor Nyström obtained her PhD in computerised image analysis from Uppsala University, Sweden, in 1997. Her research interest is interactive segmentation, visualization, digital geometry, and quantitative shape analysis of volume images with their medical applications. For 12 years until 2022, she was Director of the Centre for Image Analysis. During 2008-2018, she served as member of the Executive Committee and President 2014-2016 of the International Association of Pattern Recognition (IAPR). She was Vice-Chair of the Swedish Council for Research Infrastructure during 2014-2019 and Chair of the Board of the Swedish National Infrastructure for Computing during 2020-2022. Currently, she is board member of the strategic innovation programme Medtech4Health.
KEYNOTE
Title :
Interactive Visualization for Surgery Planning and Medical Training
Abstract :
Three-dimensional (3D) imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) are routinely used in medicine. This has led to an increasing flow of high-resolution, high-dimensional image data that needs to be qualitatively and quantitatively analysed. This requires accurate segmentation of the image into relevant structures such as bones, soft tissue, liver, or blood vessels. In this talk, I will present some of the powerful methods for interactive image segmentation and visualization we have developed. We combine volume rendering with 3D texture painting to enable quick identification of the objects of interest. The user can work on the surfaces in 3D as well as on 2D slices. The methods are implemented on the GPU and can achieve real-time update rates for large volumes. Our system is used in clinical research by the clinicians.