|
Keynote Speakers
|
|
Prof. Robertas Damaševičius
Kaunas University of Technology, Lithuanian
Robertas Damaševičius received his Ph.D. in Informatics Engineering from Kaunas University of Technology (KTU) in 2005. Currently, he is a Professor at Software Engineering Department, KTU. He is also Professor at Department of Applied Informatics, Vytautas Magnus University, Kaunas; and Adjunct Professor at Faculty of Applied Mathematics, Silesian University of Technology, Poland. He is the author of over 400 papers as well as a monograph published by Springer. He is also the Editor-in-Chief of the Information Technology and Control journal and has been Guest Editor of several invited issues of international journals (IEEE Access, Biomed Research International, Computational Intelligence and Neuroscience, Journal of Universal Computer Science).
Title: Deep Learning for Scalable Forest Monitoring using Remote Sensing
Abstract: Scalable forest monitoring increasingly depends on remote sensing data streams spanning airborne/UAV LiDAR, aerial orthophotos, and satellite RGB imagery. This keynote outlines how modern deep learning supports end-to-end forest intelligence—from individual tree detection to forest and tree-crown segmentation—with an emphasis on practical performance under heterogeneous data conditions, limited spatial resolution, and real-world deployment constraints. Recent progress in LiDAR-based tree detection and segmentation is driven by hybrid approaches that combine geometric priors with efficient deep architectures and point/voxel representations, while persistent challenges remain: limited labelled data, dense-canopy occlusions, and inconsistent evaluation protocols that hinder cross-site comparability. Robust segmentation under operational constraints is illustrated through hybrid deep learning architectures that achieve strong accuracy on low-resolution digital orthophotos, supported by architectural refinements and imbalance-aware objectives that improve boundary delineation and generalization across datasets. For large-scale forest inventories, modern object detectors enable fast tree detection in RGB satellite imagery, with clear accuracy–latency trade-offs that influence model selection for scalable forest monitoring workflows. The keynote highlights the importance of sensor integration, uncertainty-aware outputs, and reproducible benchmarking practices that strengthen reliability and decision relevance at scale.
|
|
|
Prof.ShiKuo Chang
University of Pittsburgh, USA
Dr. Chang is the founder and President of Knowledge Systems Institute. Dr. Chang received the B.S.E.E. degree from National Taiwan University in 1965. He received the M.S. and Ph.D. degrees from the University of California, Berkeley, in 1967 and 1969, respectively. He was a research scientist at IBM Watson Research Center from 1969 to 1975. From 1975 to 1982, he was Associate Professor and then Professor at the Department of Information Engineering, University of Illinois at Chicago. From 1982 to 1986, he was Professor and Chairman of the Department of Electrical and Computer Engineering, Illinois Institute of Technology. From 1986 to 1990, he was Professor and Chairman of the Department of Computer Science, University of Pittsburgh. He is currently Professor and Director of Center for Parallel and Distributed Systems, University of Pittsburgh.
Dr. Chang is a Fellow of IEEE. He has been consultant for IBM, Laboratories, Standard Oil, Honeywell, and Naval Research Laboratory. His research interests include knowledge-based systems, pictorial information systems, visual languages and computer vision. Dr. Chang has published over one hundred and thirty papers, and written or edited eight books. His books, Principles of Pictorial Information Systems Design, (Prentice-Hall, 1989), and Principles of Visual Programming Systems,(Prentice-Hall, 1990), are pioneering advanced textbooks in these news research areas.
Title: Prosperity and Longevity in the Age of the Smart Machines
Abstract: In early 2026 Elon Musk made some bold predictions regarding prosperity and longevity of the human race in the age of the smart machines. In this keynote I will examine the
pre-suppositions and boundary conditions regarding his predictions, and discuss what are the possible futures for the human race.
|
|
|
|
Dr. Noman Sohail
Linköping University, Sweden
Dr. Noman Sohail is a Senior Research Engineer at Linköping University, Sweden, with a Ph.D. in Computer Science and Technology and over five years of international postdoctoral experience across Europe, Asia, and Africa. His interdisciplinary research lies at the intersection of data science, artificial intelligence, bioinformatics, public health epidemiology, and educational technology, with a strong focus on translating computational methods into real-world healthcare and societal impact.
Dr. Sohail has authored and co-authored 60+ peer-reviewed publications in high-impact journals (h-index ≥ 20, 1300+ citations), covering topics such as AI-driven decision support systems, digital literacy, machine learning in healthcare, and technology-enabled education management. He currently serves as Editor-in-Chief of the International Journal of Computational Medicine and Healthcare and is on the editorial boards of several international journals.
His work emphasizes bridging technology, education, and healthcare, particularly through AI-enabled analytics, learning technologies, and data-driven policy insights. Dr. Sohail is actively involved in mentoring graduate and doctoral students and collaborates globally on projects spanning educational innovation, biomedical data analysis, and sustainable technology management.
|
|
|
