| Title & Full Name | Lee, Saro |  |
| Affiliation | Faculty of Aerospace Engineering, Le Quy Don Technical University, Hanoi, Vietnam | |
| Presentation Title | Introduction and Application of GeoAI | |
| Abstract | GeoAI (Geospatial Artificial Intelligence) integrates artificial intelligence (AI) with geospatial analysis, leveraging machine learning (ML) techniques to address complex geoscientific challenges. This study explores the application of GeoAI in diverse geospatial domains, including landslides, land subsidence, floods, mineral resources, groundwater potential, and ecological habitats. Machine learning, a core component of GeoAI, facilitates predictive modeling through supervised, unsupervised, and reinforcement learning approaches. Various ML algorithms, including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Support Vector Regression (SVR), and Decision Trees (DT), are applied to construct and validate geospatial models. These models enable accurate classification, regression, clustering, and density estimation for geospatial predictions. In the domain of natural disasters, GeoAI is utilized to generate landslide susceptibility maps, predicting high-risk zones based on factors such as slope, topography, soil composition, vegetation, and hydrological features. Various ML models, including DNN, CNN, and hybrid ensemble techniques, are employed to improve prediction accuracy. Similarly, land subsidence susceptibility maps are created using models like Generalized Linear Models (GLM), Maximum Entropy (MaxEnt), ANN, and SVM, identifying vulnerable areas based on subsurface characteristics and hydrological conditions. Flood susceptibility analysis benefits from deep learning methods, integrating geospatial databases with ML algorithms such as SVR, Genetic Algorithm (GA), and Convolutional Neural Networks (CNN) to assess flooding risks in urban and rural regions. The study also highlights the application of GeoAI in mineral resource exploration, using spatial correlation techniques to delineate mineral deposit locations. Groundwater potential mapping is another critical application, employing ML models such as VIKOR-RF ensembles, Boosted Classification Trees (BCT), and Frequency Ratio-based methods to predict groundwater availability. These models analyze hydrological, geological, and topographical variables to optimize water resource management. Beyond geological applications, GeoAI contributes to ecological habitat modeling, predicting suitable environments for species such as Ruditapes philippinarum (Korean littleneck clam) and Prionailurus bengalensis (Leopard cat). Habitat suitability maps are generated using logistic regression, frequency ratio models, and ANN, aiding conservation efforts. The study concludes that GeoAI’s integration of machine learning and geospatial analysis provides a robust framework for predictive modeling across various geoscience applications. The adaptability of GeoAI allows for the transferability of algorithms across domains, enhancing decision-making in disaster risk assessment, resource management, and environmental conservation. The effectiveness of GeoAI models is validated using statistical performance metrics, ensuring reliability in geospatial predictions. | |
| Biographical Sketch | The researcher has achieved numerous internationally recognized publications related to this research project through studies on geological hazards such as landslides, floods, and ground subsidence, as well as research on groundwater, potentially hazardous elements, and ecology. The creativity of these studies is demonstrated through the application of big data and AI, which have become increasingly important in the Fourth Industrial Revolution. Using Geographic Information Systems (GIS) and remote sensing, the researcher has conducted spatial prediction and validation for study areas worldwide. These studies involve extensive spatial big data on topography, geology, soil, vegetation, land cover, groundwater, flood traces, landslides, and valley erosion traces, utilizing various machine learning algorithms, including deep learning, tree-based models, ensemble methods, and Bayesian approaches. Based on these research achievements, the researcher has published approximately 230 SCI(E)-indexed papers since 2001, with around 80% as the first author. These publications have been widely cited worldwide, reaching approximately 31,000 citations as of February 2025, with an H-index of 97 (based on Google Scholar). To accomplish these publications, the researcher has collaborated internationally with scholars from South Korea, Australia, China, Iran, India, the United States, Malaysia, Vietnam, Sweden, Norway, Austria, Portugal, Spain, Saudi Arabia, Romania, and the Netherlands. This international collaboration has helped elevate the researcher’s global reputation. Additionally, the research is not limited to South Korea but extends across multiple countries, including Iran, India, Serbia, and China. Notably, rather than simply co-authoring papers, the researcher has played a leading role as the first author, driving both research and publication. The researcher has published numerous corresponding-author papers in top SCI(E) journals, such as Landslides, Engineering Geology, Journal of Hydrology, Journal of Environmental Management, Geoscience Frontiers, Catena, Environmental Pollution, Applied Soft Computing, Science of the Total Environment, and Environment International. The researcher has also conducted international collaborative research on geological resources and geological hazards with various countries, including Tunisia, Indonesia, the Philippines, Mongolia, Brazil, Bhutan, Malaysia, Vietnam, Cambodia, Thailand, China, and Japan. Furthermore, from 2006 to 2015, the researcher organized and conducted a total of 10 KOICA training programs titled “Mineral Resource Exploration and GIS/RS”, targeting participants from over 30 countries. These experiences demonstrate the researcher’s extensive international research collaborations and training expertise. | |
| Title & Full Name | Nabil Abdennadher |  |
| Affiliation | University of Applied Sciences and Arts, Western Switzerland (HES-SO) | |
| Presentation Title | ThA ML-based edge-to-cloud platform for digital energy services | |
| Abstract | New forms of electricity production and consumption are disrupting the energy market. Renewable energy sources are intermittent and distributed in vast numbers of small-scale decentralized energy producers, which affects grid management. In parallel, consumption scenarios are changing as fossil fuels are being replaced by electricity in several sectors such as electric vehicles. Along the same lines, digital transformation is reshaping the electricity market. To name a few, internet of things, edge-to-cloud computing and machine learning techniques will allow the proliferation of intelligent versions of today’s “smart meter”. We can expect that, soon, the new smart meters devices will supportadditional functions including: · Monitoring: monitor/control home appliances, optimise local consumption or microgrid’s consumption, · Communication: gather information about other households’ consumption/production, · Learning and predicting consumption/production, · Negotiation: a negotiation can be initiated, among smart meters, acting on behalf of the household to set-up an energy transfer transaction. Thanks to these new functionalities, we can expect new “digital energy services” to emerge. These services will rely on a ML-based edge-to-cloud framework. To be able to build viable and sustainable ML-based edge-to-cloud framework for the new digital energy services, three cornerstones are needed: 1. Business models: the new microgrid structure will clearly involve a shift in the current business model. Rates that are now set by energy suppliers will be replaced by peer-to-peer and decentralized negotiations. 2. IT technology: our framework must support IT technology such as Internet of Things (to collect and gather data), Artificial Intelligence (to set up predictive models and self-adapt), Cloud and Edge computing (to store and process data), collaborative models to insure collaboration, etc. 3. Social acceptance: for the new digital energy services to spread out, they must be accepted and used by the different stakeholders such as DSOs, energy providers, households. Whether these actors would tolerate such appliances is far from obvious. This presentation focuses on the last two points. It details the different components of the ML-based edge-to-cloud framework developed within two European projects: SWARM and LASAGNE. We will present: 1. intermediate experimental results related to learning algorithms used to predict electricity consumption in households. 2. The results of a social acceptability study carried out as part of the two projects. 3. Two deployments in the canton of Geneva (Switzerland) using the ML-based edge-to-cloud framework 4. Prospects for this work. | |
| Biographical Sketch | Nabil Abdennadher received the Diploma in Engineering (Computer science) from Ecole Nationale des Sciences de l’Informatique (ENSI, Tunisia), and the Ph.D. degrees in Computer Science from University of Valenciennes (France) in 1988 and 1991, respectively. He was an assistant professor at the University of Tunis II from 1992 to 1998 and a research assistant at the Swiss Federal Institute of Technology (EPFL) from 1999 to 2000. In 2001, he joined the University of Applied Sciences, Western Switzerland (HES-SO, HEPIA) as an assistant professor. In 2008, he became an associate professor and in 2017 he was promoted to full professor. Nabil Abdennadher was head of the inIT research institute at HES-SO, HEPIA from 2010 to 2022. He is currently head of the Large-Scale Distributed Systems research group, representative of the Innovation DataBooster initiative in Swiss Romandie, member of the Editorial Board of the Journal of Reliable Intelligent Environments and member of the Swiss AI centre team. He is author and co-author of several publications and book-chapters. He is currently working on several Swiss and European projects aiming at developing self-adaptive edge-to-cloud digital platforms for energy sector. | |
| Title & Full Name | Prof. Joanna Paliszkiewicz |  |
| Affiliation | Warsaw University of Life Sciences, Management Institute, Poland | |
| Presentation Title | Artificial Intelligence in Education and Research – Transforming Teaching, Learning, and Research Practices | |
| Abstract | Artificial Intelligence (AI) is increasingly influencing education and research, offering new opportunities for innovation while also raising ethical and practical concerns. This keynote presentation examines the evolving role of AI in these fields, exploring both its transformative potential and the challenges it introduces. The session will begin with an overview of AI’s historical development in education and research, followed by an analysis of its current applications. AI-powered tools are enhancing teaching methodologies, personalizing learning experiences, and streamlining academic research. Adaptive learning systems, AI-assisted tutoring, and intelligent content creation platforms are enabling more efficient and tailored educational processes. In research, AI is revolutionizing data analysis, literature reviews, and knowledge dissemination through advanced automation and pattern recognition. Despite its advantages, AI integration presents significant challenges, including concerns about academic integrity, ethical AI implementation, and the risk of bias in AI-driven decision-making. This presentation will critically assess these issues, highlighting the need for responsible AI adoption in academic settings. Additionally, it will address the role of policymakers and educators in ensuring that AI complements rather than replaces traditional teaching and research practices. The discussion will conclude with insights into the future of AI in education and research, including anticipated developments in immersive AI-enhanced learning environments and the increasing role of AI in collaborative academic work. Recommendations will be provided on how institutions can balance innovation with ethical considerations, ensuring AI’s benefits are maximized while mitigating potential risks. This presentation contributes to the ongoing discourse on AI’s role in academia, offering a comprehensive perspective on its impact, limitations, and future possibilities. | |
| Biographical Sketch | Joanna Paliszkiewicz works as a full professor at the Warsaw University of Life Sciences (WULS—SGGW). She is the director of the Management Institute. She is a professor at the University of Economics in Ho Chi Minh City, Vietnam. She is also an adjunct professor at the University of Vaasa in Finland. She obtained the academic title “full professor” from the International School for Social and Business Studies in Slovenia. She is well recognized in Poland and abroad for her expertise in management issues: knowledge management and trust management. She has published over 250 papers/manuscripts and is the author/co-author/editor of 23 books. She has been a part of many scholarship endeavors in the United States, Ireland, Slovakia, Taiwan, the United Kingdom, and Hungary. She has actively participated in presenting research results at various international conferences. Currently, she serves as the deputy editor-in-chief of the Management and Production Engineering Review. She is an associate editor for the Journal of Computer Information Systems, Expert System with Applications, Issues in Information Systems, Przegląd Organizacji, Intelligent Systems with Applications. She serves as chair of the International Cooperation in European Business Club. She serves as president of the International Association for Computer Information Systems in the United States. She has successfully supervised many Ph.D. students, leading them to the completion of their degrees. She has also served as an external reviewer for several Ph.D. students in Poland, India, and Finland. She is actively involved in participating in the scientific committees of many international conferences. She was named the 2013 Computer Educator of the Year by IACIS in the USA. She is an expert in the Polish Accreditation Commission, and she is a member of the Polish Academy of Science. https://paliszkiewicz.pl | |
| Title & Full Name | PProfessor Maksim Iavich |  |
| Affiliation | Caucasus University / Scientific Cyber Security Association | |
| Presentation Title | The novel method of optimizing post-quantum digital signatures | |
| Abstract | As quantum computing advances, many widely used public key cryptosystems face the risk of being compromised, threatening the security of commercial applications. While countermeasures against quantum attacks exist, their inefficiency and complexity hinder practical deployment. This paper explores hash-based digital signature schemes, specifically evaluating Merkle tree-based signatures. To enhance efficiency and scalability, we introduce a novel methodology that optimizes post-quantum digital signatures by leveraging Verkle trees, k-ary Verkle structures, and vector commitments. Our approach integrates vector commitments with lattice-based constructions to ensure post-quantum security. Additionally, we propose an advanced framework incorporating both pseudo-random and quantum random number generators to enhance efficiency and security. Through this methodology, we present an improved digital signature scheme that balances security and efficiency in the post-quantum era. | |
| Biographical Sketch | Maksim Iavich is Ph.D. in mathematics and a professor of computer science. Maksim is an affiliate professor and the Head of cyber security direction at Caucasus University. He is also a Head of the information technologies bachelor and of the IT management master programs. Since 2020, Maksim Iavich is an expert-evaluator at National Center for Education Quality Development of Georgia. Prof. Iavich is a Director of the Cyber Security Center, CST (CU), which is the official representative of BITSENTINEL in the region. He is CEO & President of Scientific Cyber Security Association (SCSA). In 2025 he was awarded Weiser scholarship and in 2025 year he is working as post-quantum cryptography research in University of Michigan. Maksim is a computer science consultant in Georgian and international organizations. He used to be the invited speaker at international computer science conferences and is the organizer of many scientific computer science events. He was the key speaker at Defcamp and DeepSec in 2018-2024 with the talks about cyber security and artificial intelligence. He has many scientific awards in computer field. In 2018 he was acknowledged as a best your scientist in computer science by Shota Rustaveli National Foundation and in 2024 he was acknowledged as best scientist at Caucasus University. Maksim is the author of many scientific papers. The topics of the papers are cyber security, cryptography, artificial intelligence, machine learning, mathematical models, 5G security and simulations. | |
| Title & Full Name | Associate Professor, PhD Bohdan Haidabrus |  |
| Affiliation | Riga Technical University, Riga, Latvia | |
| Presentation Title | Agentic AI for Project and Delivery Management in Agile Environment. | |
| Abstract | ||
| Biographical Sketch | Experienced Project and Program Management leader, Agilist. More than 12 years of successful project management experience, more than 5 years of high level managerial experience. Successful experience in project and delivery management; implementation of Project Management methodologies (PMI, IPMA, P2M, etc.); and Agile ways of working. Over 5 years experience as Scrum Master in Software Development teams (Data science, Digital, DevOps). Certified Scrum Master (PSM I) and Scaled Agile Framework (SAFe 5 Practitioner). Has successful experience as a tutor, facilitator and coach in IT/Software Development/Agile Teams. | |
| Title & Full Name | Assistant Professor Dr. Narendra Khatri |  |
| Affiliation | Department of Mechatronics Manipal Institute of Technology, Manipal, India | |
| Presentation Title | AI-Driven Precision Agriculture: Integrating ANN, CNN, and DNN with IoT, Drones, and AGVs for Sustainable and Resilient Farming | |
| Abstract | The integration of Artificial Intelligence (AI) in precision agriculture has revolutionized farming operations by enhancing efficiency, sustainability, and resilience against environmental uncertainties. Advanced AI models such as Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), and Deep Neural Networks (DNNs) play a crucial role in optimizing various aspects of modern agriculture. These models are extensively deployed for pest detection, identification, and treatment recommendation by analyzing real-time imagery from drones and IoT-enabled sensors. Weed management, crop mapping, irrigation, and harvesting are further improved through AI-driven analytics, enabling precise resource allocation and reducing operational costs. Beyond crop-specific applications, AI-powered predictive models assist in estimating agricultural losses due to extreme weather events such as floods and storms. By analyzing satellite imagery, climate data, and past yield patterns, AI enables early damage assessment, allowing policymakers and farmers to implement mitigation strategies effectively. Additionally, the integration of drones and fleets of autonomous ground vehicles (AGVs) facilitates large-scale automation in farming operations, including seeding, fertilization, and surveillance, significantly reducing labor dependency. To enhance sustainability, precision agriculture must transcend single-crop operations and adopt a diversified, integrated farming model. AI-driven systems can optimize resource distribution in multi-sector agricultural setups, where traditional farming is combined with dairy, poultry, fishery, and other allied activities. This holistic approach not only improves land-use efficiency but also ensures economic stability for farmers in the face of rising inflation. By leveraging AI and IoT for data-driven decision-making, farmers can achieve higher productivity, reduced wastage, and enhanced resilience against market fluctuations. The future of precision agriculture lies in the seamless integration of AI, IoT, and autonomous systems, fostering sustainable and profitable farming practices. With continued advancements, AI-driven smart agriculture will play a pivotal role in securing global food production while minimizing environmental impact. | |
| Biographical Sketch | Dr. Narendra Khatri, SM IEEE, LM ISTE, Faculty Advisor IEEE Robotics and Automation Society (RAS), Student Branch Manipal (SBM), Research Fellow (Visiting), INTI International University, Malaysia and currently working as Assistant Professor in the Department of Mechatronics, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India. He has received his B.E. Degree in ECE from University of Rajasthan, in 2008, the M. Tech. degree in ECE (Specialization in Communication Systems) from CTAE, MPUAT Udaipur, in 2014, the Ph.D. in Mechatronics Engineering from The LNM Institute of Information Technology Jaipur, India, in 2021, and worked as Postdoctoral Research Associate (Agri-Drones) in World Bank Sponsored project at Centre of Excellence for Digital Farming Solution for Enhancing Productivity by Robots, Drones and AGVs, VNMKV Parbhani, India. He is Academic editor of PLOS ONE (SCI Indexed Journal) and Discover computing, Springer Nature (Scopus Indexed Q1). He has a granted 1 Indian utility patent, 10 Indian design patent granted, and 1 UK design registration granted, filed 2 Indian Utility patent, and published 25+ SCI/SCIE Indexed Journal articles, 4 Scopus Indexed Articles and 27+ international/national conference papers. He is a reviewer of 40+ internationally acclaimed SCI- Indexed Journals. He has published a book with AAP, CRC Press, Taylor and Fransis group. He has various international research collaborations viz. IHE delft, the Netherlands, INTI International university, Malaysia, SUMAIT University Zanzibar, and Amity University Tashkent etc. He is awardee with prestigious TMA Pai Gold medal for outstanding research publication in year 2023. He is awarded with MIT Best Researcher Award (Electrical Stream) and MAHE Best Research Paper Award – 2024. Also, awarded with best paper award at international conferences @ Dubai and Tashkent. His research interest includes Artificial intelligence and expert systems, IoT, Embedded systems, Image processing, and Machine learning etc. | |
| Title & Full Name | Dr. Ardashir Mohammadzadeh |  |
| Affiliation | Professor at Shenyang University of Technology | |
| Presentation Title | Advances in Type-3 fuzzy logic systems and controllers | |
| Abstract | In recent years, Type-3 fuzzy logic systems have emerged as a powerful extension of traditional fuzzy logic, offering enhanced capabilities for handling uncertainty and imprecision in complex decision-making environments. This keynote presentation will explore the latest advances in Type-3 fuzzy logic systems and their application in various control scenarios. We will discuss the theoretical foundations that differentiate Type-3 fuzzy logic from its Type-1 and Type-2 counterparts, emphasizing the benefits of incorporating a third dimension of uncertainty. Key advancements in algorithm design, computational efficiency, and real-time implementation will be highlighted, showcasing how these innovations contribute to more robust and adaptive control systems. Furthermore, we will present case studies demonstrating the successful application of Type-3 fuzzy controllers in fields such as robotics, structural control systems, and smart grid technology. By examining the challenges and future directions of research in this area, this keynote aims to inspire further exploration and collaboration among researchers and practitioners seeking to leverage the potential of Type-3 fuzzy logic in solving real-world problems. | |
| Biographical Sketch | Dr. Ardashir Mohammadzadeh is a professor at Shenyang University of Technology. As reported by Stanford University, in 2021-2024, he was listed among the top 2% of the best researchers in the field of artificial intelligence. He was also listed among the top 1% of highly cited researchers in 2023 based on the ESI database. His research interests include control theory, fuzzy logic systems, machine learning, neural networks, intelligent control systems, electric vehicles, power system control systems, chaotic systems, and medical control systems. | |