Chabbi Houda is a Full Professor at the Fribourg School of Engineering and Architecture, University of Applied Sciences and Arts Western Switzerland. She leads research at the iCoSys Institute for Complex Systems, focusing on AI-driven solutions for industrial and societal challenges. Her work bridges computer vision, deep learning, and practical applications from medical imaging to construction materials. Her research explores: Advanced computer vision for industrial inspection and monitoring Deep learning architectures for anomaly detection and predictive modeling Multimodal data fusion in surveillance systems AI applications in material science and healthcare She leads significant projects including: HIGH-ROAD (2025-2026): Hierarchical AI for road asset inventory using orthoimagery VideoCognition (2023-2025): Explainable AI for surveillance systems with Morphean SA SoNIT (2025-2028): Sonography nerve tracking with FHNW Concrete AI (2022-2025): Machine learning for recycled concrete optimization Her lab at iCoSys Institute collaborates with academic partners including University of Applied Sciences Northwestern Switzerland and industry leaders in medical tech, surveillance, and construction.
Prof. Dr. Kerstin Denecke is a Professor at Bern University of Applied Sciences (BFH) in the Engineering and Computer Science department, where she co-leads the Institute for Patient-centered Digital Health (PCDH). She maintains an affiliate position at the University of Victoria's School of Health Information Science and has conducted research visits at Canadian and New Zealand institutions. Her academic journey includes leadership roles in national and EU research projects, heading the 'Digital Patient Model' research group at Leipzig University prior to joining BFH in 2015. Dr. Denecke's research focuses on the intersection of artificial intelligence and healthcare, with particular expertise in natural language processing, conversational agents, and patient-centered digital health solutions. Her work spans multiple clinical domains including mental health interventions, radiology documentation, and suicide prevention. She employs participatory design methodologies that actively involve healthcare professionals and patients in the development process. Analysis of her recent publications reveals a strong emphasis on the practical application of large language models in clinical settings, ethical considerations in healthcare AI, and the development of taxonomies for conversational agents. Her research demonstrates a consistent trajectory toward making AI tools clinically usable while addressing real-world healthcare challenges. Young Talent Award of the Friedrich Wingert Foundation for outstanding approaches in medical linguistics and semantics Best Poster Award at MIE 2021 for 'Crowdsourcing for Creating a Dataset for Training a Medication Chatbot' Professor Denecke actively supervises bachelor, master, and PhD students, with current doctoral candidates working on medical text classification, social media chatbots for physical activity, and NLP applications in radiology. Her research is supported by multiple active grants including Innosuisse-funded projects on generative AI for clinical documentation. She leads the PCDH/AI for Health research unit which develops practical AI solutions for healthcare challenges while maintaining strong connections with clinical partners. The Institute for Patient-centered Digital Health under her co-leadership focuses on developing human-centered digital health solutions that address real clinical needs through interdisciplinary collaboration between computer scientists, healthcare professionals, and patients.
Dr. Anastasios Kouvelas is a Lecturer at ETH Zurich, where he serves as head of the Road Traffic Engineering research group at the Institute of Transport Planning and Systems (IVT), Department of Civil, Environmental and Geomatic Engineering. He has held this position since August 2018, succeeding Dr. Monica Menendez who moved to New York University in Abu Dhabi. Prior to joining ETH Zurich, he was a research associate at the Urban Transport Systems Laboratory (LUTS) at EPFL (2014-2018) and a postdoctoral fellow at Partners for Advanced Transportation Technology (PATH) at the University of California, Berkeley (2012-2014). Dr. Kouvelas' research focuses on modeling, simulation, optimization and traffic flow control. His work aims to develop real-time solutions based on control theory and operations research methods. The Road Traffic Engineering group develops algorithmic solutions that are components of intelligent transportation systems used in traffic control centers. Recent technological advances in autonomous vehicles have expanded their research topics as the industry seeks efficient operational solutions for autonomous mobility. They are particularly interested in extending their work to the design of advanced management strategies for urban networks that utilize connected vehicles to improve traffic operations and develop network-wide control strategies that minimize environmental impacts. His recent publications (2023-2025) demonstrate strong focus on traffic prediction using deep learning techniques, bike lane allocation impacts on urban networks, transit network resilience against disruptions, vehicle trajectory extraction from aerial recordings, and traffic control for mixed traffic systems with connected and autonomous vehicles. His work bridges theoretical developments in control theory with practical traffic engineering challenges. Scientific Awards No specific scientific awards were mentioned in the provided information. Advising and Grants Dr. Kouvelas supervises PhD and Master's students in traffic engineering and intelligent transportation systems. His research is supported by various grants including a grant from the Hong Kong Research Grant Council (Grant No. GRF 11216323) for research on traffic speed prediction. Laboratories and Teams Dr. Kouvelas leads the multidisciplinary Road Traffic Engineering research group at IVT, which consists of researchers with backgrounds in civil engineering, electrical engineering, mechanical engineering, computer science, control, and operations research. The group's work spans multiple areas including traffic flow theory, traffic operations, connected and automated vehicles, and intelligent transportation systems.
Marcel Blattner serves as Senior Lecturer and Co-Head of the Applied AI Research Lab at Lucerne University of Applied Sciences and Arts (HSLU), concurrently holding CTO and Board Member roles at AlpineAI AG since 2023. His career bridges academia and industry, with prior leadership positions including Principal Data Scientist at ETH Swiss Data Science Center and Chief Data Scientist at TX Group. PhD in Physics Diploma in Theoretical Physics Blattner specializes in applied artificial intelligence with emphasis on real-world implementation. His core competencies include Machine Learning, Deep Learning, and AI Strategy, leveraging expertise in Nonlinear Dynamics and Graph Theory to solve complex industrial problems—exemplified by his Prognostic Seismograph AI project which applies dynamical systems theory to predictive modeling. As Co-Head of HSLU's Applied AI Research Lab, he directs initiatives focused on translating academic research into commercial solutions, particularly in AI-driven predictive analytics. The lab collaborates closely with industry partners to develop deployable AI systems while training next-generation data scientists through hands-on projects.
