جست‌وجوی استاد و پژوهشگر

Jan-Hendrik Bastekمشاهده پروفایل

پژوهشگر

• Computational Mechanics
• Mechanical Metamaterials
• Physics-Informed Machine Learning
• +۳ مورد دیگر

Jan-Hendrik Bastek is a Researcher affiliated with the Department of Mechanics and Materials Research at ETH Zürich. His work focuses on computational mechanics, mechanical metamaterials, and the application of physics-informed machine learning in engineering challenges. Based in Zürich, Switzerland, he contributes to advancing material design through interdisciplinary approaches that integrate deep learning, inverse problem solving, and advanced modeling techniques. His research interests span topics such as nonlinear mechanics, material property prediction, and the development of novel metamaterials with tailored properties. He has published extensively on physics-informed neural networks, data-driven simulation methods, and the optimization of truss-based metamaterials. His work bridges computational science and engineering applications, emphasizing practical solutions for complex structural and material systems. Recent publications highlight trends in applying video denoising diffusion models for metamaterial design, GNN-assisted phase space integration, and viscoelastic behavior analysis of time-dependent materials. His contributions reflect a commitment to merging traditional mechanics with cutting-edge AI techniques to address forward and inverse problems in computational mechanics. No scientific awards or grants are explicitly listed in the provided information. Bastek collaborates within the Mechanics and Materials Research group at ETH Zürich, contributing to both fundamental and applied research projects in the field.

• Aerothermodynamics
• Mechanical Engineering
• Process Engineering
• +۳ مورد دیگر

Dr. Ndaona Chokani is a Lecturer at the Department of Mechanical and Process Engineering at ETH Zürich. Their research focuses on aerothermodynamics, mechanical engineering, and process engineering, with a recent emphasis on interdisciplinary applications in computer vision and image processing. Affiliated with the Professur f. Aerothermodynamik, their work spans theoretical and applied domains. While explicit educational background details are not provided, their academic career includes contributions to fields such as fluid dynamics and process systems engineering. Research interests are inferred from departmental affiliation and recent publications, emphasizing computational methods in mechanical systems and image quality assessment. Recent publications highlight work in perceptual quality metrics for images and videos, immersive systems (VR/360 content), and machine learning applications in 3D pose estimation and generative models. Key areas include diffusion models for low-light imaging, spatial-temporal geometric networks, and benchmarking frameworks for image harmonization. No awards or grants are explicitly listed in the provided text. Their research often involves collaborations on datasets like Salient360! and tools for gaze data analysis in 3D environments. Future work appears to focus on improving perceptual metrics and expanding applications in healthcare and immersive technologies.

• Power Systems
• Energy Transition
• Grid Reliability and Risk Engineering
• +۳ مورد دیگر

Dr. Blazhe Gjorgiev is a Lecturer at the Department of Mechanical and Process Engineering at ETH Zürich. His research focuses on power systems reliability, energy transition modeling, and grid risk engineering. He leads the Reliability and Risk Engineering group, addressing challenges in grid resilience, renewable integration, and cascading failure mitigation. His work bridges machine learning applications with physical grid systems, emphasizing data-driven approaches for infrastructure optimization. Key research interests include: Power grid reliability and vulnerability analysis Renewable energy integration and policy implications Data-driven modeling of transmission and distribution systems Machine learning for fault detection and grid operation Recent publications highlight advancements in anomaly detection for power line inspection, European energy transition policies, and graph-based power grid benchmarking. His work often intersects with socio-technical issues, such as energy inequities and infrastructure resilience in aging systems. Dr. Gjorgiev collaborates on projects like the Nexus-e platform for energy-economic assessments and the Cascades-Risk model for expansion planning. His research has practical implications for grid modernization, policy design, and sustainable energy systems.

• Mechanical Engineering
• Materials Science
• Additive Manufacturing
• +۳ مورد دیگر

Dr. Thomas Tancogne-Dejean is a Lecturer in the Department of Mechanical and Process Engineering at ETH Zürich. His research focuses on advanced materials and metamaterials, with particular emphasis on mechanical behavior under extreme conditions, additive manufacturing processes, and computational modeling. Key areas include damage mechanics, fracture analysis, and the design of energy-absorbing structures through experimental and numerical methods. His work integrates machine learning techniques to optimize metamaterial designs and predict material behavior under various loading conditions. He has contributed extensively to understanding the mechanical properties of lithium-ion batteries and additively manufactured metals like stainless steel 316L and AlSi10Mg. Dr. Tancogne-Dejean’s publications span topics such as nanoindentation of viral particles, hierarchical lattice structures, and high-throughput testing methodologies. His research bridges theoretical mechanics with practical applications in energy storage systems and aerospace materials. He holds a prominent role in advancing interdisciplinary approaches to material science, combining experimental rigor with computational innovation.

• Pattern Recognition
• Applied Machine Learning
• Document Analysis
• +۴ مورد دیگر

Andreas Fischer is an Ordentlicher Professor at the Fribourg School of Engineering and Architecture (HES-SO), specializing in Pattern Recognition, Machine Learning, and Document Analysis. His research focuses on handwriting recognition, graph-based methods, and applications in cultural heritage preservation and medical imaging. Education: BSc in Computer Science from Fribourg School of Engineering and Architecture Research Interests: Graph Neural Networks for automata universality analysis Hybrid systems for Vietnamese stele keyword spotting Medical image analysis (colorectal cancer, tumor budding) Large language models for post-OCR correction Key Projects: TAINA Technology (handwriting validation for tax forms) Swisscom (Swiss German to High German translation) Hasler Foundation (Vietnamese stele graph-based analysis) Publications: Over 30 peer-reviewed articles in top journals/conferences (IEEE Access, Medical Image Analysis, Pattern Recognition, etc.), with focus on graph-based methods, handwriting recognition, and medical applications. Grants & Roles: Principal Applicant for multiple industry-funded projects (TAINA, Swisscom) Co-developer of DIVA-DAF deep learning framework

• Machine Learning
• Biomedical Informatics
• Medical Genomics
• +۳ مورد دیگر

Prof. Gunnar Rätsch is a Full Professor in the Department of Computer Science at ETH Zürich and Deputy Head of the Institute for Machine Learning. His research focuses on developing machine learning methods for biomedical applications, including genomics, medical imaging, and clinical decision support systems. He specializes in integrating multi-omics data, spatial transcriptomics, and time-series analysis to address challenges in precision medicine and critical care. His work emphasizes ethical AI frameworks, algorithmic fairness, and robust clinical prediction models. Key research areas include: Deep learning for medical imaging and histopathology Single-cell analysis and tumor profiling Reinforcement learning for treatment optimization in ICUs Multimodal data integration for clinical applications Recent work highlights advancements in: Standardizing single-cell cytometry readouts for clinical use Developing foundation models for critical care time-series analysis Creating interpretable survival models for ICU patients His contributions span foundational machine learning theory and applied healthcare technologies, with a focus on translational research to improve clinical outcomes. Current projects include the Tumor Profiler Study for multi-omic tumor analysis and ethical frameworks for clinical AI systems.

• Calculus of Variations
• Partial Differential Equations
• Optimal Transport
• +۴ مورد دیگر

Alessio Figalli is a renowned mathematician and Professor at the Department of Mathematics , ETH Zurich , where he also serves as Director of the Forschungsinstitut für Mathematik (FIM) . Born in Rome (Italy) in April 1984, he holds Italian citizenship and is a Swiss permanent resident. His academic journey includes a PhD from the Scuola Normale Superiore (Pisa) and École Normale Supérieure (Lyon), with postdoctoral roles at institutions like the University of Nice and École Polytechnique. Prior to ETH Zurich, he held professorships at the University of Texas at Austin (2009–2019). Figalli's research focuses on Calculus of Variations , Partial Differential Equations (PDEs) , Optimal Transport , and Free Boundary Problems . His work bridges pure and applied mathematics, with applications in geometry, probability, and physics. He is particularly known for contributions to optimal transport theory, regularity in free boundary problems, and stability estimates for geometric inequalities. Figalli has authored over 200 publications, including seminal papers on regularity of optimal transport maps , stability of geometric inequalities , and nonlocal PDEs . His invited lectures include plenary talks at the International Congress of Mathematicians (2018) and the Bourbaki seminar . He has supervised numerous PhD students and postdocs, fostering collaborations globally. Awards: Fields Medal (2018), EMS Prize (2012), Feltrinelli Prize (2017). Editorial Roles: Arch. Ration. Mech. Anal., Duke Math. J., and 10+ other journals . Grants: ERC Grant RSPDE , NSF awards, and the Swiss National Science Foundation. His ERC-funded project RSPDE explores regularity and stability in PDEs, while his mentorship has shaped the careers of over 30 students/postdocs. Figalli actively promotes mathematics through outreach, including public lectures and media engagements.

Markus Püschelمشاهده پروفایل

استاد

• Program Generation
• Fourier Analysis
• Signal Processing
• +۶ مورد دیگر

Markus Püschel is a Professor of Computer Science at ETH Zurich, leading the Advanced Computing Laboratory. He previously served as Head of the Department of Computer Science at ETH from 2013 to 2016. Before joining ETH in 2010, he was a Professor at Carnegie Mellon University (CMU) and retains adjunct status there. He holds a PhD in Computer Science (1998) and a Mathematics Diploma (1995) from the University of Karlsruhe. His research focuses on program generation for performance, Fourier analysis, signal processing, machine learning, and compiler optimization. He pioneered the SPIRAL system for generating optimized signal processing libraries and has contributed to algebraic signal processing theory. His work bridges mathematical foundations with practical high-performance computing, emphasizing automated code generation and domain-specific languages. Research trends in his articles include causal inference on directed acyclic graphs, quantized neural network inference, and efficient compiler techniques. His work on graph signal processing and causal analysis has led to novel methods in time-series data and DAG learning. Awards: IEEE Fellow (2020), Golden Owl Teaching Award (2015), NSF Discovery Grant (2008), and multiple best paper awards. Grants/Projects: Co-PI for Making Program Analysis Fast (SNF), SPIRAL GPU projects, and collaborations with industry partners like Intel and AMD. He advises over 40 PhD and master’s students, many of whom contribute to impactful projects in compilers, machine learning, and signal processing. His lab also co-founded the Swiss Data Science Center.

Gerhard Schrattمشاهده پروفایل

استاد

• Molecular Neuroscience
• Synaptic Plasticity
• Non-coding RNAs
• +۱ مورد دیگر

Gerhard Schratt is Full Professor and Head of the Institute for Neuroscience at ETH Zürich. His laboratory investigates molecular mechanisms of synapse development and plasticity, with emphasis on non-coding RNA regulation in neurological disorders. Research integrates molecular neurobiology with computational approaches to study microRNA functions in neuronal development, synaptic homeostasis, and stress responses. Current projects examine RNA-based therapies for neurodegenerative conditions and computational pathology platforms for digital histology. Professor Schratt's group develops AI frameworks for neurological assessment including multimodal dementia diagnosis, voice-based cognitive testing with privacy protection, and digital pathology for kidney disease. Collaborative projects with the Chan Zuckerberg Initiative explore mitochondrial regulation by microRNAs. He teaches molecular neurophysiology and neuroscience courses, supervising doctoral candidates in systems neuroscience approaches.

• Structural Health Monitoring
• Wind Energy
• Graph Neural Networks
• +۳ مورد دیگر

Dr. Gregory Duthé is a researcher at the ETH Zürich in the Structural Mechanics and Monitoring department. His work bridges computational modeling and structural diagnostics with applications in renewable energy systems. Research contributions include: Development of Graph Neural Networks for aerodynamic flow reconstruction Advancements in wake-induced load estimation for wind farms Innovations in unsupervised fault detection for offshore turbine systems Key publication trends show focus on physics-informed machine learning (2025), multi-agent infrastructure decision support (2025), and leading edge erosion modeling (2021). He combines graph-based architectures with structural health monitoring techniques across wind energy applications. Contact: duthe@ibk.baug.ethz.ch

• Graph-based learning
• Adaptation and learning in non-stationary environments
• Intelligence for embedded systems
• +۵ مورد دیگر

Cesare Alippi is a Full Professor at the Faculty of Informatics, Università della Svizzera italiana (USI), and also holds a professorship at Politecnico di Milano, Italy. He serves as a visiting Professor at Guangdong University of Technology (China) and Consultant Professor at Northwestern Polytechnic of Xi'an (China). His academic leadership extends to multiple international institutions where he has served as a visiting researcher including UCL (UK), MIT (USA), ESPCI (France), CASIA (China), A*STAR (Singapore), and University of Kobe (Japan). Professor Alippi's research interests center around graph-based learning, adaptation and learning in non-stationary environments, and intelligence for embedded, cyber-physical systems and IoT. His work bridges theoretical foundations with practical applications in sensor networks, environmental monitoring, and industrial processes. He has established significant research infrastructure including the Wireless Embedded Systems (WEmSy) Lab and the Internet of Things Lab, with notable deployments for marine environment monitoring in Queensland, Australia and the Fiji Islands, as well as rockfall and landslide monitoring systems across Italy and Switzerland. His research output shows a clear evolution toward graph-based deep learning approaches for time series analysis, anomaly detection, and spatiotemporal forecasting, reflecting the growing importance of graph neural networks in handling complex relational data in non-stationary environments. Major Awards: IEEE CIS Enrique Ruspini Meritorious Service Award (2024) IEEE CIS Outstanding Computational Intelligence Magazine Paper Award (2018) Gabor Award from International Neural Network Society (2016) IBM Faculty Award (2013) IEEE Instrumentation and Measurement Society Young Engineer Award (2004) Professor Alippi has held significant leadership roles including Past Board of Governors member of the International Neural Network Society, Past member of the Administrative Committee of the IEEE Computational Intelligence Society, and Past Vice-President for Education of the IEEE Computational Intelligence Society. He has served as Associate Editor for Proceedings of IEEE and several other prestigious journals. His research has been supported through numerous grants including an IBM Faculty Award in 2013 specifically for research on Intelligent Embedded Systems working in non-stationary environments. His research infrastructure includes the Wireless Embedded Systems (WEmSy) Lab and the Internet of Things Lab, with notable deployments including a sophisticated automatic, adaptive, sustainable and reliable wireless monitoring system for marine environments deployed in Queensland, Australia (2007) and under deployment at the Fiji Islands (2014-2015). He has also led several top-world deployments for rockfall and landslide monitoring across Italy and Switzerland since 2010, demonstrating the practical impact of his research in real-world harsh environments.

Ingo Scholtesمشاهده پروفایل

استاد

• Machine Learning
• Network Science
• Graph Mining
• +۵ مورد دیگر

Prof. Ingo Scholtes is a Full Professor of Machine Learning for Complex Networks at Julius-Maximilians-Universität Würzburg's Center for Artificial Intelligence and Data Science (CAIDAS). He holds a doctorate in computer science and mathematics from the University of Trier and has held roles including SNSF Professor at the University of Zurich, Full Professor at Bergische Universität Wuppertal, and Senior Assistant at ETH Zürich. His research focuses on higher-order graph analytics for temporal networks, machine learning, and computational social science. Education: PhD in Computer Science (University of Trier, Germany), Postdoctoral Research at ETH Zürich (2011–2016), and prior roles at Karlsruhe Institute of Technology and CERN. Research Interests: Machine learning on graphs, temporal network analysis, higher-order network models, and their applications in software engineering and social systems. He develops open-source tools like pathpy and git2net for network analysis. Recent Work: Focuses on causality-aware graph neural networks, temporal graph isomorphism, and network science applications in AI. Recent articles include studies on temporal network dynamics, path prediction, and Bayesian inference of network transitions. Awards: SNSF Professorship (2018), Junior-Fellowship (2014), and German Academic Scholarship Foundation (2004-2005). Active in editorial roles for EPJ Data Science and leadership in GI's Computational Social Science working group.

Daniele Zambonمشاهده پروفایل

پژوهشگر

• Graph Representation Learning
• Machine Learning
• Learning in Non-Stationary Environments
• +۷ مورد دیگر

Daniele Zambon is a postdoctoral researcher at the Dalle Molle Institute for Artificial Intelligence (IDSIA), affiliated with Università della Svizzera italiana (USI) in Lugano, Switzerland. He is a member of the Faculty of Computer Science and the Graph Machine Learning Group, as well as the IEEE Task Force on Learning for Graphs. PhD : Informatics, Università della Svizzera italiana (USI), 2022 Master’s & Bachelor’s : Mathematics, University of Milan, Italy Visiting Researcher : University of Florida, University of Exeter Internship : STMicroelectronics, Italy His research lies at the intersection of machine learning and graph-structured data, with a strong emphasis on graph representation learning , learning in non-stationary environments , and time series analysis . He explores how to model dynamic graphs, detect anomalies and changes over time, and develop deep learning methods for spatiotemporal forecasting. His work integrates statistical testing, geometric deep learning, and neural architectures like Graph Neural Networks (GNNs) and Neural ODEs. The recent publications highlight a clear trend toward temporal and dynamic graph modeling , especially for time series forecasting and irregularly sampled data . There is a growing focus on generative and foundation models for graphs , uncertainty-aware learning , and the creation of benchmark datasets like PeakWeather. His work bridges theoretical contributions (e.g., statistical tests, Kalman filters on graphs) with practical applications in sensing, environmental modeling, and system monitoring. Co-author of patent: Method for the Detecting Electrocardiogram Anomalies and Corresponding System (US10610162B2) PhD thesis featured in D22 Excellent Computer Science Dissertations (2022) Associate Editor, IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS) Organizer of tutorials and special sessions at ICML, LoG, KDD, and ESANN Daniele actively contributes to the academic community through advising and teaching at USI’s Bachelor’s and Master’s programs. He has co-supervised research projects and co-organized educational initiatives such as tutorials on graph deep learning. His collaborative work involves grants and partnerships with institutions like MeteoSwiss, leading to impactful datasets and applied research. He is deeply involved in building research capacity through workshops and community engagement in the graph learning field. He is a core member of the Graph Machine Learning Group at IDSIA and contributes to the IEEE Task Force on Learning for Graphs , fostering international collaboration and setting research agendas in the domain of graph-based AI.

• Machine Learning
• Data Mining
• Artificial Intelligence
• +۷ مورد دیگر

Prof. Alexandros Kalousis holds the position of Ordinarius HES Professor at the Geneva School of Economics and Management (HES-SO). His primary affiliation is within the Department of Management Information Systems under the School of Economics and Services. His research focuses on machine learning, data mining, and their applications in biomedical systems, cybersecurity, and generative modeling. Key projects include SimGait (SNSF-funded), which develops neuromechanical models for pathological gait analysis using machine learning, and RAWFIE (EU-funded), creating a mixed network testbed for autonomous vehicle experimentation. He has also led projects on time series forecasting, olfactory modeling for perfume creation, and metric/kernel learning optimization. Notable contributions span graph generative models like DGAE and GLAD, cybersecurity implications of LLMs, and reproducible indoor positioning systems. His work integrates theory-driven models with deep learning, emphasizing interpretability and extrapolation capabilities. Research collaborations include EPFL's Biorobotics Lab, Geneva University Hospitals, and industry partners like Firmenich. Total funding exceeds CHF 3M across projects like SimGait (CHF 2.1M) and RAWFIE (CHF 623K).

Robert Weibelمشاهده پروفایل

استاد

• Geographic Information Science
• Cartographic Generalization
• Movement Analysis
• +۱۰ مورد دیگر

Robert Weibel is a Professor in the Department of Geography at the University of Zurich, where he conducts cutting-edge research in Geographic Information Science (GIScience), cartographic generalization, movement analysis, and human mobility. His work bridges computer science, geography, and health sciences, with strong applications in aging, environmental monitoring, and urban planning. Research Interests: His primary research areas include: Computational movement analysis and trajectory modeling Cartographic and map generalization using AI and deep learning Indoor and outdoor navigation systems Spatial cognition and human mobility GIScience and geospatial data science Linguistic geography and dialect modeling Publication Trends: His recent publications (2023–2025) reflect a strong focus on AI-driven map generalization (e.g., SpaGAN, GNNs), explainable AI in cartography, indoor navigation modeling, and interdisciplinary studies on human mobility in aging and post-stroke recovery. He frequently publishes in top journals such as the International Journal of Geographical Information Science , ISPRS Journal , and Computers, Environment and Urban Systems . Scientific Contributions: Robert Weibel is a leading figure in GIScience, particularly in map generalization and movement data science. He has contributed to major research initiatives including the MOBITEC-Stroke project and has co-organized key conferences like GIScience. His work on real-time generalization, semantic modeling, and deep learning for cartography has advanced the field significantly. Advising and Collaboration: He has supervised numerous students and collaborators across disciplines, including in gerontology, computer science, and ecology. His research often involves interdisciplinary teams and international partnerships. Labs and Teams: He is affiliated with the GIScience research group at the University of Zurich, contributing to projects involving mobile mapping, real-time data processing, and spatial analytics. His work is integral to the development of intelligent geospatial systems and e-learning in GIS (e.g., the GITTA project).