Find Academic Supervisors

Carlos M. Lima AzevedoView profile

Associate Professor

• Transportation Engineering
• Smart Mobility
• Urban Planning
• +6 more

Carlos M. Lima Azevedo is an Associate Professor at the Technical University of Denmark (DTU), affiliated with the Transport Division, Intelligent Transport Systems Section within the Department of Technology, Management and Economics. He also serves as a Research Affiliate at MIT's ITSLab. His research focuses on mathematical modeling of human mobility, smart mobility services, and integrated transportation technologies. He has held roles including Research Scientist at MIT's ITSLab and Executive Director of MIT's Transportation Education Committee. Education includes a PhD from MIT (2014) and an MSc from LNEC (2008). Key projects include SimMobility (a simulation platform) and Tripod (sustainable travel incentives). Teaching includes courses on transportation systems and data analysis at MIT. His research interests span traffic simulation, safety analysis, and agent-based modeling. Recent work emphasizes equity in shared mobility, AI-driven traffic control, and urban sustainability. He collaborates on projects like Mobility of the Future and FMOD (Flexible Mobility On-Demand). His contributions include frameworks for automated mobility-on-demand systems and policy-sensitive models for transportation networks.

Peter DologView profile

Associate Professor

• Recommender Systems
• Web Engineering
• Machine Learning
• +5 more

Peter Dolog is an Associate Professor at the Department of Computer Science, Aalborg University, Denmark. He is affiliated with The Technical Faculty of IT and Design. His research focuses on Recommender Systems, Web Engineering, Machine Learning, and Health Informatics. He leads projects such as the MEco Medical Ecosystem and the IWIS Intelligent Web and Information Systems initiative. His work emphasizes explainable AI, knowledge graphs, and social media analytics for public health monitoring. Notable contributions include hypergraph-based recommendation models and sensitive information detection in legal documents. Projects include MEco (medical event surveillance) and IWIS (web systems personalization), funded by EU and national grants. His research spans 148 publications, with recent work on explainable recommendation systems and neural networks for medical data analysis. Collaborations include the University of Vienna and international conferences like ECIR and RecSys. Media coverage highlights his work on using social media for epidemic detection. Key research areas include recommendation systems with attention mechanisms, knowledge graph integration, and ethical AI applications in healthcare. His methodologies bridge machine learning with user-centric design, emphasizing transparency and explainability in AI-driven systems.

Kristian TorpView profile

Professor

• Trajectory Data
• GPS Data Management
• Energy Engineering
• +5 more

Professor Kristian Torp is affiliated with the Department of Computer Science at Aalborg University, where he leads research in the Daisy Center for Data-Intensive Systems and participates in the BLUE Marine & Maritime Research initiative. His work focuses on spatial data management, trajectory analysis, and green mobility solutions. He has contributed to projects like Streamspin (smart push technology), TransDB (GPS data management), and REMOTE (traffic monitoring). Torp has published over 90 peer-reviewed articles and holds six awards for best papers and demos at international conferences. His research explores energy consumption optimization for electric vehicles, vessel trajectory prediction, and maritime data analysis, emphasizing practical applications in transportation and environmental sustainability. Research interests include trajectory data analytics, GPS-based systems, and data privacy in mobility contexts. Key contributions involve developing efficient spatial data warehouses, automated traffic monitoring frameworks, and frameworks for eco-routing and CO2 reduction. His work often bridges theoretical computer science with real-world infrastructure challenges, such as optimizing roundabout efficiency and reducing emissions through data-driven approaches. Awards: Best Paper (2018, 2014), Best Demo (2018, 2013), Best Poster (2014) Labs: Daisy Center, BLUE Research Group Grants: EU FP6, Viking Tempo Program Current projects include ACTIVE (vessel trajectory similarity search) and Mobispaces (energy-efficient mobility data architecture). His work is widely cited in transportation, environmental science, and database systems domains.

Sune LehmannView profile

Professor

• Networks and Complexity Science
• Social Data Science
• Complex Systems Analysis
• +4 more

Sune Lehmann is a Professor of Networks and Complexity Science at DTU Compute, Technical University of Denmark, and a Professor of Social Data Science at the Center for Social Data Science (SODAS), University of Copenhagen. His research focuses on quantitative analysis of social systems using large-scale datasets, integrating approaches from complex systems physics, machine learning, and statistical analysis. Key areas include modeling complex networks, human mobility, sleep patterns, epidemic spreading, and social media behavior. Education: B.Sc. and M.Sc. in Physics from the Niels Bohr Institute (2001-2003), Ph.D. in Complex Networks from DTU (2007). Professional roles include membership in the Danish Royal Academy of Sciences and Letters, and advisory roles in Danish government task forces during the COVID-19 pandemic. Research Interests: Complex networks, social data science, human behavior analysis, epidemiological modeling, and the application of machine learning to social systems. Notable contributions include studies on SARS-CoV-2 genomic data, temporal networks, and behavioral dynamics during pandemics. Scientific Contributions: Over 100 publications, including work on graph representation learning, surrogate network generation, and interdisciplinary collaborations. Supervised multiple PhD students in areas like social network properties, air pollution impacts, and mobility patterns. Awards: Member of the Danish Royal Academy of Sciences and Letters (202X). Labs/Teams: Active in DTU Compute and SODAS, leading projects on network science, social behavior, and policy-relevant research on tech giants and AI governance.

Nina GierasimczukView profile

Associate Professor

• Epistemic Logic
• Formal Learning Theory
• Artificial Intelligence
• +3 more

Nina Gierasimczuk is an Associate Professor in the Department of Applied Mathematics and Computer Science at the Technical University of Denmark (DTU), affiliated with the Algorithms, Logic and Graphs research group. Her work focuses on formal learning theory, epistemic logic, and computational models of cognitive processes. She holds a PhD from 2010, titled Knowing one's limits: Logical analysis of inductive inference . Her research interests include the logical foundations of learning, multi-agent systems, and the dynamics of knowledge and belief revision. She has supervised multiple PhD students in areas like dynamic logic, formal learning, and AI applications. Key projects involve modeling cognitive agents, semantic universals, and belief revision mechanisms in artificial intelligence contexts. Publications span topics such as causal intervention learning, semantic alignment in populations, and the integration of logic with learning theory. Her work bridges theoretical computer science, philosophy, and cognitive science. She is actively involved in international workshops and conferences, contributing to the advancement of dynamic logic and epistemic systems. Professional activities include examining PhD theses, advising on multi-agent systems, and collaborating on projects like hospital staff planning with multi-agent goals. Her research has been published in venues like Journal of Logic and Algebraic Programming and proceedings of the International Workshop on Dynamic Logic .

Mathieu JacomyView profile

Assistant Professor

• Network Visualization
• Digital Methods
• Social Network Analysis
• +3 more

Mathieu Jacomy is an Assistant Professor at Aalborg University's Department of Culture and Learning, affiliated with The Techno-Anthropology Lab and MASSHINE. His work focuses on network visualization, digital methods, and the socio-technical dimensions of AI tools. He leads and participates in projects like CD4T (Co-Design for Transitions) and GE-AI (Generative Ethnographic AI), exploring sustainability design, generative AI applications, and Arctic sustainability research. His research emphasizes critical technical practice through tools like Gephi and Gephisto, addressing issues of algorithmic transparency, network interpretation, and human-AI collaboration. Notable contributions include developing the Hyphe web corpus curation tool and analyzing AI self-consistency in LLMs. He has received awards including the Ziman Award (2020) and the ICWSM19 Test of Time Award for foundational network visualization work. Key Projects : Generative Ethnographic AI, Co-Design for Transitions, Arctic Sustainability Mapping Tools Developed : Gephi, Gephisto, Hyphe Awards : Ziman Award (2020), ICWSM19 Test of Time (2019) His work bridges computer science, anthropology, and critical theory, emphasizing ethical and epistemological dimensions of digital tools. Current projects explore LLM ethics, transdisciplinary design, and the role of networks in public discourse.

Panagiotis KarrasView profile

Professor

• Data Mining
• Database Systems
• Graph Data Management
• +7 more

Panagiotis Karras is a Professor of Computer Science at the University of Copenhagen and a faculty affiliate at Aarhus University. His research centers on robust and versatile methods for data access, mining, and representation. He has held academic positions at Aalborg University, Skoltech, Rutgers, NUS, the University of Zurich, and DTU, reflecting a broad international academic footprint. His research interests lie at the intersection of database systems, data mining, and machine learning, with a focus on graph data management, data privacy, indexing, influence maximization, and clustering. He aims to develop scalable and efficient algorithms that maintain high utility under privacy and accuracy constraints. His recent publications reveal a strong trend in graph-based methods, including graph alignment (GRASP, FREDE), influence and diffusion modeling, data anonymization, and adaptive indexing. These works appear in premier venues such as VLDB, SIGMOD, KDD, ICDE, and AAAI, indicating sustained high-impact contributions. He has been recognized with the 2008 Young Scientist Award in Physical/Mathematical Science from HKIS. Karras is actively seeking motivated PhD students and has supervised numerous collaborative projects. While specific grant details are not listed, his continuous publication output and affiliations suggest active research funding. His work often involves interdisciplinary collaboration, particularly in graph analysis and privacy-preserving technologies. He has contributed significantly to the development of efficient data synopses, anonymization frameworks (e.g., SABRE, L-opacity), and scalable graph processing systems, often in collaboration with leading researchers in the database and data mining communities.

Nicolaj Søndberg-JeppesenView profile

Part-Time Lecturer

• Bayesian Networks
• Cyber-Physical Systems
• Healthcare Informatics
• +4 more

Nicolaj Søndberg-Jeppesen is a Part-Time Lecturer at the Department of Computer Science, Aalborg University, affiliated with The Technical Faculty of IT and Design. His research focuses on Bayesian networks, cyber-physical systems, and their applications in healthcare, industrial diagnostics, and decision support systems. Key research interests include: Development of Bayesian network models for predictive maintenance and health monitoring in industrial systems Integration of operational data into continuous improvement frameworks Application of probabilistic graphical models in healthcare logistics and emergency management Design of smart manufacturing architectures for diagnostics and predictive maintenance Notable projects include: Animated Computer Games (ongoing since 2010) Extending the scope of graphical models for decision problems (ongoing since 2010) His recent work emphasizes: Patient flow prediction in emergency departments Risk assessment in home care deliveries Object-oriented Bayesian networks for component-level diagnostics Publications span applications in healthcare informatics, industrial engineering, and game theory, with a focus on practical implementations of probabilistic models.

Kai ZhaoView profile

Research Fellow

• Time Series Analysis
• Machine Learning
• Data Mining
• +3 more

Kai Zhao is a Research Fellow in the Department of Computer Science at the Technical Faculty of IT and Design, Aalborg University, Denmark, specializing in time-series analytics and machine learning applications. Research Interests: Time Series Analysis Machine Learning Data Mining Contrastive Learning Graph Neural Networks Anomaly Detection His recent publications (2023-2025) demonstrate a cohesive focus on graph-based and contrastive learning techniques for time-series challenges, particularly addressing few-shot scenarios, multivariate forecasting, and anomaly detection in IoT contexts. Methodological innovations include dynamic graph modeling and generative contrastive frameworks. Scientific Awards: No awards mentioned in available documentation. As Principal Investigator, he led the project 'Time Series Analyse with Few-shot Learning' (2022-2023), advancing few-shot learning applications for time-series analysis. His collaborative network spans multiple institutions, evidenced by co-authorships with researchers from Aalborg University and international partners. His research integrates theoretical frameworks with practical implementations, showing strong emphasis on robustness and adaptability in real-world time-series applications.

Jonas PetersView profile

Professor

• Causality
• Machine Learning
• Earth System Science
• +5 more

Jonas Peters is a Professor of Statistics at ETH Zurich, Switzerland, since 2023. Previously, he held positions at the University of Copenhagen and the Max Planck Institute for Intelligent Systems. His research focuses on causal inference, machine learning, and distribution generalization. He earned his PhD from ETH Zurich and the Max Planck Institute, with earlier studies at the University of Heidelberg and the University of Cambridge. His research interests span causal discovery, machine learning applications in Earth system science, and developing statistical methods robust to distributional shifts. Notable contributions include foundational work on causal inference frameworks, such as the Elements of Causal Inference book and the invariant prediction method. Peters has been recognized with awards like the Test of Time Award (runner-up) at ICML 2022 and the ASA Causality in Statistics Education Award. His work bridges theory and practice, emphasizing real-world applications. Peters has supervised numerous PhD students and postdocs, contributing to advancements in causal learning algorithms and statistical testing. His open positions and community service reflect his commitment to fostering academic collaboration and sustainability in academia. Education: PhD in Mathematics, ETH Zurich and Max Planck Institute (2012) MSc/MPhil Mathematics, University of Cambridge (2007) BSc Mathematics, University of Heidelberg (2006) Peters' publications address causal structure recovery, kernel methods for independence testing, and time series analysis. His work emphasizes causal reasoning in machine learning and climate science, with applications to policy learning and dynamical systems. He is an active member of statistical societies and serves on editorial boards of leading journals. His outreach efforts include popular science articles and books like The Raven's Hat , aiming to make complex concepts accessible. Peters advocates for sustainable academic practices, notably reducing travel for environmental reasons since 2020.

Finn Årup NielsenView profile

Associate Professor

• Neuroinformatics
• Text Mining
• Data Mining
• +8 more

Finn Årup Nielsen is an Associate Professor at the Technical University of Denmark (DTU), affiliated with the Cognitive Systems department under Applied Mathematics and Computer Science. His career spans neuroinformatics, text mining, and social media analysis, with a focus on integrating neuroscience and computer science. Education : Master in Engineering (1993-1996), Technical University of Denmark Research Interests : Neuroinformatics: Developing software and databases for brain imaging data and neuroscience text analysis Social Media Analysis: Mining Twitter and Wikipedia for citation patterns, sentiment, and topic trends Knowledge Graphs: Wikidata integration, lexeme alignment, and semantic representation Environmental Informatics: Applying AI to sustainable assessment through projects like DreamsKG Project Supervision : Supervised PhD projects on federated learning, neural network explainability, and big data analytics at DTU Contributed to foundational neuroimaging research in the Human Brain Project since 1994

Aasa FeragenView profile

Professor

• Machine Learning
• Medical Imaging
• Explainable AI
• +12 more

Aasa Feragen is a Professor in the Department of Applied Mathematics and Computer Science at the Technical University of Denmark (DTU), affiliated with the Visual Computing section. Her research lies at the intersection of machine learning, medical imaging, and trustworthy AI, with a strong emphasis on fairness, explainability, and clinical integration. Her research interests include Machine Learning , Medical Imaging , Explainable AI , Fairness in AI , Image Segmentation , and Anomaly Detection . She actively investigates how AI systems can be made more transparent, equitable, and clinically valid, particularly in sensitive domains like dermatology and fetal ultrasound imaging. The recent publications highlight a consistent trend toward ethical AI , clinical validation , and human-AI collaboration . Her work spans generative models, counterfactual explanations, and fairness in both vision and language models, demonstrating a broad yet cohesive research agenda focused on responsible AI deployment in healthcare. Scientific Activities and Leadership: Organized workshop: Fairness of AI in Medical Imaging (October 2023) Featured in public media discussing cautious deployment of AI in public services (October 2023) Research Supervision and Grants: She is the main or co-supervisor of multiple PhD projects, including: Human-XAI Collaboration for Improved Fetal Ultrasound Imaging Bias and Fairness in Medical Imaging SONAI: Explainable AI in the clinic Explainable AI supporting simulation-based medical education Bayesian neural networks for molecular discovery These projects are actively funded and run from 2022 to 2028, indicating sustained research support and leadership in interdisciplinary AI research. Research Labs and Teams: She is part of the Visual Computing research group at DTU Compute, engaging in close collaboration with clinical partners and AI researchers. Her network includes strong ties to medical institutions, focusing on real-world AI deployment and evaluation in healthcare settings.

Giancarlo RuffoView profile

Associate Professor

• Computational Social Science
• Data Science
• Complex Networks
• +5 more

Giancarlo Ruffo serves as Associate Professor of Computer Science at the University of Turin and Adjunct Professor at Indiana University's School of Informatics and Computing, maintaining active research and teaching roles since the early 2000s. His institutional affiliations center on computational research groups bridging computer science and social sciences. Research focuses primarily on Computational Social Science , with core expertise in Complex Networks and Data Science . Key investigation areas include social media dynamics, misinformation propagation, network structure analysis, and distributed systems. His work integrates methodologies from data mining, network theory, and human behavior modeling to address societal challenges through quantitative analysis of digital footprints. Recent publications (2020-2022) reveal intensified examination of polarization in online discourse, real estate valuation algorithms, and credibility assessment of media sources. Earlier works (2010-2012) established foundational contributions to ad-hoc network dynamics and social tie formation, demonstrating consistent methodological evolution from peer-to-peer systems to contemporary social media analytics. Ruffo leads the ARCS research group ( http://arcs.di.unito.it ), directing multiple funded projects in network science. His entrepreneurial initiatives include co-founding NetAtlas s.r.l. (2013) for mobile/social media development and Quaerys s.r.l. (2015) specializing in sentiment analysis services, translating academic research into commercial applications.

• Medical Image Analysis
• Computer Vision
• Machine Learning
• +5 more

Bulat Ibragimov is an Associate Professor in the Department of Computer Science at the University of Copenhagen, specializing in the Image Analysis, Computational Modelling, and Geometry research section. His work focuses on applying advanced computational techniques to medical imaging problems, particularly in radiology and diagnostic applications. His research interests span multiple domains of medical AI, including: Medical image analysis and computer vision for diagnostic applications Eye tracking analysis to understand radiologist decision-making processes Deep learning applications for disease detection and severity classification Explainable AI systems for medical image interpretation Computational geometry applications in medical imaging Dr. Ibragimov's recent publications demonstrate a strong focus on applying artificial intelligence to improve diagnostic accuracy and efficiency in medical settings. His work frequently bridges the gap between computer science and clinical applications, with particular emphasis on radiology, cardiology, dentistry, and gastroenterology. Many of his studies incorporate eye tracking data to better understand and augment human decision-making in medical imaging contexts. His notable contributions include work on: Cardiometric analysis from chest X-rays Dental image analysis for abnormality detection Ulcerative colitis severity classification Explainable AI for medical image models Prediction of radiological decision errors using eye tracking data

• Network Analysis
• Social Networks
• Data Mining
• +6 more

Michele Coscia is an Associate Professor in the Department of Data Science at the IT University of Copenhagen. He also serves as the Head of Programme for the BSc in Data Science. His research focuses on network analysis, social networks, data mining, and their applications in understanding human mobility, complex systems, economic development, and memetics. He has contributed to projects such as the Pioneer Centre for Artificial Intelligence and leads initiatives like ROMNET (Past social network reconstruction from material culture data) and Work2Vec (exploring deep learning in healthcare and work hours analysis). His research interests encompass interdisciplinary network science, including misinformation dynamics, ideological polarization, and the impact of social media systems. He has developed methodologies like the generalized Euclidean measure for multilayer networks and explored cultural data analytics through case studies like Italian music history. His work also addresses real-world challenges, such as quantifying the effects of violence on migration patterns and optimizing network sampling strategies for cost efficiency. Michele Coscia has received the Årets Forskningsmiljø 2022 award, recognizing his contributions to fostering outstanding research environments. He actively engages with media, discussing topics like misinformation and data visualization. As a principal investigator, he oversees projects funded by institutions such as the Villum Foundation and Danish National Research Foundation. His research spans academic collaborations across countries, reflecting his global network and commitment to advancing network theory and its applications.