Find Academic Supervisors

• Business Process Management
• Predictive Analytics
• Machine Learning
• +3 more

Ilya Verenich is a Researcher at Queensland University of Technology (QUT), known for his work in Business Process Management and Predictive Analytics. He completed his PhD in 2018 with a thesis titled 'Explainable predictive monitoring of temporal measures of business processes.' His research focuses on developing machine learning and AI-driven tools for predictive process monitoring, such as the Apromore platform and Nirdizati web tool. Collaborations with international experts like Marlon Dumas and Marcello La Rosa highlight his contributions to process mining, workflow optimization, and predictive modeling. His work bridges computer science, data mining, and business systems, addressing challenges in real-time process analysis, resource allocation, and anomaly detection. Key areas of expertise include temporal process analysis, LSTM neural networks for sequential data, and minimizing operational waste through predictive activity ordering. He has published extensively in top-tier conferences like CAiSE and BPM, with topics ranging from white-box process performance prediction to symbolic sequence clustering for process monitoring. His interdisciplinary approach combines theoretical frameworks with practical applications in industries requiring efficient workflow management.

Georg SperlView profile

Researcher

• Physics-based Simulation
• Computer Graphics
• Material Science
• +3 more

Georg Sperl is a research scientist at CLO Virtual Fashion . He holds a PhD in physics-based simulation from the Institute of Science and Technology Austria (IST Austria) , where he was supervised by Chris Wojtan . His research focuses on physics-based animation of natural phenomena like cloth, yarns, granular media, and fluids, emphasizing multi-scale simulation techniques. Education: BSc and MSc in Visual Computing from the Technical University of Vienna , followed by a PhD at IST Austria. His work bridges computational mechanics and visual detail through methods like numerical homogenization. Notable achievements include the SIGGRAPH Outstanding Doctoral Dissertation Award (Honorable Mention) and the Eurographics PhD Award . His research has advanced yarn-level cloth simulation, thin-shell mechanics, and inverse modeling of fabric properties. Prior to his current role, he contributed to projects like iCaRL in computer vision.

• Computer Vision
• Machine Learning
• Artificial Intelligence
• +6 more

Prof. Fabio Galasso is a Full Professor in the Department of Computer Science at Sapienza University of Rome, where he heads the Perception and Intelligence Lab (PINLab). His research focuses on fundamental innovation in computer vision and machine learning, with particular emphasis on distributed intelligent systems, perception frameworks, and general intelligence within sustainable and interpretable AI contexts. His research interests span multiple domains of computer vision including video segmentation , motion forecasting , distributed intelligent systems , and shape reconstruction . Galasso's work emphasizes sustainable AI approaches that operate within constrained computational resources while maintaining interpretability and verifiability. His research bridges theoretical foundations with practical applications across retail, smart cities, and industrial settings. His recent publications demonstrate a clear progression toward increasingly complex human motion understanding and forecasting, with a strong emphasis on real-world applications. The research trajectory shows movement from foundational video segmentation techniques toward sophisticated motion prediction systems and anomaly detection frameworks that integrate multiple modalities. Key themes include temporal consistency, computational efficiency, and practical deployability in resource-constrained environments. His scientific achievements have been recognized with prestigious awards: 2019 IoT/WT Innovation World Cup 2019 Digital Champions Award 2018 Deutscher Digital Award Galasso has coordinated significant research initiatives including a Marie Sklodowska-Curie Actions project (Horizon 2020) and served as Principal Co-Investigator in multiple German-funded projects from the Ministry of Education and Ministry of Economics. His industry experience includes founding and directing OSRAM's Computer Vision Department in Munich, where he led R&D efforts connecting AI research with smart lighting applications, resulting in successful innovation transfers like the award-winning VISN product. He leads the Perception and Intelligence Lab (PINLab) at Sapienza University of Rome, fostering research that spans fundamental computer vision techniques to practical implementations in retail, smart cities, and industrial applications. The lab maintains strong connections with both academic institutions (including previous collaborations with University of Cambridge and Max Planck Institute) and industry partners.

• Computer Vision
• Pattern Recognition
• Machine Learning
• +7 more

Prof. Dr.-Ing. Joachim Denzler is a Professor leading the Chair for Digital Image Processing (Lehrstuhl für Digitale Bildverarbeitung) at Friedrich-Schiller-Universität Jena. His research spans computer vision, machine learning, medical imaging, and remote sensing applications across diverse domains including biomedical analysis, environmental monitoring, and facial recognition systems. His research interests focus on explainable AI, causal discovery, physics-informed neural networks, and bias mitigation in deep learning models. He has made significant contributions to fine-grained classification, concept activation vectors, and privacy-preserving techniques in facial recognition. His work often bridges theoretical computer vision with practical applications in medical diagnostics, environmental science, and infrastructure monitoring. His recent publications demonstrate a strong trend toward causal discovery methods, physics-informed neural networks, and addressing bias in machine learning systems. His work spans both theoretical advancements in model interpretability and practical applications in medical imaging, environmental monitoring, and infrastructure safety. The interdisciplinary nature of his research is evident from collaborations with ecologists, neuroscientists, and civil engineers. Best Paper Award at International Conference on Pattern Recognition (ICPR) 2024 Prof. Denzler actively mentors numerous PhD students and postdoctoral researchers, with frequent co-authors including Maha Shadaydeh, Niklas Penzel, Gideon Stein, and Tim Büchner appearing as first authors on significant publications. His laboratory has secured research funding across multiple domains including medical imaging, environmental monitoring, and AI safety. His work on CausalRivers represents a major contribution to benchmarking causal discovery methods with real-world time series data. The Chair for Digital Image Processing maintains strong industry and clinical partnerships, particularly in medical imaging applications for facial palsy analysis and neonatal care. Prof. Denzler's team has developed novel techniques for dam deformation monitoring using remote sensing data and created advanced methods for analyzing plant diversity effects on ecosystem functioning.

• Human-Computer Interaction
• Automotive Engineering
• Virtual Reality
• +4 more

Marine Capallera is a Researcher affiliated with the HumanTech - Technology for Human Wellbeing Institute at the University of Applied Sciences and Arts Western Switzerland (HES-SO). Her work focuses on Human-Vehicle Interaction (HVI), Virtual Reality (VR) applications for education and disability support, and driver state monitoring using physiological signals. She holds a PhD in Informatics from the University of Fribourg (2023), where her thesis addressed adaptive multimodal systems for driver supervision in automated vehicles. Her research spans projects like AdVitam (funded by Hasler Foundation), which explores collaborative driver-vehicle interaction models, and Pro-GIS, a VR initiative enabling social skills training for youth with intellectual disabilities. She collaborates with institutions like EPFL+ECAL Lab and the University of Fribourg, contributing to datasets on driver physiology and automated driving behavior. Key themes include: 1) Designing HVI systems that maintain driver situation awareness via ambient interfaces and physiological feedback; 2) Developing inclusive VR solutions for special needs populations; 3) Applying machine learning to classify driver states (fatigue, workload) using biometric data. Recent work emphasizes multimodal interaction in automated vehicles and cross-modal emotion integration in VR environments. Grants: Hasler Foundation-funded AdVitam project (2018-2021) Teams: Collaborates with Elena Mugellini, Quentin Meteier, and Omar Abou Khaled in automotive HVI research Labs: Leads VR training modules for nursing education and disability support

Aleksandra KnapińskaView profile

Researcher

• Network Optimization
• Machine Learning
• Traffic Prediction
• +7 more

Aleksandra Knapińska is a doctoral researcher at the Wrocław University of Science and Technology, Faculty of Electronics, Photonics and Microsystems, Department of Computer Networks and Systems. She is an active member of multiple research teams including the Computer Networks Team, Machine Learning Team, and Advanced Data Analysis Methods Team. Her work is primarily associated with the MAAN project focused on optimizing multilayer application-aware networks. Her research interests center on network optimization , machine learning for traffic prediction , and multi-criteria optimization in optical and multilayer networks . She applies advanced data analysis and machine learning techniques to model and predict time-varying network traffic, particularly in backbone and optical networks. Her work bridges theoretical modeling with practical network performance evaluation. The most recent articles highlight a strong trend in using machine learning—especially ensemble and neural network models—for short-term and long-term network traffic forecasting. These publications emphasize challenges such as feature selection, bandwidth blocking, node failure resilience, and traffic fragmentation in spectrally-spatially flexible optical networks. The research is deeply applied, targeting real-world network performance improvements. Scientific profiles: Google Scholar ResearchGate ORCID: 0000-0003-2654-4893 She is involved in supervising diploma theses and has participated in international research collaborations, including an internship at Politecnico di Torino, Italy, under the InterDocSchool program. She has presented her work at major conferences such as GLOBECOM, ONDM, RNDM, and CNSM. Her PhD thesis, titled "Optimization of multilayer networks with time-varying traffic aided by traffic prediction", is supervised by Prof. Krzysztof Walkowiak, with Dr. Piotr Lechowicz as co-supervisor. She is part of ongoing research projects including: Dark-Box Optimization – Developing highly effective general-purpose optimizers Evolutionary methods for multi-criteria optimization with many criteria Advanced optimization of multi-layer application-aware networks (MAAN) Using multi-criteria optimization in classifier training for decision-making tasks

Tami Brown-BrandlView profile

Professor

• Precision Livestock Farming
• Animal Behavior Monitoring
• Computer Vision in Agriculture
• +3 more

Tami Brown-Brandl is Professor and holder of the Dr. William E. and Eleanor L. Splinter Chair in Biological Systems Engineering at the University of Nebraska-Lincoln, where she conducts pioneering research at the intersection of agricultural engineering and animal science. Her research program focuses on: Computer vision systems for animal behavior monitoring Vibration-based vital signs detection in livestock Digital twin development for agricultural buildings RFID and sensor fusion for precision livestock farming Swine and beef cattle production optimization Individual animal identification using deep learning Recent publications (2023-2025) demonstrate a clear trajectory toward real-time, non-invasive monitoring systems using multi-modal sensor fusion. Her work integrates computer vision with ambient vibration analysis for piglet nursing behavior assessment, develops depth-image-based posture classifiers for sows, and creates digital twin frameworks that harness real-time data for precision livestock management. These innovations address critical challenges in animal welfare assessment and production efficiency through advanced engineering solutions. Dr. Brown-Brandl's leadership in precision livestock farming is evidenced by her extensive publication record on sensor systems development, with particular emphasis on practical applications for swine production systems including shoulder lesion detection, feeding behavior monitoring, and farrowing pen optimization.

Matthew ThorpeView profile

Associate Professor

• Machine Learning
• Data Science
• Applied Mathematics
• +4 more

Matthew Thorpe is an Associate Professor in the Department of Statistics at the University of Warwick and a member of the European Laboratory for Learning and Intelligent Systems (ELLIS). His research focuses on applying methods from applied analysis—including partial differential equations (PDEs), calculus of variations, and optimal transport—to machine learning and data science challenges. He has organized workshops such as the 'Machine Learning in Infinite Dimensions' at ETH Zurich and the 'LMS-Bath Symposium on Inverse Problems and Artificial Intelligence in Medicine.' Thorpe currently seeks PhD students for his research projects. His work bridges theoretical mathematics with practical applications in data-driven fields. Thorpe's research interests include manifold learning in Wasserstein space, PDE-based approaches to data science, and convergence analysis of graph-based learning algorithms. He has contributed to understanding the impact of imputation quality on machine learning models and developed novel transportation distances for pattern recognition. His interdisciplinary approach integrates mathematical rigor with advancements in artificial intelligence. He has co-organized the One World Seminar Series on the Mathematics of Machine Learning and remains active in promoting collaborative research initiatives. Despite no explicitly listed awards, his prolific publication record reflects sustained academic impact. Thorpe’s advising focuses on training students in the intersection of applied mathematics and modern data science techniques.

Samuel DahanView profile

Associate Professor

• Legal AI
• Dispute Resolution
• Global Work
• +4 more

Samuel Dahan is an Associate Professor at Queen’s University Faculty of Law and Director of the Conflict Analytics Lab. He holds visiting faculty positions at Cornell University, Paris Dauphine University, ENA, and Harvard University. His expertise spans Legal AI, Dispute Resolution, and Global Work, with a focus on open-source platforms like OpenJustice and the Deel Lab for global employment policy. Education: MA: Sorbonne-Ecole Normale Supérieure Ulm LLM: Katholieke Universiteit Leuven PhD: University of Cambridge Research Interests: Dahan’s work integrates data science with legal challenges, including AI-driven legal tools, conflict resolution analytics, and global workforce compliance. He leads initiatives like OpenJustice, an open-source platform with over 20,000 monthly queries, and the Deel Lab for HR tech innovation. Notable Achievements: Secured $1.1M in grants (NSERC-MITACS Partnership). Published in top venues: AAAI, ICML, McGill Law Journal. Keynote speaker at the French Supreme Court Hearing, Stanford Codex, and Law Society of Ontario. Labs & Teams: Directs the Conflict Analytics Lab at Queen’s University and co-leads the Deel Lab. His teams develop tools like the Deel AI Classifier and MyOpenCourt, addressing legal challenges through data-driven solutions.

Ian BayleyView profile

Senior Lecturer

• Cybersecurity
• Secure Programming
• Exploits
• +11 more

Dr. Ian Bayley is a Senior Lecturer in Computer Science at the School of Engineering, Computing and Mathematics, Oxford Brookes University. He serves as Subject Coordinator for MSc courses in Computing Science, Advanced Computer Science, and Computer Science for Cyber Security. His research focuses on cybersecurity, secure programming, software engineering, and design patterns, with collaborations on topics like LLM evaluation, exploratory testing for machine learning, and agent-oriented programming for microservices. He is affiliated with the Cloud Computing and Cybersecurity Group (CCC) and the Artificial Intelligence, Data Analysis and Systems (AIDAS) Institute. Teaching responsibilities include modules such as Secure Programming (undergraduate/postgraduate) and Professional Programming Practice for first-year undergraduates. He actively supervises cybersecurity projects and students, including Debalina Ghosh (LLM evaluation) and Kieren Stanton (authentication in vehicular networks). Research interests span cybersecurity patterns, software design composability, formal methods for web services, and agent-oriented approaches to microservices. Recent work explores LLM evaluation via scenario-based meta-information and testing challenges in machine learning applications. He co-leads research on design pattern composition and algebraic specifications. Publications span journals like Journal of Systems and Software and IEEE Transactions on Software Engineering , addressing topics from cybersecurity patterns to formal verification of web services. His teaching and research emphasize practical software engineering principles and cutting-edge cybersecurity practices.

• Safety Analysis of Autonomous Systems
• Multi-Agent Systems
• Hazard Analysis Simulation
• +3 more

Rob Alexander is a Senior Lecturer in the Department of Computer Science at the University of York. He holds a BSc from Keele University (2001) and a PhD in Computer Science from the University of York (2008). His research focuses on safety analysis and testing of autonomous robots and multi-agent systems, including simulation methods for hazard analysis and empirical evaluation of safety engineering techniques. He is part of the High Integrity Systems research group. Key research interests include situation coverage-based safety analysis, autonomous systems verification, and safety assurance methodologies. His work spans robotics, autonomous vehicles, and safety-critical systems, with applications in mine environments, healthcare, and transportation. Recent publications emphasize rigorous testing frameworks, risk assessment in complex systems, and bridging theoretical and practical safety engineering challenges. No scientific awards or grants are explicitly listed. He serves as a Union Rep within the department and is involved in academic leadership roles. His research group collaborates on projects such as SCALOFT and SASSI, focusing on safety assurance in autonomous systems.

• Evolutionary Swarm Robotics
• Optimisation and Learning
• Artificial Intelligence
• +1 more

Peter Ross is a Researcher at the Edinburgh Napier University , affiliated with the School of Computing Engineering and the Built Environment and the Centre for Algorithms, Visualisation and Evolving Systems . He collaborates with academics like Emma Hart, Alistair Lawson, and Andrew Webb on projects involving evolutionary swarm robotics , artificial immune systems , and optimisation algorithms . His research focuses on applying bio-inspired computing to robotics, including work on perceptual aliasing , adaptive scheduling , and swarm intelligence . He has supervised postgraduate research, notably serving as Director of Studies for Dr Neil Urquhart’s thesis on evolutionary machine learning in metamorphic malware analysis (1999-2003). His publications span 1998-2003 and explore intersections between immunology , sparse distributed memory , and robotic systems . Recent projects like VanFill Innovation Voucher (2025) indicate ongoing involvement in AI-driven solutions and human-robot interaction research.

• Machine Learning
• Kernel Methods
• Model Selection
• +11 more

Gavin Cawley is a Professor in the School of Computing Sciences at the University of East Anglia (UEA), with additional affiliations to the Data Science and AI group, the Centre for Ocean and Atmospheric Sciences, and the Statistics group. His research spans machine learning, bioinformatics, climate modeling, and environmental data analysis. His primary research interests include Machine Learning , Kernel Methods , Model Selection , Bayesian Regularization , Bioinformatics , and Climate Modeling . He has made significant contributions to understanding overfitting in model selection, sparse logistic regression for gene and cancer classification, and time series classification using ensemble methods. His work bridges theoretical machine learning with practical applications in biology, archaeology, and environmental science. The recent trend in his publications shows a strong interdisciplinary focus, combining machine learning with climate science (e.g., Arctic sea ice prediction) and molecular biology (e.g., protein domain movements). His work often involves developing and evaluating statistical models for complex real-world problems, emphasizing robustness, interpretability, and predictive accuracy. While no specific awards are listed in the provided text, his extensive publication record in top journals such as Journal of Machine Learning Research , Bioinformatics , and Neural Networks , along with high citation counts (e.g., over 1,800 citations for his 2010 paper on overfitting), indicates significant recognition in the academic community. He has also contributed to organizing major machine learning challenges, such as the ChaLearn AutoML and Active Learning challenges. He has supervised or collaborated with numerous researchers across disciplines, though specific student names are not listed. His work involves methodological development in model selection, kernel learning, and survival analysis, often applied to biological and environmental datasets. He has been involved in projects related to predictive uncertainty, ozone forecasting, and microbial growth modeling. While no specific lab or team name is mentioned, his affiliations with the Data Science and AI group and the Centre for Ocean and Atmospheric Sciences suggest active participation in interdisciplinary research teams focused on data-driven environmental and biological modeling.

• Numerical and computational mathematics
• Data management and data science
• Artificial intelligence
• +2 more

Musa Mammadov is a Senior Lecturer in Data Science at Deakin University's School of Information Technology, part of the Faculty of Science Engineering and Built Environment. His research focuses on data science, machine learning, and computational mathematics with applications in environmental modeling, healthcare analytics, and financial systems. Education: Doctor of Philosophy from University of Ballarat Research Interests: Specializing in numerical and computational mathematics, Mammadov develops advanced machine learning techniques for complex classification problems while exploring optimization methods in mathematical economics. His work spans environmental modeling applications in Sri Lanka's Kalu River Basin, healthcare fraud detection algorithms, and financial market analysis. Scientific Contributions: The recent publications highlight his work in hydrological forecasting using deep learning architectures, anomaly detection in medical billing systems, and probabilistic modeling of financial indices. His methodological contributions include improving Bayesian network classifiers and developing novel dependency estimation techniques. Academic Roles: Mammadov serves as editorial board member for Optimization Letters and Annals of Data Science . He supervises doctoral students in data science projects including health provider billing analysis and satellite downlink scheduling optimization.

Walter BisangView profile

Professor

• Language Typology
• Theoretical Linguistics
• Historical Linguistics
• +2 more

Walter Bisang (born February 2, 1959, in Zurich) is a Swiss linguist and Professor of General and Comparative Linguistics at Johannes Gutenberg University Mainz since 1992. His research focuses on language typology and theoretical linguistics, with extensive empirical work on East and Southeast Asian languages, Caucasian languages (especially Georgian), Austronesian languages, and Yoruba. His educational background includes: Major in General Linguistics with minors in Chinese and Georgian at the University of Zurich (1978-1986) Advanced studies in Thai, Khmer, and linguistics at the School of Oriental and African Studies, University of London (1986/1987) Doctorate in General Linguistics from the University of Zurich (1990) with a comparative thesis on East and Southeast Asian languages Bisang's research spans language typology , grammaticalization , areal typology , and language contact , investigating phenomena such as verb serialization, clause linking, finiteness, numeral classifiers, and argument structure. His work integrates formal and functional linguistic frameworks to analyze structural diversity and change across language families, emphasizing how contact situations reshape linguistic systems. He critically examines linguistic complexity metrics and their theoretical implications across different grammatical traditions. His publication record (1992-2009) reveals a sustained focus on comparative grammar of understudied language families, particularly highlighting typological patterns in East/Southeast Asia. His articles consistently bridge theoretical debates with empirical data, demonstrating how grammaticalization pathways diverge in areal contexts and how precategorial systems challenge traditional parts-of-speech classifications. His scientific recognition includes: Election to Academia Europaea (2016) Bisang has led major interdisciplinary projects including the EUROTYP initiative (1992-1995) and the German Research Foundation's Collaborative Research Center on 'Cultural and Linguistic Contacts' (1999-2008), where he coordinated teams spanning ancient history, ethnology, and linguistics. He currently serves on the DFG Review Board 104 evaluating typology and historical linguistics proposals, while co-editing the 'Trends in Linguistics' series and two journals ('Asian Linguistics' and 'Zeitschrift für Sprachwissenschaft'). His editorial work significantly shapes publication standards in cross-linguistic research.