Find Academic Supervisors

Kris De BrabanterView profile

Adjunct Associate Professor

• Statistics
• Machine Learning
• Nonparametric Regression
• +3 more

Kris De Brabanter is an Affiliate Associate Professor at Iowa State University. His research focuses on statistical methodologies, machine learning, and their applications in forensic science, particularly bloodstain pattern analysis, as well as industrial engineering and kernel-based regression techniques. He holds a PhD from Katholieke Universiteit Leuven (2011) and advanced degrees from Erasmus Hogeschool Brussel and other Belgian institutions. Education PhD in Statistics, Katholieke Universiteit Leuven, 2011 Master of Science (Erasmus Hogeschool Brussel and Katholieke Universiteit Leuven), 2005–2007 Bachelor of Science, Erasmus Hogeschool Brussel, 2003 Research Interests De Brabanter’s work emphasizes kernel methods, nonparametric regression, and statistical modeling for real-world problems. He has pioneered automated bloodstain pattern analysis techniques using Euclidean geometry and likelihood ratios, contributing to advancements in forensic science. His research also extends to optimization under uncertainty, machine learning applications for large datasets, and robust statistical estimation. Publications Trends Recent articles highlight his expertise in bloodstain pattern classification, kernel-based regression with correlated errors, and surrogate modeling for remanufacturing systems. His work bridges theoretical statistics with practical applications in forensics, epidemiology, and engineering. Awards and Grants No specific awards or grants are listed in the provided information. Labs/Teams No lab affiliations or research teams are explicitly mentioned.

Daniel SchmidtView profile

Senior Lecturer

• Bayesian Inference
• Information Theory
• Statistical Genomics
• +7 more

Daniel Schmidt is a Senior Lecturer in Data Science at Monash University's Faculty of Information Technology, specializing in Bayesian inference, information theory, and statistical genomics. He holds a PhD in Computer Science (2008) and a Bachelor of Digital Systems (Honours) from Monash University (2003). His research focuses on high-dimensional Bayesian regression, Minimum Message Length (MML) principles, and applying machine learning to medical risk prediction, particularly in breast cancer via mammography analysis. He leads projects on scalable time series forecasting, quantum computing applications, and epileptic seizure prediction. Teaching commitments include developing and lecturing in units like FIT2086 (Modelling for Data Analysis) and FIT3154 (Advanced Data Analysis). He collaborates with institutions like the University of Melbourne (Adjunct Senior Research Fellow) and has contributed to open-source tools like the BayesReg package and GitHub repositories for statistical methods. His work contributes to UN Sustainable Development Goals related to health and innovation. Key research projects include efficient time series classification (MONSTER repository), seizure forecasting using EEG data, and quantum computing applications. He has authored over 119 publications, with recent work addressing adversarial attacks on time series models and Bayesian shrinkage priors for regression. Notable collaborations involve international teams in cancer genomics, statistical epidemiology, and materials science. His GitHub contributions include tools for random correlation matrix generation and fast AR model estimation.

• Machine Learning
• Neural Networks
• Computer Vision
• +4 more

Xiao Wu is a researcher affiliated with multiple academic institutions, including Southwest Jiaotong University (School of Information Science and Technology), University of Michigan (Department of Electrical Engineering and Computer Science), and Chinese Academy of Sciences (Institute of Computing Technology). His work spans diverse areas such as machine learning, computer vision, remote sensing, and medical image analysis. Research interests include transformer architectures , deep learning for time series and image processing , multi-agent control systems , and industrial optimization . Recent publications focus on novel neural network designs for applications in drilling process optimization, brain-computer interfaces, and multispectral/hyperspectral image fusion. His work integrates advanced algorithms like tensor decomposition , multiscale temporal convolution , and adaptive recalibration modules to address challenges in engineering and biomedical domains. Collaborations involve institutions like Harvard University, Jiangnan University, and Hong Kong Polytechnic University.

• Data Privacy
• Evolutionary Computing
• Recommendation Systems
• +5 more

Dr. Jinli Cao is a full-time Associate Professor in the Department of Computer Science and Information Technology at La Trobe University. She holds a BSc from Hebei University, China, and a PhD from the University of Southern Queensland, Australia (1997). Her research focuses on evolutionary computing, data privacy, deep learning for vulnerability assessment, and decision support systems. She has published over 150 papers in top venues such as VLDB and IEEE Transactions series. Dr. Cao leads an ARC-funded project on software vulnerability risk discovery and has secured three ARC grants. She has supervised 11 PhD, 2 Master’s, and 57 Honours students, many of whom work in academia and industries like Oracle and Commonwealth Bank. Teaching contributions include developing courses in databases, data warehouses, and artificial intelligence. Research Interests: Privacy-preserving data publishing and optimization Evolutionary algorithms for dynamic data partitioning Deep learning applications in cybersecurity and healthcare Graph-based machine learning for access control and anomaly detection Decision support systems and top-k query processing Her recent articles explore cutting-edge topics like privacy-preserving spatial crowdsourcing tasks, graph neural networks for traffic prediction, and cybersecurity frameworks for vulnerability prioritization. Awards include competitive ARC grants totaling $450,000 (2023-2025). She actively serves as an Associate Editor for Health Information Science and Systems and has examined over 100 PhD theses across Australian universities. Teaching highlights: Developed 20+ courses including Database Management Systems, Data Warehousing, and Artificial Intelligence. Coordinates units like Decision Support Systems and Intermediate Programming in Java.

• Machine Learning
• Distributed Systems
• Sensor Networks
• +7 more

Miloš Stanković is a Professor at the Faculty of Informatics and Computing, Singidunum University. His research focuses on distributed systems, reinforcement learning, machine learning applications, and sensor networks. He has contributed significantly to areas like multi-agent systems, optimization algorithms, and cybersecurity. Recent work includes distributed sensor network calibration, adaptive consensus algorithms, and AI-driven solutions for healthcare and infrastructure monitoring. Education: Not explicitly listed in provided texts. Likely holds advanced degrees in computer science or electrical engineering based on his publications. Research Interests: His primary areas include distributed multi-agent reinforcement learning, metaheuristic optimization for machine learning models, and real-world applications of AI in healthcare, surveillance, and smart infrastructure. He explores topics like sensor fusion, fault detection in networks, and consensus-based algorithms for decentralized systems. Article Trends: Recent publications emphasize AI-driven solutions (e.g., Parkinson’s disease detection via LSTM tuning, student dropout analysis with explainable AI) and distributed algorithms for multi-agent systems. His work bridges theoretical advancements in reinforcement learning with practical applications in sensor networks and cybersecurity. Grants/Projects: Not explicitly detailed, but involvement in EU-funded projects like Sinteza and SITCON conferences suggests external funding. Labs/Teams: Likely part of Singidunum’s research groups in AI, distributed systems, and cybersecurity. Collaborates with institutions like KTH Royal Institute of Technology (via co-author K.H. Johansson) on sensor networks and control systems.

George TzougasView profile

Associate Professor

• Actuarial Science
• Applied Statistics
• Computational Statistics
• +5 more

George Tzougas is an Associate Professor in the Department of Actuarial Mathematics & Statistics at Heriot-Watt University, Edinburgh. He serves as Academic Director of the Scottish Financial Risk Academy and Academic Chair of the IFoA’s Data Science Research working party on Statistical Learning in Actuarial Applications. Previously, he held a tenured position at the London School of Economics (LSE), where he was Programme Director for the BSc in Actuarial Science and a member of the Royal Statistical Society. His research focuses on applying statistical learning and computational methods to non-life insurance, finance, and climate change impact analysis. Key areas include insurance ratemaking, optimal reinsurance, green bond pricing, and climate-related risk modeling. He has published extensively on topics such as multivariate claim count models, machine learning for carbon price forecasting, and zero-inflated regression techniques. Education: Tenured position at LSE Department of Statistics (previously Programme Director for BSc Actuarial Science) Lecturer at University College Cork, Ireland Notable awards include multiple Excellence in Education Awards from LSE (2017–2020) and the Best Class Teacher Award (2017). His work contributes to UN Sustainable Development Goals related to climate action and sustainable finance. He advises on PhD projects involving climate change hazards in insurance and has taught courses such as Time Series and Machine Learning. Research collaborations span institutions globally, with a focus on interdisciplinary applications of actuarial science and data science.

John LiechtyView profile

Professor

• Statistics
• Financial Markets
• Marketing Research
• +7 more

John Liechty is a Professor of Marketing and Statistics at the Smeal College of Business, Pennsylvania State University. He holds a Ph.D. in Mathematical Statistics from the University of Cambridge (1998) and advanced degrees from Brigham Young University. His research spans statistical methodology, financial modeling, and marketing analytics, with notable contributions to option pricing, asset allocation, and systemic risk monitoring. He serves on editorial boards for journals like Marketing Science and Quantitative Finance . Education: Ph.D. in Mathematical Statistics, University of Cambridge, 1998 M.S. in Statistics, Brigham Young University, 1993 B.S. in Applied Physics, Brigham Young University, 1991 Research Interests: Liechty’s work combines statistical innovation with practical applications in finance and marketing. Key areas include: Bayesian methods and Markov Chain Monte Carlo (MCMC) algorithms Financial risk modeling and systemic risk analysis Public goods economics and incentive-aligned mechanisms Data reduction techniques and large-scale data analysis Marketing research methodologies, including conjoint analysis and web path analysis Professional Activities: Founder, Committee to Establish the National Institute of Finance (CE-NIF) Researcher, U.S. Department of Treasury’s Office of Financial Research (2013–2016) IBM Research Fellow (2010–2012) Consultant to financial firms like Morgan Stanley and Goldman Sachs Awards: Fellow of the American Statistical Association (2011) Fellow of the Royal Statistical Society (1999) IBM Faculty Fellow (2011) Teaching: Courses include Marketing Research (MKTG 342), Marketing Strategy (MKTG 450W), and Business Statistics (BA 815).

• Speech Processing
• Natural Language Processing
• Machine Learning
• +3 more

Murat Saraçlar is a full professor at the Electrical and Electronic Engineering Department of Boğaziçi University. He holds a B.S. from Bilkent University (1994), and M.S.E. and Ph.D. degrees from Johns Hopkins University (1997, 2001). Before joining Boğaziçi in 2005, he worked at AT&T Labs Research (2000–2005). He has held visiting positions at Google (2011–2012) and IBM T.J. Watson Research Center (2012–2013). Affiliations: Editorial roles include IEEE Transactions on Audio, Speech, and Language Processing (Senior Area Editor), and Computer Speech & Language (Editorial Board). Research Interests: Speech Processing, Natural Language Processing, Machine Learning, and Artificial Intelligence. His work focuses on speech recognition, keyword search, and medical signal analysis. Over 100 publications span journals like IEEE/ACM Transactions on Audio, Speech, and Language Processing. Awards include TÜBA-GEBİP Young Scientist Award (2009) and IBM Faculty Award (2010). Recent articles emphasize multimodal systems, unsupervised learning, and medical diagnostics. His contributions bridge theoretical advancements with practical applications in healthcare and communication systems.

Thomas BonaldView profile

Professor

• Data Analysis
• Machine Learning
• Graph Theory
• +4 more

Thomas Bonald is a Professor at Telecom Paris, part of the Institut Polytechnique de Paris, and heads the DIG (Data, Intelligence and Graphs) team within the LTCI laboratory. His research focuses on data analysis, machine learning, graph theory, knowledge bases, and natural language processing. He leads projects like the YAGO knowledge base and develops open-source tools such as scikit-network and torch-kge for graph analysis and knowledge graph embedding. Key achievements include advancing link prediction, knowledge base refinement using LLMs, and contributions to fair resource allocation in networks. His work integrates theoretical insights with practical applications, including enhancing adaptive streaming performance in mobile networks. Scientific awards include recognition of his former students Céline Comte (Telecom Paris award) and Mathieu Feuillet (Gilles Kahn award). Bonald advises numerous PhD students and has supervised over 20 doctoral candidates. His research spans algorithmic fairness, network science, and large-scale data integration. Labs/Teams: DIG team at LTCI, contributing to projects like YAGO and NetSet datasets. His teaching includes probability, statistics, graph learning, and reinforcement learning, with lecture notes on topics like PageRank and spectral embedding.

• Recommender Systems
• Machine Learning
• Graph Neural Networks
• +7 more

Yiwen Zhang is a researcher affiliated with Anhui University in Hefei, China, with a focus on Recommender Systems , Machine Learning , and Graph Neural Networks . Their work spans Data Mining , Imbalanced Data challenges, and Big Data optimization. Recent publications highlight advancements in robust recommendation via heterogeneous graphs, causal feature selection , and anomaly detection in time series. Key research areas: Recommender Systems, Machine Learning, Graph Neural Networks, Data Mining, Edge Computing. Notable applications: Imbalanced Data Classification, Social Recommendation, Edge Server Placement, Causal Discovery. Their 2025 and 2024 contributions include 15+ papers on topics like parameter-free sampling , graph attention networks , and causal inference . These works emphasize robustness , uniformity , and low-cost optimization in complex scenarios. Collaborations: Lei Sang, Dengcheng Yan, Qiang He, Yun Yang, Zhaolong Ling. Published in journals: Applied Intelligence , IEEE Transactions on Knowledge and Data Engineering , Expert Systems with Applications .

Keith SmithView profile

Lecturer

• Biomedical Network Analysis
• Neuroimaging Data Analysis
• Machine Learning in Neuroscience
• +4 more

Keith Smith is a Lecturer in the Department of Computer and Information Sciences at the University of Strathclyde, where he leads the Digital Health & Wellness Research Group (DHaWG). Previously, he held positions as a lecturer at Nottingham Trent University and as a UKRI Innovations Fellow in Medical Informatics at the University of Edinburgh. He earned his PhD in biomedical signal processing from the University of Edinburgh's IDCOM lab. His research focuses on computational tools for analyzing biomedical networks, including neuroimaging data from structural and functional brain networks, protein interaction networks, and metabolic networks. Key areas include hierarchical complexity of brain networks, machine learning applications for neuroimaging, and theoretical foundations of network geometry and complexity. He collaborates widely with clinical and academic partners to address challenges in neurological and mental health conditions like Alzheimer’s, depression, and schizophrenia. His work contributes to UN Sustainable Development Goals, particularly improving health and well-being through advanced data-driven methodologies. He currently oversees PhD projects exploring brain networks, deep learning for disease prediction, and evolutionary protein biology. Notable achievements include the UKRI fellowship and impactful interdisciplinary collaborations. His talks and presentations, such as on statistical complexity of brain networks, highlight his commitment to advancing theoretical and applied network science.

Paul L BendichView profile

Adjunct Professor

• Topological Data Analysis
• Machine Learning
• Computational Topology
• +4 more

Paul L Bendich is an Adjunct Professor of Mathematics at Duke University's Trinity College of Arts & Sciences. He holds a Ph.D. from Duke University (2008). His research focuses on adapting topological and geometric methods for data analysis, particularly in topological data analysis (TDA). He has pioneered TDA methodologies for applications in machine learning, sensor fusion, and environmental modeling. Current appointments include leading research initiatives in multi-modal data analysis and reinforcement learning optimization. Key areas of expertise include computational topology, persistent homology, and topological signal processing. He teaches courses on topological data analysis (COMPSCI 434, MATH 412) and has developed educational programs like Data+ at Duke. Grants include NSF-funded projects (BIGDATA: F: DKA: CSD) and Air Force Office of Scientific Research initiatives. Recent work emphasizes topological methods in AI safety (topological parallax), reinforcement learning efficiency, and geophysical feature tracking. Professional activities include conference presentations on TDA applications and editorial work for journals. His research bridges theoretical mathematics with practical data-driven challenges in science and engineering.

Harriette RieseView profile

Professor

• Psychopathology
• Emotion Regulation
• Depression
• +5 more

Dr. Harriette Riese is a Professor at the University of Groningen's Faculty of Medical Sciences and a core member of the Interdisciplinary Centre Psychopathology and Emotion regulation (ICPE). She serves as Principal Investigator for major research projects including the Netherlands Study of Depression and Anxiety (NESDA), ongoing since 2004, and the Lifelines population study. Her research expertise spans multiple critical areas in mental health: Psychopathology and emotion regulation mechanisms Depression and anxiety disorders across the lifespan Neuroticism and vulnerability to mental health conditions Digital mental health interventions and personalized treatment approaches Experience Sampling Method for real-time assessment of psychological processes Network analysis of psychological phenomena Dr. Riese's recent publications demonstrate a methodological sophistication in analyzing psychological processes, with increasing emphasis on digital tools for personalized mental healthcare. Her work bridges complex statistical approaches with clinical applications, particularly evident in projects like PETRA eDiary and the You-Turn study focused on implementing personalized digital diaries in routine mental healthcare settings. She actively supervises PhD students at the University of Groningen and maintains extensive collaborative networks across institutions. Her research is supported by major longitudinal studies that have generated significant insights into mental health trajectories and treatment responses. Her laboratory work centers on the Interdisciplinary Centre Psychopathology and Emotion regulation (ICPE), where her team investigates dynamic processes underlying mental health using innovative methodologies including digital phenotyping, experience sampling, and computational modeling of psychological networks.

• Computer Architecture
• High-Performance Computing (HPC)
• Cloud Computing
• +4 more

Prof. Weikuan Yu is a Professor in the Department of Computer Science at Florida State University. His research focuses on computer architecture, high-performance computing (HPC), cloud computing, parallel file systems, and deep learning applications. He holds the role of Chair and can be contacted via yuw@cs.fsu.edu or (850) 644-5442. His expertise includes optimizing storage systems and I/O behaviors in scientific workflows, developing scalable distributed systems, and applying machine learning to improve computational efficiency. Notable projects include work on burst buffer systems (e.g., BurstFS, TRIO), persistent memory management (PHAST), and distributed deep learning frameworks (e.g., compression techniques for time-evolutionary data). Recent research trends emphasize enhancing HPC storage efficiency through novel file systems and I/O emulation, as well as leveraging machine learning for fault tolerance and configuration tuning. His work bridges hardware-software co-design to address challenges in exascale computing and big data analytics. Prof. Yu has contributed to multiple open-source projects and frameworks, including OpenSHMEM-based key-value stores and MapReduce optimizations. His publications highlight advancements in parallel processing, distributed algorithms, and energy-efficient memory architectures.

Robert AzencottView profile

Professor

• Genomics
• Proteomics
• Medical Imaging
• +9 more

Robert Azencott is a Professor of Mathematics at the University of Houston and holds the title of Emeritus Professor at École Normale Supérieure in France. He specializes in interdisciplinary research at the intersection of mathematics, biosciences, and imaging. His work spans stochastic processes, data mining, and medical imaging applications such as 3D-echocardiography analysis and deformable shape matching. Azencott has contributed to probabilistic methods for bacterial genetic evolution models and financial market microstructure analysis. His research also addresses texture classification, kernel-based learning, and stochastic differential equations (SDEs) in finance and biology. Research Interests Genomics & Proteomics : Sparse modeling of gene interactions, microRNA impact on cancer survival, proteomic mass spectra analysis. Bacterial Evolution : Stochastic models for genetic evolution with periodic selection and large deviations theory. Medical Imaging : 3D-echocardiography strain analysis, deformable shape dynamics via diffeomorphic matching, and ROI reconstruction in X-ray tomography. Probability & Statistics : SDE parameter estimation, kernel-based clustering, and applications to algorithmic trading and option pricing. Labs & Collaborations Azencott collaborates on projects such as digital stains for live-cell microscopy and intra-cardiac echography analysis to assess myocardium deformations. His work intersects with teams in cardiology, computational biology, and financial engineering.