Find Academic Supervisors

Eran HalperinView profile

Professor

• Computational Biology
• Genomics
• Machine Learning in Medicine
• +4 more

Dr. Eran Halperin is a Professor at the University of California, Los Angeles, affiliated with the School of Engineering (Computer Science Department) and the School of Medicine (Human Genetics, Computational Medicine, Anesthesiology). His research bridges computational biology, genomics, and machine learning, with a focus on developing statistical methods to analyze big medical data for disease prediction and treatment. Developed open-source software tools like FEAST, ReFACTor, and Bisque Recipients of prestigious awards including Rothschild Fellowship and ISCB Fellow (2021) Research Interests: Computational Genomics: Applying machine learning to genomic data (methylation, RNA expression) for disease understanding. Machine Learning in Medicine: Creating deep learning architectures for ophthalmology, anesthesiology, and acute care applications. Medical Data Science: Integrating electronic health records with genomic datasets for predictive modeling. Scientific Recognition: Rothschild Fellowship Technion-Juludan Research Prize Krill Prize in Science Elected ISCB Fellow (2021) Dr. Halperin's lab collaborates across disciplines, utilizing software platforms such as GLINT (methylation analysis) and MTV-LMM (microbiome prediction). His work has received funding from NIH, NSF, and international foundations.

• Artificial Intelligence
• Physics
• Computer Technology
• +4 more

Pedro Lind is a Professor at Oslo Metropolitan University's Faculty of Technology, Art and Design, where he serves in the Department of Information Technology with a focus on Artificial Intelligence. His academic appointments include active participation in research groups for Applied Artificial Intelligence and Mathematical Modeling. Dr. Lind's research spans interdisciplinary domains including: Biomedical AI applications (EEG classification, ECG analysis, eye tracking) Stochastic processes and complex systems modeling Trustworthy machine learning for security/privacy Physics-inspired computational methods Renewable energy statistics and modeling His recent publications demonstrate strong focus on developing novel AI methodologies for medical diagnostics (2024-2025), particularly using generative models and interpretable AI approaches for physiological data analysis. He leads significant research initiatives including the AI-Mind project developing diagnostic tools for dementia. Additional projects include international technology transfer collaborations with Czech Republic institutions. Dr. Lind maintains active research teams and labs focused on computational neuroscience and applied AI.

• Natural Language Processing
• Clinical Informatics
• Medical AI
• +5 more

Dr. Madhumita Sushil is an Assistant Professor in the Department of Medicine at the University of California, San Francisco School of Medicine. She holds a PhD in Computational Linguistics from the University of Antwerp (2021) and completed her postdoctoral training in Clinical NLP in Prof. Atul Butte's lab at UCSF in 2024. Her educational background includes a B.Tech in Computer Science and Engineering from VIT University (2013) and an M.Sc. in Language Science and Technology from Saarland University (2016). Dr. Sushil's research focuses on the intersection of natural language processing, artificial intelligence, and clinical medicine. Her work spans multiple healthcare domains including oncology, emergency medicine, pharmacology, and social determinants of health. She has published extensively on large language models in clinical settings, developing methods for clinical text analysis, patient risk assessment, and treatment outcome prediction. Her recent publications demonstrate her expertise in applying cutting-edge NLP techniques to real-world clinical challenges across various medical specialties. Her scholarly output shows a clear trajectory of increasing impact, with 11 publications in 2024 and 2 in 2025 already. These works appear in high-impact journals including JAMA Network Open, Nature Medicine, and JAMIA. Dr. Sushil frequently collaborates with key researchers at UCSF including Travis Zack, Christopher Williams, and Prof. Atul Butte, indicating strong institutional integration within UCSF's medical informatics ecosystem. Natural Language Processing in Clinical Settings Large Language Models for Medical Applications Clinical Decision Support Systems Analysis of Social Determinants of Health through Text Mining Oncology Informatics and Radiology Report Analysis Pharmacovigilance through Clinical Text Mining Dr. Sushil's work demonstrates a strong commitment to methodological rigor in applying AI to healthcare, with particular attention to reliable clinical implementation and validation of NLP systems across multiple institutions and clinical contexts.

Nicolas DuchateauView profile

Associate Professor

• Medical Imaging
• Cardiac Function Analysis
• Statistical Atlases
• +5 more

Nicolas Duchateau is an Associate Professor at Université Lyon 1 and researcher at the CREATIS lab in Lyon, France. He is also a Junior member of the prestigious Institut Universitaire de France (IUF) and serves as Associate Editor for the Neurocomputing journal. His academic career includes positions at Universitat Pompeu Fabra in Barcelona and INRIA Epione in Sophia-Antipolis, with his current role at Polytech Lyon's Biomedical Engineering department since 2016. His research focuses on characterizing diseases from medical imaging populations, with methodological development centered on statistical atlases and machine learning approaches to represent populations. On the applicative side, he concentrates on cardiac function and imaging modalities such as echocardiography and magnetic resonance. His work spans computational anatomy, pattern statistics, representation learning, manifold learning, auto-encoders, information fusion, cardiac imaging, shape and deformation analysis, risk stratification, and image synthesis. Duchateau's recent publications reveal strong trends in multimodal data fusion, particularly combining echocardiography with clinical records for patient stratification. He has made significant contributions to representation learning for cardiac population analysis, with increasing emphasis on diffusion models, uncertainty estimation, and domain adaptation techniques. His work bridges deep learning methodologies with clinical cardiology applications, focusing on interpretable AI solutions for cardiac function assessment. Junior Member of Institut Universitaire de France (2021) PhD prize for knowledge transfer from Universitat Pompeu Fabra (2014) Young Investigator Award at Euroecho conference (2010) Duchateau actively supervises numerous PhD and Master's students, including Anita Salvador, Thierry Judge, Pierre-Elliott Thiboud, and Romain Deleat-Besson. He has secured major research funding including a €75k grant from the Institut Universitaire de France (2021-2026), a €251k French ANR Young Researchers grant for the "MIC-MAC" project (2019-2024), and a €139k grant from the Fédération Française de Cardiologie for the "MI-MIX" project (2020-2023). He leads a vibrant research team at CREATIS lab focused on medical image analysis, where his group develops computational approaches to characterize cardiac diseases through population analysis. The team works at the intersection of machine learning, medical physics, and clinical cardiology, with ongoing projects spanning echocardiography analysis, MRI processing, synthetic data generation, and clinical decision support systems.

Satu-Pia ReinikainenView profile

Professor

• Multivariate Statistical Analysis
• Process Control
• Spectroscopy
• +3 more

Satu-Pia Reinikainen is a tenured Professor in Computational Engineering at the Lappeenranta-Lahti University of Technology (LUT) School of Engineering Sciences . With expertise in chemometrics and multivariate analysis, her work bridges statistical modeling, spectroscopy, and environmental monitoring. Research Focus Development of advanced kernel-based methods for process control Application of hyperspectral imaging in material and environmental analysis Microplastic pollution dynamics in aquatic systems Integration of spectroscopic techniques for real-time monitoring Conservation of geological and heritage materials through data-driven approaches Her research combines chemometric algorithms, environmental data analysis, and industrial process monitoring to solve complex analytical challenges.

• Forensic Science
• DNA Profiling
• Y-STR Analysis
• +3 more

Dr. Roberto Puch-Solis is a Principal Investigator at the Leverhulme Research Centre for Forensic Science , affiliated with the University of Dundee . His work focuses on probabilistic decision support systems, forensic statistics, and computational methods in forensic analysis. Expertise: Forensic genetics, DNA profiling, gas chromatography-mass spectrometry (GCMS), convolutional neural networks (CNNs), and Y-STR mutation modeling. Key Contributions: Development of open-access software ( MUCalc ), segmentation datasets for firearm analysis, and ground truth datasets for drug profiling. Collaborations: Active in interdisciplinary networks, with partnerships in digital forensics, analytical chemistry, and machine learning. Research Trends: Recent work integrates deep learning for forensic image analysis (e.g., shoeprint matching, cartridge case segmentation) and statistical frameworks for DNA evidence interpretation. Applications span firearms identification, drug quantification, and crime scene reconstruction. Activities: Delivered invited talks on probabilistic systems, served as an external examiner, and participated in neural network training workshops.

• Artificial Intelligence
• Machine Learning
• Big Data
• +5 more

Lingjia Tang is an Assistant Professor in Computer Science with expertise in artificial intelligence, machine learning, big data, and no-code automation. Her research focuses on developing machine learning algorithms for medical data analysis and advancing no-code automation tools to democratize technology access. Research Interests Artificial Intelligence & Machine Learning Big Data Analytics & Graph-Based Retrieval No-Code Automation & User-Centric Systems Data Quality & Ethical AI Considerations Scientific Contributions With over 20 publications in prestigious journals, Dr. Tang's recent work explores: Graph-based retrieval frameworks (GraphRunner, TOBUGraph) LLM calibration and evaluation (SLMEval) Memory subsystem optimization in datacenters Meaning-typed programming paradigms Multi-agent conversational AI systems Awards 2023 Award for contribution to machine learning technologies Teaching Dr. Tang teaches courses in artificial intelligence, algorithms, and computational theory with a dynamic interactive approach. Current Projects Machine learning algorithms for medical diagnosis No-code automation tools for non-technical users

Athol J KemballView profile

Professor

• Computation and Data
• Observation
• Stars and Planets
• +4 more

Athol J Kemball is a Professor in the Department of Astronomy at the University of Illinois at Urbana-Champaign, within the College of Liberal Arts & Sciences. He also holds affiliations with the National Center for Supercomputing Applications (NCSA) as a Professor and is a faculty affiliate of the Computational Science and Engineering program. Kemball is a member of the Center for Extreme-Scale Computation at NCSA/IACAT and leads the Kemball Research Group, which focuses on applying advanced computing to problems in observational astronomy. Dr. Kemball earned his Ph.D. in Physics in 1993. His educational background has provided the foundation for his interdisciplinary work at the intersection of computational science and astrophysics. Kemball's research lies at the intersection of advanced computing and astrophysics, with specific focus areas including: The theory of interferometry Astrophysical masers Late-type, evolved stars Gravitational lensing His work leverages extreme-scale computer systems to transform observational astronomy, enabling new scientific inquiries that were previously impossible. The exponential growth in computing capability has profoundly influenced his approaches to data-and compute-intensive scientific questions. An analysis of Kemball's recent publications shows a strong focus on applying computational methods to astronomical observations. His work spans from exoplanet detection using Bayesian methods to studying gravitational lensing and maser polarization. The research demonstrates a consistent theme of using advanced computing to extract maximum scientific value from observational data, particularly in the areas of interferometry and polarization studies. Among his notable recognition: Blue Waters Professor Named to the "List of Teachers Ranked as Excellent" four times since 2010 Kemball has been actively involved in teaching, offering courses such as Introduction to Astrophysics, Observational Astronomy, Scientific Writing for Astronomy, and Astronomical Techniques. His research group has participated in significant projects including the Square Kilometer Array Technology Development Project, specifically in the Calibration and Processing Group, addressing petascale computing challenges for radio astronomy. The Kemball Research Group focuses on applying high-performance computing to observational astronomy problems, particularly in interferometry, maser studies, and gravitational lensing. The group collaborates with the Center for Extreme-Scale Computation at NCSA/IACAT and contributes to advancing computational methods for next-generation astronomical facilities.

John PaparrizosView profile

Assistant Professor

• Databases
• Data Science
• Machine Learning
• +5 more

John Paparrizos is an Assistant Professor of Computer Science and Engineering at The Ohio State University's College of Engineering, where he directs The DATUM Lab (Data Analytics, Understanding, Mining, and Management Lab). He maintains an adjunct affiliation with the School of Informatics at Aristotle University of Thessaloniki. His research spans databases, data science, machine learning, and artificial intelligence , with focus areas including: Time-series analysis (clustering, anomaly detection) Scalable data mining for structured/unstructured data Adaptive algorithms for resource-constrained environments Foundational technologies for data-intensive applications His work addresses real-world challenges across relational, time-series, multimedia, text, graph, web, and IoT data domains. Notable recognition includes: 2025 ACM SIGMOD Test-of-Time Award for k-Shape time-series clustering 2023 IEEE TCDE Rising Star Award ACM SIGMOD Research Highlight Award NetApp Faculty Award His research has been featured in New York Times (front page), Washington Post , Forbes , and adopted by Fortune 500 companies (Exelon, Nokia) and the European Space Agency. He actively serves on program committees for premier conferences including ACM SIGMOD, VLDB, IEEE ICDE, ACM SIGKDD, and NeurIPS. His open-source tools have exceeded 100,000 downloads and are integrated into academic curricula at Brown, Columbia, Purdue, and University of Chicago.

Christophe KervazoView profile

Assistant Professor

• Sparse Blind Source Separation
• Nonnegative Matrix Factorization
• Hyperspectral Imaging
• +4 more

Christophe Kervazo is an Assistant Professor (Maître de Conférences) at Télécom Paris, France, affiliated with the IMAGES group under the Image, Data, Signal (IDS) department . His research focuses on sparse blind source separation, nonnegative matrix factorization, hyperspectral imaging, and optimization techniques for remote sensing and biomedical applications. Education: Engineering degree from Supélec (2015), Master of Science from Georgia Institute of Technology (2016), PhD in Signal and Image Processing from Université Paris Saclay (2019). His work spans deep learning for inverse problems (including deep unrolling techniques), remote sensing (hyperspectral imaging and SAR), and uncertainty quantification . Recent publications address synthetic data training for medical imaging, distributed sparse BSS, and nonlinear component separation. Collaborators include institutions like CEA Saclay, Université de Mons, and ONERA. Current students include PhD candidates working on topics such as digital breast tomosynthesis, hyperspectral unmixing, and SAR image reconstruction. Former students and interns have contributed to projects involving plug-and-play methods, unrolling algorithms, and implicit regularization. He is involved in teaching and research projects, including collaborations with Airbus and ONERA on hyperspectral imaging and spectral band optimization. His lab, LTCI (Information Processing and Communication Laboratory), supports interdisciplinary work in signal and image processing.

Laurence Likforman-SulemView profile

Associate Professor

• Document Analysis
• Handwriting Recognition
• Historical Document Processing
• +7 more

Laurence Likforman-Sulem is an Associate Professor at Institut Polytechnique de Paris , affiliated with the Signal, Statistics and Learning (S2A) team in the Image, Data, Signal (IDS) department . She has been at Télécom Paris since 1991, where she teaches Pattern Recognition , Signal Processing , and Document Analysis . PhD from ENST-Paris (1989) HDR from Sorbonne University (2008) Her research integrates Markovian methods (HMMs, Bayesian Networks) and deep learning (BLSTMs, CNNs) for: Handwriting recognition in historical documents Character analysis in Byzantine seals Parkinson’s disease detection through multimodal signals Biometric authentication using hand shape Recent work focuses on Byzantine seal character recognition (BHAi project) and multimodal group cohesion analysis (IEEE ICMI 2021 Best Paper). She has supervised 10 PhD students and numerous Master internships. Scientific Awards Winning system at ICDAR 05 Arabic Hand-Written Word Recognition Competition Fondation Telecom Thesis Award 2014 (2nd prize for Olivier Morillot) Best Paper Award, ICMI 2021 Active in conference leadership, she chaired ICDAR 2015 and ICPR 2022 document analysis tracks. Her 15 most recent publications span Byzantine document analysis, Parkinson’s detection, and low-energy neural architectures.

Sylvain MeignierView profile

Professor

• Speech Processing
• Audio Signal Processing
• Speaker Diarization
• +3 more

Sylvain Meignier is a Professor in Computer Science at the University of Mans, where he has been affiliated since 2004. He currently serves as Deputy Director of the LIUM (Laboratoire d'Informatique de l'Université du Mans) and leads research in speech and audio processing. His academic journey began with a PhD from Université d’Avignon et des Pays de Vaucluse in 2002. Research Focus: Speech processing, speaker diarization, audio signal analysis, and lifelong learning systems. Collaborations: Active in projects like DIGING and the ANTRACT project. Software Development: Co-developer of the SIDEKIT and S4D toolkits for speaker diarization. His recent work explores cross-domain speech processing, including overlap detection, gender analysis in broadcast media, and lifelong learning frameworks. Publications span interdisciplinary applications in digital humanities and core technical advancements in machine learning. No specific scientific awards are mentioned in the provided text. Sylvain also contributes to open-source tools and large-scale multimedia indexing challenges.

Cameron BrownView profile

Associate Professor

• Pharmaceutical Manufacturing
• Crystallization Processes
• Digital Design Tools
• +4 more

Dr. Cameron Brown is a Reader (equivalent to Associate Professor) at the Strathclyde Institute of Pharmacy and Biomedical Sciences, University of Strathclyde, Glasgow. He specializes in developing digital design tools and strategies for pharmaceutical manufacturing. Brown joined Strathclyde in 2014 and has progressed through research associate, research fellow, and Chancellor's fellow positions. He currently coordinates the Drug Substance Manufacturing module for the Advanced Pharmaceuticals Manufacturing MSc program. Education: Brown holds a PhD in crystallization process characterization and a Chemical Engineering degree, both from Heriot-Watt University. Research Focus: His work centers on three primary areas: Hybrid modeling approaches : Integrating physics-based and data-driven models to enhance drug substance manufacturing efficiency Self-driving labs : Developing automated systems for drug substance process development with model-based experimental design Digital decision-making : Implementing coupled models through GenAI and LLMs for rapid pharmaceutical process development His research contributes to UN Sustainable Development Goals through improved medicine manufacturing sustainability. Publication Trends: Brown's recent articles focus on pharmaceutical crystallization, digital design methodologies, AI applications in manufacturing, and process optimization. His work demonstrates strong emphasis on translating computational models into industrial practice, particularly in continuous manufacturing and quality-by-design frameworks. Honors: Elected staff officer of British Association of Crystal Growth (2024) Research Leadership: Brown serves as Principal Investigator for PharmaCrystNet and co-investigator on multiple major initiatives including Digital Design and Manufacturing of Amorphous Pharmaceuticals, Future CMAC Manufacturing Hub, Accelerated Discovery and Development of New Medicines Prosperity Partnership, and ARTICULAR. He leads knowledge exchange projects with pharmaceutical companies and manages knowledge transfer partnerships. Professional Engagement: Brown is active in the Acceleration Consortium and serves on the committee of the British Association of Crystal Growth.

Farhan TanvirView profile

Lecturer

• Graph Mining
• Bioinformatics
• Computational Biomedicine
• +3 more

Farhan Tanvir is a Lecturer in the Department of Computer Science at Georgia State University. His research focuses on graph mining applications in bioinformatics and computational biomedicine, particularly addressing challenges in drug-drug interaction prediction, drug repurposing, and disease modeling. He holds a PhD in Computer Science from Oklahoma State University and a BSc in Computer Science and Engineering from the Islamic University of Technology. His work emphasizes heterogeneous networks to model relationships between biological entities like drugs, proteins, and diseases. Recent research trends include tackling oversmoothing in graph neural networks (GNNs) through sparsification techniques and developing attention-based models for biomedical applications. His publications appear in top-tier venues such as KDD, DSAA, and ACM BCB. Tanvir has contributed to projects leveraging graph-based methods for computational biology, with a focus on predictive modeling and network analysis. His office is located at 1 Park Place, room 717.

• Vibrations
• Nonlinear dynamics
• Stochastic systems
• +3 more

Thomas Breunung is a Researcher and Principal Investigator of the Dynamics, Structures, and Data (DSD) Lab at the University of Wisconsin-Madison's Department of Mechanical Engineering. His work integrates applied mathematics, physics, and data science to study nonlinear structural dynamics, vibrations, and stochastic systems, with applications in aerospace engineering, biological systems, and oceanography. He holds a PhD from ETH Zurich (2021), an MS and BS from Technische Universität Darmstadt (2016, 2013). His research focuses on analytical, computational, and experimental methods to understand complex dynamic systems, including vibration attenuation, rogue wave prediction, and nonlinear oscillator identification. Notable awards include the 2023 ASME Outstanding Reviewer Award and the 2020 USNC/TAM Fellowship. Current courses taught include E M A 545 (Mechanical Vibrations) and M E 440 (Intermediate Vibrations). The DSD Lab emphasizes interdisciplinary collaboration, combining theoretical rigor with practical engineering solutions. Breunung's recent work explores data-driven forecasting of extreme events, stochastic noise utilization in vibration control, and robust system identification techniques. Ongoing projects include improving predictions of freak waves using field measurements and developing computationally efficient models for nonlinear mechanical systems.