Find Academic Supervisors

• Biomedical Informatics
• Natural Language Processing
• Large Language Models
• +3 more

Weipeng Zhou is a Postdoctoral Associate at the Yale School of Medicine within the Department of Biomedical Informatics and Data Science . Working under Professor Hua Xu , he specializes in pre-training and evaluating large medical language models using electronic health records and medical claims data. His work bridges Natural Language Processing , Biomedical Data Science , and Clinical Informatics to address critical healthcare challenges. PhD in Medical Informatics from the University of Washington (2025) Bachelor's in Computer Science and Statistics from the University of Wisconsin (2019) His research involves NLP/LLM applications in healthcare domains such as: Long COVID characterization and prediction Cardiovascular disease analysis Suicide prevention through clinical text mining Clinical note section identification Emerging water contaminant detection via PubMed article analysis His publications focus on model transferability , automated cohort discovery , and contextual health research tools . Notable collaborations include work with teams at University of Washington and Yale .

Kobus BarnardView profile

Professor

• Computer Vision
• Machine Learning
• Scientific Applications
• +3 more

Kobus Barnard is a Professor in the Department of Computer Science at the University of Arizona, with his office located in GS 708. His research bridges computer vision, machine learning, and interdisciplinary scientific applications across diverse domains. Education: Ph.D. from Simon Fraser University (1999) His research interests focus on extracting meaningful insights from complex data through computer vision and probabilistic modeling. Key areas include machine learning for environmental monitoring (flood detection, plant disease analysis), social dynamics (interpersonal coordination, emotional coregulation), astronomy (transient classification), and multimodal learning (visual-linguistic integration). His work consistently applies deep learning to real-world problems requiring high-resolution data interpretation. Analysis of his 2022-2025 publications reveals three dominant trends: (1) Environmental applications using satellite imagery for flood mapping and agricultural monitoring, (2) Cognitive modeling of human teams and emotional dynamics through probabilistic frameworks, and (3) Astronomical data analysis leveraging host galaxy properties for transient classification. These threads demonstrate his commitment to solving practical scientific challenges through computational innovation. While scientific awards aren't documented in available sources, his leadership in projects like FloodPlanet and ToMCAT indicates significant contributions to data infrastructure. His advising and grant activities remain unreported in the source material, though his extensive interdisciplinary collaborations suggest substantial mentorship impact. Barnard's work operates at the intersection of multiple scientific communities, evidenced by applications spanning neuroscience, agriculture, astronomy, and social science. His current focus on high-resolution data fusion and multimodal modeling positions him at the forefront of real-world AI deployment.

Maarten van SteenView profile

Professor

• Distributed Systems
• Artificial Intelligence
• Edge AI
• +4 more

Maarten van Steen is a Professor active in the fields of Distributed Systems , Artificial Intelligence , and Cybersecurity . With an h-index of 35 and over 5,400 citations, his work focuses on Edge AI , Privacy Preservation , and WiFi-Based Sensing . His research emphasizes non-intrusive authentication, anonymization techniques, and crowd monitoring without compromising individual privacy. Key research areas: Distributed Systems, Privacy Preservation, WiFi Security Recent projects: RoomKey, LocKey, FlowPrint Crowd-monitoring applications: Subway travelers, pedestrian dynamics Van Steen's work combines Machine Learning with Homomorphic Encryption to develop privacy-first solutions. He has contributed to mobile app fingerprinting , WiFi authentication , and blockchain scalability challenges. His 2024–2025 publications reveal trends in contextual security , crowd behavior analysis , and automated threat intelligence . Notable methods include Bloom Filters, automata learning, and WiFi beacon frame analysis. Dutch Cyber Security Best Research Paper Award 2024 Runner-up (shared prize) Van Steen supervises research teams and collaborates on datasets like Code for Threat Intelligence Processing and DeepCASE . His work spans 20+ years , with 208 total research outputs and significant contributions to decentralized systems, network traffic analysis, and urban mobility.

Fajar Juang EkaputraView profile

Academic

• Semantic Web
• Knowledge Graphs
• Neurosymbolic AI
• +4 more

Fajar Juang Ekaputra is a Tenure Track Assistant Professor at the Institute of Data, Process, and Knowledge Management (DPKM), WU Vienna and a part-time Postdoctoral Researcher at the Data Science research unit, TU Wien . With a focus on Semantic Web , Knowledge Graphs , and their integration with Machine Learning in Neurosymbolic AI systems, his work spans domains like Cyber-Physical Systems and Materials Engineering . Education: Dr.techn. (2018), TU Wien M.T. (2010) and S.T. (2008), Institute Teknologi Bandung (ITB) Research Interests center on hybrid AI systems combining Semantic Web and Machine Learning , with applications in Cyber-Physical Systems (e.g., smart grids, smart buildings), data privacy in smart cities, and materials engineering . His 102+ publications include frameworks like SWeMLS-KG and SHACL4Protege . Recent Articles (2024) address explainable AI in cyber-physical systems, privacy trust in data infrastructures, and neurosymbolic frameworks . Earlier works (2023–2022) explore ontology-based data management , auditable AI , and hybrid system architectures . Scientific Awards: Best Paper Awards (ICoDSE 2023, ICoDSE 2016) Best Poster Nomination (SEMANTiCS 2019) PhD Scholarship (Austria’s Agency for Education and Internationalisation, 2012) Advising includes supervising PhD students (e.g., Majlinda Llugiqi, Katrin Schreiberhuber) and master’s theses on topics like knowledge graph characteristics and data quality assessment . He leads projects such as FAIR-AI (FFG-funded, 2024–2026) and SENSE (Horizon Europe, 2023–2025).

• VLSI CAD
• Low-power IC Design
• Mixed-signal IC Design
• +5 more

Riadul Islam serves as an Assistant Professor in the Department of Computer Science and Electrical Engineering at the University of Maryland, Baltimore County (UMBC), maintaining his primary office in room 316 of the Information Technology and Engineering (ITE) Building. His academic appointment focuses on hardware design and verification within the institution's engineering framework. His educational qualifications include: Ph.D. in Computer Engineering from UCSC (2017) M.A.Sc. in Electrical and Computer Engineering from Concordia University, Montreal (2011) B.Sc. in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology (2007) Professor Islam's research centers on VLSI CAD tools and low-power digital/mixed-signal IC design , with significant contributions to current-mode clock networks, vehicular security systems, and error-robust circuit architectures. His work increasingly integrates machine learning for design automation while exploring neuromorphic computing applications and secure hardware implementations. This multidisciplinary approach bridges traditional IC design with modern AI-driven optimization techniques. Analysis of his 2023-2025 publications reveals three dominant research thrusts: (1) Machine learning applications in early-stage Design Rule Checking (DRC) prediction and clock network optimization, (2) Graph-based intrusion detection systems for automotive networks (particularly CAN bus security), and (3) Event-based vision systems and neuromorphic computing architectures. These areas demonstrate consistent innovation in merging hardware design with AI/ML methodologies for enhanced system reliability and efficiency. He directs the UMBC VLSI and SoC Research Group , which develops energy-efficient clocking networks, secure vehicular communication protocols, and compute-in-memory architectures. The lab maintains active collaboration with industry partners on hardware security and neuromorphic computing initiatives while supporting graduate student research in cutting-edge IC design methodologies.

• Accessibility Research
• Web Accessibility
• Mobile Accessibility
• +5 more

Shari Trewin is a prominent researcher in accessibility and human-computer interaction at IBM Research with over 25 years of scholarly contributions. Her work focuses on making digital technologies accessible to people with disabilities, particularly in web and mobile contexts. She has published extensively in top-tier venues including ACM SIGACCESS conferences (ASSETS, W4A) and journals, CHI, and other leading HCI publications. Dr. Trewin's research interests span web accessibility, mobile accessibility for users with physical and cognitive disabilities, inclusive design methodologies, and the application of artificial intelligence to improve accessibility. Her work addresses both theoretical foundations and practical implementations of accessible technologies, with particular emphasis on user-centered design approaches and evaluation methodologies. She has made significant contributions to understanding how people with disabilities interact with digital interfaces and how to design systems that accommodate diverse user needs. Her publication record shows a clear progression from foundational work on input devices and keyboard accessibility in the 1990s to contemporary research on AI fairness for people with disabilities. Recent publications demonstrate her leadership in addressing emerging challenges at the intersection of AI and accessibility, particularly around algorithmic fairness and inclusive design practices for AI systems. Among her notable contributions are editorial work for ACM Transactions on Accessible Computing and co-editing conference proceedings for the ASSETS conference. She has collaborated extensively with leading researchers in the field including Vicki L. Hanson, Gregg Vanderheiden, and Calvin Swart. Dr. Trewin has advised junior researchers including Jessica J. Tran, and her work has influenced both academic research and industry practices in accessibility. Her research has practical implications for web developers, designers, and policy makers working to create more inclusive digital experiences.

Xu ShiView profile

Associate Professor

• Biostatistics
• Causal Inference
• Healthcare Data Analysis
• +5 more

Xu Shi is an Associate Professor in the Department of Biostatistics at the University of Michigan. Previously, they held a postdoctoral fellowship at Harvard’s Data Science Initiative (2017) under Tianxi Cai and Eric Tchetgen Tchetgen. Their research focuses on statistical methods for administrative healthcare data, electronic health records (EHR), and causal inference. Key projects include developing scalable pipelines for EHR curation, causal inference methods for comparative effectiveness studies, and co-leading the FDA’s Sentinel Initiative Innovation Center’s Causal Inference Core. Education: Ph.D. in Biostatistics from University of Washington (201?), B.S. in Mathematics & Applied Mathematics from Zhejiang University, China. Research emphasizes harmonizing distributed EHR data, addressing unmeasured confounding in air pollution studies, and rare adverse event analysis through flexible propensity score methods. They also explore medical knowledge extraction from ICD code patterns and natural indirect effect estimation robust to measurement errors. Awards: None explicitly listed. Grants & Advising: No specific grants or students listed, but their work involves collaborative initiatives like the FDA Sentinel Program. Labs/Teams: Active in the Causal Inference Core and distributed healthcare data partnerships with institutions like Henry Ford Health System and Kaiser Permanente.

İsmail ArıView profile

Assistant Professor

• Cloud Computing
• Big Data
• Machine Learning
• +12 more

Dr. İsmail Arı is an Assistant Professor in the Computer Science department at Özyeğin University . He holds a PhD from the University of California, Santa Cruz (2004), MS from University of Maryland (2000), and BS in Electrical & Electronics Engineering from Boğaziçi University (1998).

Yuè LiView profile

Professor

• Computational Biology
• Machine Learning
• Population Genetics
• +4 more

Yuè Li is a Professor in the Department of Computer Science at McGill University, where he leads the Li Lab focused on machine learning applications in genomics and healthcare. His research develops computational methods for analyzing electronic health records (EHR), single-cell multi-omics data, and population genetics. Dr. Li teaches core courses including Applied Machine Learning (COMP 551), Machine Learning in Genomics and Healthcare (COMP 565), and Computer Programming for Life Sciences (COMP 204). His research interests span: AI methods for computational biology and translational healthcare Multi-modal EHR integration and clinical topic modeling Time-series health forecasting and trajectory analysis Single-cell transcriptomics and epigenomics Polygenic risk modeling and causal variant inference Regulatory genomics and functional annotation integration Publications demonstrate strong focus on transformer architectures for healthcare forecasting, Bayesian methods for genomic inference, and neural topic models for clinical phenotyping. Recent work emphasizes foundation models for single-cell data and federated learning for EHR analysis. Scientific Awards: KDD HealthDay2022 Best Paper Award for seed-guided topic modeling Dr. Li mentors graduate students and postdoctoral researchers working on machine learning applications in biomedical domains. Current lab members include Master's students Bo-Hong Wang, Claris Gu, Neda Esfehani, and Ruilin Wang, along with postdoctoral researcher Dr. Jun Bai. The Li Lab operates within McGill's School of Computer Science, developing computational frameworks to integrate heterogeneous biomedical data for improved disease understanding and clinical decision support.

Arthur TrembanisView profile

Professor

• Coastal and estuarine morphodynamics
• Sediment transport
• Hydrodynamics
• +3 more

Arthur Trembanis is a Professor at the School of Marine Science & Policy at the University of Delaware , where he conducts interdisciplinary research in coastal and marine geoscience. His work bridges oceanography, sediment dynamics, and autonomous systems, with a focus on understanding coastal morphodynamics, hydrodynamics, and seafloor mapping. Coastal & Estuarine Morphodynamics Sediment Transport Modeling Autonomous Underwater Vehicles (AUVs) Seafloor Mapping & Geoacoustics Trembanis leads the Coastal Sediments, Hydrodynamics, and Engineering Lab (CSHEL) , which explores the intersection of marine technology and environmental science. His recent publications highlight advancements in AI-driven seafloor mapping, autonomous survey platforms, and coastal response to extreme weather. He is also active in open-source tools for geological feature detection and educational outreach. The 15 most recent papers reflect trends in machine learning for coastal geology (e.g., AI for Carolina Bay detection), autonomous robotics in marine surveys, and storm impact analysis on coastal systems. Key subfields include LiDAR processing, bedform dynamics, and multi-platform data integration for environmental monitoring. Fulbright Fellowship (University of Sydney) SERDP Project MR20-1480 (Munition mobility in estuarine environments) Follow his work via the CSHEL website , Instagram , or YouTube for fieldwork and lab updates.

• Machine Learning
• Deep Learning
• Video Classification
• +3 more

Reza Bosagh Zadeh is an Adjunct Professor at the Institute for Computational and Mathematical Engineering (ICME) at Stanford University. His research focuses on machine learning, deep learning, and their applications in video classification, healthcare analytics, and distributed algorithms. He specializes in developing scalable computational methods for real-time data processing and has contributed to advancements in neural networks and optimization techniques. Reza's work spans theoretical and applied domains, with notable contributions to TensorFlow frameworks, video summarization systems, and medical imaging analysis. His research often integrates interdisciplinary approaches, leveraging both academic and industrial collaborations. Notable projects include developing machine learning models for glaucoma detection and creating efficient algorithms for large-scale data processing in environments like Apache Spark. His publications emphasize real-time video stream analysis, distributed computing architectures, and practical implementations of deep learning. Reza holds a strong presence in both academic and tech sectors, with contributions to platforms like Twitter's Who-to-Follow system and innovations in edge computing for video surveillance.

• Business Process Management
• Process Mining
• Process Analytics
• +4 more

Hajo A. Reijers is a Professor at the University of Utrecht, Netherlands, with a former affiliation at Vrije Universiteit Amsterdam. His research focuses on Business Process Management (BPM), Process Mining, and Robotic Process Automation (RPA), emphasizing practical applications in healthcare, organizational processes, and human-computer interaction. He contributes to developing tools like SWORD for detecting workarounds and DEUCE for auditing electronic health records. His work spans algorithm development for process discovery, predictive analytics, and optimization techniques. Key areas include analyzing event logs, modeling workplace behavior, and enhancing process transparency. Reijers collaborates extensively with industry partners, addressing challenges in process automation, employee acceptance of AI, and ethical monitoring. His contributions to conferences like BPM, CAiSE, and ICIS highlight interdisciplinary approaches, combining computer science with organizational studies. Notable projects include frameworks for task mining, reinforcement learning in care processes, and pattern recognition in government transparency assessments. Research initiatives often involve cross-disciplinary teams, exploring topics like workplace well-being through process mining, decision-making support systems, and overcoming barriers to BPM adoption. His work bridges theoretical advancements with real-world impact, influencing both academic discourse and practical business solutions.

• New Product Development
• Knowledge Management
• Collaborative Work Environments
• +5 more

Angelo Corallo is an Associate Professor at the Department of Experimental Medicine, University of Salento, specializing in technologies and methodologies for collaborative processes in industrial systems. His research spans Digital Business Ecosystems , Cybersecurity , and Collaborative Product Design , focusing on the interplay between technology and organizational dynamics. He leads interdisciplinary research divisions in Open Networked Business Management , Learning and Innovation , and Collaborative Product Design . Research Interests : Corallo's work integrates Information and Communication Technologies (ICT) with Business Management, particularly in Digital Twins for healthcare and manufacturing Knowledge Modeling and Ontology Engineering Industry 4.0 and Smart Manufacturing Agri-Food Sustainability through digitalization Scientific Contributions : His recent articles explore trends in Cybersecurity for Industrial IoT Metaverse Applications in business models Traceability Systems in food supply chains Collagen-Based Biomaterials from aquaponics

Yasmeen GeorgeView profile

Senior Lecturer

• Artificial Intelligence
• Machine Learning
• Medical Image Analysis
• +6 more

Yasmeen George is a Senior Lecturer in the Department of Data Science & AI at Monash University's Faculty of Information Technology. She holds a PhD in Medical Image Processing from the University of Melbourne (2018) and a Master's in Computer Science from the University of Ain Shams (2013). Her research focuses on AI applications in healthcare, particularly medical image analysis for conditions like cancer, glaucoma, and psoriasis. She co-founded the AIM for Health Lab at Monash IT and is a research affiliate at the Victorian Institute of Forensic Medicine. Education: PhD (Medical Image Processing), University of Melbourne (2018); Master of Computer Science (Medical Image Analytics), University of Ain Shams (2013). Research interests include AI-driven medical image analysis, machine learning, and cross-domain healthcare analytics in radiology, dermatology, and ophthalmology. Her work addresses challenges in automated disease detection, lesion segmentation, and severity assessment across modalities like 2D/3D imaging and text data. Recent articles focus on kidney segmentation, glaucoma detection, federated learning for breast cancer, and AI frameworks for hazardous waste policy. Her research has led to patents with IBM and grants from MRFF and NHMRC. Awards: Recipient of the 2023 Heidelberg Laureate Foundation Alumni Award. Collaborations include projects on clean energy sustainability and hazardous waste management through advanced AI techniques. She actively advises PhD students and engages in interdisciplinary research teams across Monash and industry partners. Labs/Teams: Co-founder of the AIM for Health Lab, affiliated with the Victorian Institute of Forensic Medicine.

• Artificial Intelligence
• Pattern Recognition
• Biometrics
• +6 more

Venu Govindaraju is a SUNY Distinguished Professor of Computer Science and Engineering at the University at Buffalo, where he also serves as Vice President for Research and Economic Development. He founded the Center for Unified Biometrics and Sensors (CUBS) in 2003 and leads the National AI Institute for Exceptional Education, funded by a $20M NSF grant. His research focuses on artificial intelligence, pattern recognition, biometrics, and handwriting analysis, with notable contributions to postal automation, cybersecurity, and early screening for dyslexia/dysgraphia in children. Govindaraju holds IEEE and ACM Fellowships, and was named Person of the Year by the Council of Heritage and Arts of India in 2024. He has advised 47 doctoral students and pioneered foundational AI technologies impacting global industries. Research interests include: AI-driven education tools, handwriting recognition systems, document analysis, and cross-domain biometric technologies. His work bridges AI with humanities through projects like the Marianne Moore Digital Archive. Recent initiatives focus on leveraging AI to address speech-language pathologies and enhance K-12 education accessibility. Leadership roles include co-chair of SUNY’s AI Task Group and advisor to the SUNY-IBM AI Research Alliance. He is a vocal advocate for responsible AI policy, advising lawmakers at White House events and contributing to legislative briefings. His innovations are highlighted in Empire AI, New York’s $400M computing consortium.