Find Academic Supervisors

Gregory ErhardtView profile

Associate Professor

• Activity-Based Travel Models
• Application of Big Data to Travel Forecasting
• Transport Forecast Accuracy

Gregory Erhardt is an Associate Professor at the University of Kentucky's Stanley and Karen Pigman College of Engineering. His research focuses on advancing transportation forecasting through evidence-based policy decisions, integrating big data and activity-based models to address challenges in transit investment and emerging mobility technologies. Research Interests: Activity-Based Travel Models, Big Data Applications, Forecast Accuracy Assessment Email: greg.erhardt@uky.edu Erhardt's work spans the intersection of transportation infrastructure, data science, and policy analysis. He specializes in developing modeling tools to predict the effects of transit projects, evaluating ride-hailing impacts, and improving forecasting methodologies. Recent publications highlight trends in transportation network companies (TNCs), activity-based modeling frameworks, and transit ridership dynamics. His research explores ride-hailing driver participation, multi-modal optimization, and the relationship between microtransit and congestion patterns. Key themes include the integration of longitudinal datasets, bias mitigation in TNC data analysis, and evaluating the accuracy of traffic forecasting systems. His work provides actionable insights for policymakers in a rapidly evolving transportation landscape.

Matthew GrilliView profile

Associate Professor

• Neuropsychology
• Cognitive Neuroscience
• Memory
• +6 more

Matthew Grilli is an Associate Professor in the Department of Psychology at the University of Arizona , where he directs the Clinical Program, Neuropsychology Minor, and Human Memory Lab. His research spans the neuropsychology and cognitive neuroscience of autobiographical memory, imagination, and cognitive aging, with a focus on disorders like amnesia and Alzheimer’s disease. His work investigates individual differences in autobiographical thought , the impact of aging on memory specificity, and innovative neuropsychological assessment methods. Recent publications highlight aging-related changes in memory dynamics, brain structure-function relationships, and real-world applications such as phishing vulnerability and bilingualism’s role in cognitive aging. Grilli’s research utilizes naturalistic observation and computational approaches (e.g., latent brain state analysis, large language models) to study memory coherence, emotional simulation, and intergenerational conversations. He is also involved in developing tools like the Phishing Email Suspicion Test (PEST) to assess cognitive mechanisms in aging populations. The Human Memory Lab under his direction explores memory’s intersection with well-being, identity, and brain health, employing multimodal methodologies to address both theoretical and applied questions in cognitive neuroscience.

Stefan BleeckView profile

Professor

• Hearing Science
• Audiology
• Signal Processing
• +5 more

Professor Stefan Bleeck is a Professor of Hearing Science and Technology at the University of Southampton, leading the Hearing and Balance Centre and directing the Institute of Sound and Vibration Research (ISVR). His research focuses on the intersection of hearing science, audiology, and signal processing, with specialties in bio-inspired auditory modeling, speech intelligibility in noise, cochlear implants, and auditory evoked potentials. He holds a PhD in computational neuroscience and has held roles including Head of the Hearing and Balance Centre. Awards include Vice-Chancellor's Teaching Awards (2009) and Google Research Awards (2012). Education: Diploma in Physics (University of Darmstadt, 1995), PhD in Computational Neuroscience (University of Darmstadt, 2000). Research spans experimental, computational, and clinical approaches to improve hearing aids and cochlear implants. Active projects include developing speech enhancement algorithms, antiphasic speech tests for hidden hearing loss, and neural-space speech processing. Supervises multiple PhD students in engineering and computer science. Publications highlight advancements in speech enhancement, bio-inspired models, and cross-linguistic hearing tests. Collaborates with institutions like Google and the European Union on projects funded by EPSRC, Cancer Research UK, and others. His work aims to enhance speech understanding for hearing-impaired individuals through innovative signal processing and auditory modeling.

Ninghao LiuView profile

Assistant Professor

• Artificial Intelligence
• Machine Learning
• Explainable AI (XAI)
• +6 more

Dr. Ninghao Liu is an Assistant Professor of Computer Science in the School of Computing at the University of Georgia, part of the Franklin College of Arts & Sciences - Division of Physical & Mathematical Sciences. He holds a Ph.D. in Computer Science from Texas A&M University (2021) and an M.S. in Electrical and Computer Engineering from Georgia Institute of Technology (2015). His research focuses on Explainable AI (XAI), Graph Mining, Model Fairness, Recommender Systems, and Outlier Detection, with notable contributions to foundational AI techniques and their applications in education, healthcare, and environmental sciences. Dr. Liu has secured significant funding, including a three-year NSF grant (2022–2025) for 'Graph-Oriented Usable Interpretation' and a five-year $10 million grant from the U.S. Department of Education (2024–2029) for the GenAI Empowered National Initiative for STEM+C Education. He has also been honored with the Outstanding Paper Award at ICML 2022, Best Paper Award Shortlist at WWW 2019, and other distinctions. His work emphasizes interpretable machine learning, graph neural networks, and addressing algorithmic bias. He collaborates across disciplines, contributing to radiology AI, climate-smart forestry, and pandemic prediction through knowledge-enhanced deep learning. His lab is based at the Boyd Research and Education Center, where he advances research in trustworthy AI systems and data-centric solutions.

Enoch YeungView profile

Associate Professor

• Systems Biology
• Control Systems
• Machine Learning
• +7 more

Enoch Yeung is an Associate Professor in the Department of Mechanical Engineering at the University of California, Santa Barbara (UCSB). His research focuses on systems biology, control systems, machine learning, and data mining, with a particular emphasis on understanding how mechanical forces in DNA regulate gene dynamics and cell fate. He leads projects on distributed biological computing, data-driven control architectures, and synthetic biological systems design, supported by funding from DARPA, NSF, and the U.S. Army. Yeung holds a PhD in Control and Dynamical Systems from the California Institute of Technology and a BS in Mathematics from Brigham Young University. His work integrates methods from DNA biophysics, synthetic biology, microfluidics, and control theory to study genome organization and cellular decision-making. Recent projects include the DARPA Living Foundries program, the NSF Molecular Programming Project, and the AFOSR Biological Research Initiative. He has received numerous awards, including the NSF Early CAREER Award and Young Investigator Award from the U.S. Army. His lab conducts interdisciplinary research, including a 2024 Summer Synthetic Biology Workshop for high school students. Key research themes include DNA supercoiling dynamics, biophysical feedback control in cells, and scalable Koopman operator methods for analyzing complex biological systems. Lab Focus: Biological Control Lab explores DNA mechanics, synthetic biology, and data-driven modeling. Grants & Collaborations: PI on multi-institutional programs involving PNNL, DARPA, and NSF. Advisory Roles: Served on panels for DARPA, NIST, and the National Defense University.

Farshad MoradiView profile

Professor

• Neuromorphic Computing
• Spintronics
• Biomedical Engineering
• +5 more

Farshad Moradi is a Professor at the Department of Electrical and Computer Engineering at Aarhus University, specializing in neuromorphic engineering, spintronics, and biomedical device design. His work focuses on integrating advanced materials and circuits for applications in neural interfaces, energy-efficient computing, and wireless biomedical systems. Research Interests include: Spintronic-based neuromorphic computing architectures Ultra-low power analog/mixed-signal integrated circuits Ultrasonically powered implantable medical devices Neural signal processing and seizure detection systems Wireless energy transfer and structural health monitoring Key Projects (2016-2026): SPICE: Spintronic-Photonic Integrated Circuit Platform PHOTON-NeuroCom: Photonic-assisted Neuromorphic Computing Neuro-Sense: Flexible bioinspired neuroprostheses CorroSense: Self-powered corrosion monitoring HERMES: Hybrid Enhanced Regenerative Medicine Systems Recent innovations include: Ultrasonically powered optogenetic implants Low-power neural amplifiers for deep-brain interfaces Spin-torque nano-oscillator-based neuromorphic hardware Energy harvesting systems for structural monitoring

• Credit Scoring
• Consumer Credit Risk Modelling
• Predictive Analytics
• +3 more

Christophe Mues is a Professor of Data Science and Information Systems at the University of Southampton's School of Management, within the Department of Decision Analytics and Risk. His research focuses on credit scoring, consumer credit risk modeling, and applications of predictive analytics, including machine learning techniques for credit risk assessment. He leads the Information Systems & Business Analytics section and supervises multiple PhD students in Business Studies and Management. His work spans advanced statistical methods for predicting Probability of Default (PD), Loss Given Default (LGD), and loan profitability. He is actively involved in the academic community, serving on the organizing committee for the Credit Scoring and Credit Control conference. His teaching includes topics in information systems and business analytics. Contact: C.Mues@soton.ac.uk. Research Interests: Credit Scoring and Consumer Credit Risk Modelling Predictive Analytics in Finance Machine Learning Applications (Deep Learning, Graph Neural Networks) Non-Traditional Data Integration Credit Model Transparency and Fairness Debt Collection Optimization PhD Supervision: Currently guiding four students in Business Studies & Mngt: Kameswara Rao Korangi, Sarthak Gurnani, Pablo Casas, and Nora Agyei-Ababio. Professional Activities: Leads research groups and contributes to international conferences. His work bridges academic research with practical financial risk solutions, emphasizing ethical AI and regulatory compliance in credit modeling. Biography: Holds a PhD in Applied Economics from KU Leuven (Belgium). Joined the University of Southampton in 2004, advancing from researcher to his current leadership role in Decision Analytics and Risk.

Aaqib SaeedView profile

Assistant Professor

• Human-Centric AI
• Federated Learning
• Self-Supervised Learning
• +3 more

Aaqib Saeed is an Assistant Professor in the Department of Industrial Design at Eindhoven University of Technology. His research focuses on Human-Centric AI, Federated Learning, Self-Supervised Learning, and Audio Understanding, with applications in Personal Health. He holds a PhD (cum laude) from TU/e and an MSc (cum laude) from the University of Twente. Education: PhD in Computer Science (cum laude), TU/e (2021) MSc in Computer Science (cum laude), University of Twente (2018) Research Interests: Development of robust federated learning frameworks for decentralized data Self-supervised learning for audio and physiological signal analysis AI-driven solutions for healthcare monitoring Key Contributions: DeltaMask: Reducing communication overhead in federated fine-tuning FedNS: Mitigating noisy decentralized data in federated learning Labeling Chaos to Learning Harmony: Handling label noise in FL Professional Experience: Visiting Industrial Fellow, University of Cambridge (2023) Research Scientist, Philips Research (2019–2023) Research Internships: Google Research, TNO/EIT Digital Awards: UT Scholarship (MSc) Cum Laude awards for both PhD and MSc Labs/Teams: EAISI Health, EAISI Foundational, Computational Design Systems.

• Database Systems
• Machine Learning in Databases
• Self-Driving Database Management Systems
• +3 more

Lin Ma is an Assistant Professor in the Department of Electrical Engineering and Computer Science at the University of Michigan, Ann Arbor, since August 2023. His research focuses on advancing database systems through machine learning integration, with a particular emphasis on self-driving DBMS, query optimization, and GPU acceleration. He holds a PhD from Carnegie Mellon University, where he also served as a postdoctoral researcher, and previously worked as a Software Engineer at Databricks. Research Interests: Lin’s work bridges database management systems and machine learning, aiming to create autonomous systems capable of self-optimization. Key areas include workload forecasting, behavior modeling for self-driving DBMS, and leveraging GPU capabilities for large-scale analytics. His contributions have been recognized through publications in top venues like VLDB, SIGMOD, and CIDR. Service: He actively serves on program committees for major conferences including SIGMOD, VLDB, and CIDR, and has held roles such as Web/Information Chair for SIGMOD (2023). His contributions extend to academic service, including admissions and faculty search committees at CMU and UMich. Labs & Projects: Lin leads research initiatives in database systems, including the QueryBot5000 framework for workload forecasting, and collaborates on projects like Vortex and Database Gyms to advance GPU-accelerated analytics and self-driving system design.

Abdolmajid ErfaniView profile

Assistant Professor

• Construction Economics
• Data-driven Infrastructure Management
• Project Delivery and Procurement
• +5 more

Dr. Abdolmajid Erfani is an Assistant Professor in the Department of Civil, Environmental, and Geospatial Engineering at Michigan Technological University. He holds a PhD in Civil Engineering from the University of Maryland, College Park (2023), an MSc in Construction Engineering and Management from the University of Tehran (2019), and a BSc in Civil Engineering from the same university (2017). His research focuses on construction economics, smart construction technologies, data-driven infrastructure management, workforce development, and AI applications in project delivery. Dr. Erfani leads studies on workforce equity in transportation and construction industries, leveraging big data and natural language processing. He has published over 30 peer-reviewed papers and received prestigious ASCE awards including the 2024 Arthur M. Wellington Prize and Thomas Fitch Rowland Prize. He serves on the editorial board of the ASCE Journal of Management in Engineering. His recent grants include a National Cooperative Highway Research Program project (PI, 2024–2027) on price adjustment clauses for construction risk sharing and a Minnesota DOT-funded initiative (PI, 2025–2027) on leveraging transportation investments for economic equity. He also co-leads a Federal Railway Administration project (Co-PI, 2025–2028) aimed at promoting railroading careers. Research interests span equity analysis, AI modeling, and predictive analytics for infrastructure resilience. He integrates LinkedIn data and machine learning to study gender disparities in career progression, achieving groundbreaking insights in leadership dynamics within construction sectors.

• Bayesian statistics
• Computational statistics
• Environmental statistics
• +4 more

Roles & Affiliations: Distinguished Research Professor in Statistical Science at Queensland University of Technology (QUT), Director of QUT Centre for Data Science, and Associate Member of University of Oxford's Department of Statistics. Served as Deputy Director of ARC Centre of Excellence in Mathematical and Statistical Frontiers (2015–2021) and ARC Laureate Fellow (2015–2021). Education: BA (Hons) and PhD in Mathematical Statistics from University of New England, Australia. Completed post-doctoral roles at multiple Australian universities. Research Interests: Specializes in Bayesian statistical modelling, computational methods, and their applications in environmental science, genetics, healthcare, and industry. Leads projects on coral reef recovery, cancer epidemiology (Australian Cancer Atlas), and virtual citizen science platforms like Virtual Reef Diver. Her work emphasizes interdisciplinary collaboration, integrating complex data sources with advanced statistical techniques to address real-world challenges. Publications & Grants: Over 350 refereed journal publications and attracted >30 major grants. Recent focus areas include influenza epidemiology, spatial health disparities, and AI-driven early warning systems for climate-sensitive diseases. Active in developing methodologies for spatial statistics, small-area estimation, and federated learning. Awards & Recognition: 2024 Ruby Payne-Scott Medal (Australian Academy of Science), Pitman Medal (2016), first female recipient of this award in 35 years. Elected Fellow of Australian Academy of Science (2018), Academy of Social Sciences (2018), and Queensland Academy of Arts and Sciences (2018). Holds international roles including Vice-President of International Statistical Institute (2021–2025) and Scientific Council Member at Centre International de Rencontres Mathématiques (France). Supervision & Leadership: Supervised over 36 PhD students and leads teams in >50 collaborative projects. Current supervision includes 5 PhD and 4 Masters students at QUT. Founded the QUT Centre for Data Science and previously led the Collaborative Centre for Data Analysis, Modelling and Computation. Labs & Initiatives: Core contributor to the Australian Cancer Atlas 2.0, Virtual Reef Diver project, and Queensland's Learning Potential Fund. Active in global initiatives like the World of Statistics campaign and UN Big Data Task Teams.

• Smart Cities
• Cyber-Physical Systems (CPS)
• Internet of Things (IoT)
• +10 more

Dr. Hung Cao is an Assistant Professor of Computer Science at the University of New Brunswick, where he directs the Analytics Everywhere Lab. His work focuses on interdisciplinary research in Cyber-Physical Systems (CPS), IoT, Edge/Fog/Cloud Computing, and Explainable AI, addressing societal challenges through data-driven solutions. Prior roles include PostDoc Fellow and Data Scientist at the People in Motion Lab, UNB, and Lecturer/Researcher at Vietnam National University. He holds a Ph.D. in Geomatics Engineering (specializing in Data Science) from UNB (2020), an M.Sc. in Computer Science from University College Dublin (2015), and a B.Eng. from Vietnam National University (2011). Research interests span Smart Cities, Embedded AI, TinyML, Federated Learning, and Real-time Systems. He has led projects with Cisco, NB Power, and other industry partners to develop scalable analytics frameworks for IoT applications. Dr. Cao actively contributes to technical communities (IEEE Smart City, Edge Computing, etc.), serving as a reviewer for journals and conferences, and a Topic Editor for Electronics Journal . His innovations include the Analytics Everywhere framework for spatio-temporal data analysis, MACeIP platform for smart cities, and energy-efficient IoT systems for environmental monitoring. Current work emphasizes human-centered AI for healthcare diagnostics and industrial inspection systems.

• Artificial Intelligence and Data Science
• Decision Making & Optimization
• Machine Learning & Intelligence
• +8 more

Min Lee is a Full-time Assistant Professor of Computer Science at Singapore Management University's School of Computing and Information Systems (SCIS). Holding a PhD from Carnegie Mellon University (2021), Lee specializes in Artificial Intelligence with a focus on Human-AI Collaborative Systems and their applications in healthcare. Their research bridges technical innovation with human-centric design, emphasizing trustworthiness, explainability, and accessibility in AI systems. Research interests include decision-making optimization, human-machine collaboration, and AI-driven solutions for healthcare challenges such as stroke rehabilitation, elderly care monitoring, and clinical decision support. Lee has pioneered low-cost AI/robotic solutions for post-stroke rehabilitation exercises, integrating socially assistive robotics with real-time feedback mechanisms. Recent work highlights AI's role in enabling trustworthy clinical decision-making through explainable AI (XAI) techniques like counterfactual explanations and gradient-based methods. Their systems address ethical concerns in predictive healthcare and advocate for stakeholder-inclusive design processes. Awards and grants: No specific awards mentioned in the profile, though research has been supported through collaborative projects with clinical partners and iterative user evaluations involving therapists and patients. Advising focuses on multidisciplinary projects spanning AI, healthcare, and human-computer interaction. Current advisees include BHOSALE Rimmon Saloman, TRAN Truong Thuy, and YANG Xinlin. Lee collaborates closely with clinical stakeholders to translate technical advancements into practical healthcare solutions, emphasizing iterative design and real-world applicability. Labs/teams: Active in SCIS's AI and Data Science initiatives, leading projects on intelligent decision support systems, socially assistive robotics for rehabilitation, and human-centered AI ethics frameworks.

Fenglong MaView profile

Associate Professor

• Data Mining
• Health Care Informatics
• Machine Learning
• +5 more

Fenglong Ma is an Associate Professor at Pennsylvania State University, affiliated with the Institute for Computational and Data Sciences and the Center for Socially Responsible Artificial Intelligence. His research focuses on data mining, healthcare informatics, machine learning, natural language processing, and multimodal learning. He holds a Ph.D. from the University at Buffalo (2019) and degrees from Dalian University of Technology. His work addresses challenges in federated learning, medical AI, adversarial robustness, and multimodal systems. Key contributions include innovations in quantization for large language models, federated knowledge injection, and medical vision-language benchmarking. Recent publications explore topics like collaborative fairness in federated learning, robust medical vision-language models, and adversarial attack mitigation. His research bridges theory and practical applications in healthcare, cybersecurity, and personalized recommendation systems. He leads the PSU Data Science Lab and collaborates on projects involving AI ethics, multimodal data integration, and scalable medical foundation models.

• Machine Learning
• Augmented Intelligence
• Data Science
• +12 more

Simon Ruffieux is a Senior Researcher and Lecturer at the Department of Computer Science, University of Fribourg, and a member of the Human-IST Institute. He currently leads the HIP-Initiative (Human-IST x SwissPost Initiative) and coordinates academic projects related to Swiss Post. His academic roles include Lecturer and Senior Assistant , reflecting his active engagement in teaching and research. His research focuses on leveraging advanced technologies to support individuals, particularly those with special needs. Key areas include: Machine Learning and Data Science for urban systems (e.g., bike-sharing optimization) Human-Computer Interaction (HCI), especially gesture recognition and multimodal interfaces Augmented and Virtual Reality applications in rehabilitation and assistance Development of smart glasses for visually impaired users Physiological signal analysis for workload classification The 15 most recent publications reveal a strong trend in applying AI and data science to real-world challenges, particularly in assistive technologies and urban mobility. His work often involves interdisciplinary collaboration, integrating computer science with psychology, rehabilitation, and industrial applications. There is a consistent emphasis on user-centered design and real-world usability. Simon Ruffieux has not been mentioned as receiving specific scientific awards in the provided text. He has advised or collaborated with several researchers, including Nicolas Spycher, Samuel Torche, and Nicolas Ruffieux, on projects related to forecasting, AR, and gesture recognition. While no formal grant details are listed, his leadership of the HIP-Initiative suggests involvement in externally funded academic projects. His work is closely tied to the Human-IST Institute, where he contributes to interdisciplinary research in human-centered computing. He is actively involved in research teams focused on assistive technologies, gesture interaction, and data-driven urban solutions. The Human-IST Institute serves as the primary hub for his collaborative efforts, particularly through the HIP-Initiative with Swiss Post.