Skip to main content

Ming-Chun Huang

Associate Professor of Data and Computation at Duke Kunshan University
DKU Faculty

Overview


Huang has a B.S (2007) in Electrical Engineering at Tsing Hua University, Taiwan, an M.S. (2010) in Electrical Engineering at the University of Southern California, and a Ph.D. (2014) in Computer Science at the University of California, Los Angeles. Prior to joining Duke Kunshan University in 2021, he was an Associate Professor at Case Western Reserve University (2014-2021). His research focus is the intersection among Precision Health and Medicine, Internet-of-Things, Machine Learning and Informatics, Motion and Physiological Signal Sensing. He had over 15 years of research experience conducting interdisciplinary scientific projects with researchers from distinct areas (e.g., Biomedical Engineering, Medicine, and Nursing). He had successfully administered past funded projects and productively published over a hundred peer-reviewed publications, 6 invention patents and software copyrights, and won 7 best paper awards/runner-up, 3600+ citations. His research has been reported in hundreds of high-impact media outlets. For the nature of richness and high impact of the research topics he was involved in, his research results in a plethora of new knowledge in aspects ranging from innovative IoT sensing technology, closed-loop AI analytics methodology, optimized clinical decision-making, and just-in-time patient risk assessment.

Current Duke Appointments & Affiliations


Associate Professor of Data and Computation at Duke Kunshan University · 2021 - Present DKU Faculty

Recent Scholarly Works


NeuroLens: A multimodal patient system for early screening and real-time monitoring of Parkinson’s disease

Journal article Smart Health · September 1, 2026 Parkinson’s disease (PD) is a progressive neurodegenerative disorder that requires early detection and continuous monitoring. This paper presents NeuroLens, a multimodal patient system that integrates sensor data, behavioral analysis, and real-time monitor ... Full text Cite

DyST-GT: Learning interpretable dynamic brain connectivity for motor-related BCI via spatio-temporal graph transformer

Journal article Smart Health · September 1, 2026 Electroencephalography (EEG)-based motor brain–computer interfaces (BCIs) enable direct neural control of external devices, yet existing methods inadequately model the dynamic nature of brain connectivity during motor-related tasks. Most graph neural netwo ... Full text Cite

Neurosense: Bridging Neural Dynamics and Mental Health Through Deep Learning for Brain Health Assessment via Reaction Time and p-Factor Prediction.

Journal article Diagnostics (Basel, Switzerland) · January 2026 Background/Objectives: Cognitive decline and compromised attention control serve as early indicators of neurodysfunction that manifest as broader psychopathological symptoms, yet conventional mental health assessment relies predominantly on subjecti ... Full text Cite
View All Scholarly Works

Education


University of California, Los Angeles · 2014 Ph.D.