Biomedical Artificial Intelligence and Signal Processing Lab
Research Field
Dr. Hui-Ling Chan is an Assistant Professor at National Cheng Kung University, Taiwan (since Aug. 2023). Prior to joining NCKU, she served as a Researcher and Assistant Professor at Hiroshima University, Japan (Sep. 2019–Jul. 2023), and worked as a Machine Learning Engineer at the Industrial Technology Research Institute (ITRI), Taiwan (Jan. 2018–Sep. 2019). She completed her postdoctoral training at National Chiao Tung University, Taiwan (Jul. 2015–Dec. 2017), and previously held a research internship at McGill University, Canada (Apr. 2013–Apr. 2014).
Her research advances intelligent computing for biomedical signals, with two tightly connected thrusts: (1) EEG/PPG/ECG-driven intelligent analytics for smart healthcare and smart living applications, and (2) precision medicine for noninvasive neuromodulation (taVNS). Over the past five years, she has developed advanced neurophysiological methodologies and EEG-centered systems for real-world assessment and prediction, while also pursuing biomarker-driven personalization of neuromodulation—aiming to translate brain–body signatures into predictive models, parameter recommendation, and clinically translatable pipelines.
BAISP Lab’s overarching theme is intelligent computing based on biomedical signals. We develop computational methods and AI systems that transform neurophysiological and physiological measurements into actionable insights and clinically meaningful decision support. Our research is organized into two major domains: 1) Intelligent Analytics for EEG/PPG/ECG and 2) Precision Medicine for Noninvasive Neuromodulation. Together, these two domains form a unified “sensing → modeling → personalization” loop: biomedical signals provide measurable biomarkers, AI models generate predictions and explanations, and neuromodulation offers an intervention pathway toward precision health.
- Intelligent Computing Algorithms for EEG/PPG/ECG
We develop robust and reproducible computational methods for biomedical signals, including augmentation, representation learning, multimodal fusion, and interpretable modeling for decoding, classification, and prediction. - EEG-Centered Smart Healthcare and Smart Living
We build deployable EEG-driven systems and assessment tools for clinical decision support and everyday state monitoring (e.g., pain-, cognitive-, or affect-related states), emphasizing real-time feasibility, reliability, and cross-subject generalization. - Precision Neuromodulation: Outcome Prediction and Personalization
Centered on noninvasive neuromodulation (e.g., taVNS), we model individual variability (responders vs. non-responders), develop predictive biomarkers and outcome models, and advance stimulation-parameter recommendation toward clinically translatable personalization. - Brain–Body Coupling and Biomarkers
We quantify brain–body interactions by integrating EEG with ECG/PPG and behavioral measures, deriving objective biomarkers that link physiological dynamics to state, performance, and intervention effects—forming a foundation for both smart applications and precision interventions.
- Industrial Promotion Award
Industrial Technology Research Institute, 2018 - Student paper competition finalist
37th IEEE EMBC, 2015 - Best Paper Award
17th ASP-DAC, 2012
NATIONAL CHIAO TUNG UNIVERSITY, 2007-2015
PhD. in Computer Science & Information Engineering
NATIONAL TAIWAN NORMAL UNIVERSITY, 2001-2005
BA of Life Science
Job Description
This internship focuses on meta-learning methods for EEG, with an emphasis on brain–computer interface (BCI) applications and data analytics. The work involves building and evaluating EEG modelling pipelines that adapt across participants and sessions, with rigorous cross-subject benchmarking, reproducible experimentation and analytics workflows that translate results into actionable insights. The role also includes contributing to research-ready documentation (e.g., study protocols, ethics/participant materials where relevant), and producing clear technical resources (tutorials, guides, experiment notes) to support reliable collaboration and dissemination of results, with the assumption of effective/publishable research outputs.
Preferred Intern Educational Level
PhD student
Skill sets or Qualities
- Published research on meta-learning methods for EEG-based BCI (peer-reviewed or equivalent research output)
- Strong Python and deep learning implementation experience (e.g., PyTorch/TensorFlow) for EEG modelling pipelines
- Solid grasp of machine learning evaluation for EEG/BCI (cross-subject testing, session variability, baselines/ablations)
- Experience preparing research documentation for real-world studies (e.g., ethics submissions, participant-facing materials, protocols)
- Ability to develop clear technical materials (tutorials, guides, or training resources) that support reproducible research
- Proven facilitation and collaboration skills from delivering multiple training sessions and structured learning activities for diverse audiences
- Clear written and verbal communication for reporting results, presenting findings, and working effectively with a research team