I am a PhD student in Computer Science at Georgia State University working at the intersection of wearable sensing, bio-signal processing, and artificial intelligence (AI).
My research focuses on developing multimodal systems that integrate EEG, fNIRS, EMG, ECG, PPG, and motion data for real-time cognitive-motor and neurophysiological monitoring. I am particularly interested in reproducible wearable platforms, multimodal edge AI, and personalized health training systems that can operate reliably in everyday environments.
My work spans hardware, firmware, signal processing, machine learning, and real-time software, with the long-term goal of translating multimodal physiological data into practical and personalized support for human health.
Current Research
-
PPG-based closed-loop sensing and automated drug delivery for animal research
-
ECG signal processing, biometric security, and AI-based classification
-
Multimodal wearable sensing using EEG, fNIRS, EMG, ECG, PPG, and motion data
-
Edge AI for real-time cognitive-motor and neurophysiological state estimation
-
Personalized health training systems for exercise, cognition, and everyday activity support
Current Research Directions
• Wearable multimodal neurophysiological sensing platforms
• Signal quality assessment and synchronized biosignal acquisition
• Edge AI for robust real-time physiological state estimation
• Personalized and adaptive health training frameworks
• Usable wearable systems for older adults and real-world environments
Projects I led and contributed to
-
Built a graph neural network model for autism classification using fMRI data with gray and white matter.
-
Explored brain activation patterns during naturalistic movie watching with convolutional neural network-based video feature analysis.
-
Developed AI-enhanced Raman spectroscopy tools for detecting early skin abnormalities.
-
Designed real-time biosignal monitoring systems and emotion-recognition tools using ECG and EMG.
Technical Skills
-
Programming & Tools: Python, MATLAB, R, Linux, Git, C/C++
-
Deep Learning: CNN, Vision Transformer, Autoencoder, RNN, Transformer, LLM, AI Agents
-
Machine Learning: SVM, Random Forest, KNN, Regression
-
Applications: Detection, Segmentation, Classification, NLP
-
Biomedical Data Processing: PPG, ECG, EMG, fMRI, MRI, Raman Spectroscopy, Ultrasound, CT
-
Hardware/Firmware: nRF54, nRF52
-
Other: Real-time GUI with Python, Signal decomposition, PCA, ICA
Education
-
PhD in Computer Science, Georgia State University, USA
-
M.S. in Biomedical Engineering, New Jersey Institute of Technology, USA
-
M.E. and B.E. in Biomedical Engineering, Kyung Hee University, Korea