Prospective graduate researcher in applied mathematics, statistics, and computational neuroscience.
My interests lie in statistically grounded and reproducible methods for biosignal analysis, particularly in brain–computer interfaces, neural signal decoding, and machine learning for physiological time series.
- Statistical learning and inference
- Data science
- Brain–computer interfaces
- Computational neuroscience
- Applied mathematics
- Primary language: Python
- Core tools: PyTorch, MNE
- Methodological emphasis: signal processing, statistical learning, and reproducible experimentation
- Application domain: EEG and ECG biosignal analysis
An EEG motor imagery classification pipeline with unified preprocessing and clearly separated within-subject, subject-independent, and transfer protocols on BNCI2014_001, comparing classical, Riemannian, and EEGNet baselines.
- Bronze Prize, KNOU Statistics & Data Analysis Competition '25
A refactored Python pipeline for five-class arrhythmia classification on MIT-BIH beat-level ECG data, with modular training, augmentation ablations, and reusable experiment artifacts.
- Silver Prize, KNOU Statistics & Data Analysis Competition '24
I am interested in problems where statistical inference, signal processing, and machine learning meet neural and physiological data. My recent work has focused on Python-based workflows for preprocessing, modeling, and evaluation in EEG and ECG analysis.
I plan to pursue graduate study at the intersection of applied mathematics, statistics, machine learning, and computational neuroscience, with the long-term goal of developing mathematically grounded methods for neural and physiological data analysis.