Signals are the common thread. AI is how I explore them.
My work spans EEG and audio signal processing, coal–gangue recognition, mechanical fault diagnosis, and medical applications. I’m interested in how models learn useful structure from noisy, complex observations.
ResearchGate: October 2026 · Journal issue: January 2027.
A study of how changing working conditions affect acoustic coal–gangue recognition. It examines frequency-domain characteristics of tail-beam impact signals and the feature drift associated with varying operational parameters.
BKCad brings EEG and speech into a shared representation using pre-trained embeddings and a diffusion encoder. Bayesian uncertainty estimates and cross-modal attention guide confidence-aware fusion for depression detection.
International Journal of Coal Preparation and Utilization
MCL combines dual attention, dual Mamba modules and contrastive learning to distinguish coal from gangue in vibration signals. The framework learns class-specific similarities and differences before fusing representations for classification.