Jiadong Yan

This paper introduces a self-supervised neural network method for ECG de-noising that adapts to different devices and improves classification performance compared to traditional methods.

This study examines brain structure-cognition associations in adolescents using a large dataset, finding that frontal, temporal, and occipital regions show strong age-related variability in these links.

This paper introduces a neural network for ECG classification that improves interpretability and performance by capturing long-dependent features and temporal patterns in raw ECG signals.

This study uses multi-task deep learning to identify unique functional neuroanatomy fingerprints for seven mental processes, showing high classification accuracy and robustness across datasets.