Parkinson’s disease tremor prediction towards real-time suppression: A self-attention deep temporal convolutional network approach
Abstract: Highlights•Self-Attention Deep Temporal Convolutional Network for tremor signal prediction.•Captures PDT signals’ characteristics for accurate multi-step ahead prediction.•Hierarchical feature learning with augmented spatiotemporal feature capturing.•Enhanced generalizability through more comprehensive testing conditions.•Test statistics show a statistically significant improvement from baseline models.
External IDs:doi:10.1016/j.compbiomed.2025.109814
Loading