SensoriMind-Trans Net: EEG and sensorimotor-driven transformer for athlete potential evaluation.

Introduction: In recent years, the integration of electroencephalogram (EEG) and somatosensory data in athlete potential evaluation has garnered increasing attention. Traditional research methods mainly rely on processing EEG signals or motion sensor data independently. While these methods can provide a certain level of performance assessment, they often overlook the synergy between brain activity and physical movement, making it difficult to comprehensively capture an athlete's potential. Moreover, most existing approaches employ shallow models, which fail to fully exploit the temporal dependencies and cross-modal interactions within the data, leading to suboptimal accuracy and robustness in evaluation results. Methods: To address these issues, this paper proposes a Transformer-based model, SensoriMind-Trans Net, which combines EEG signals and somatosensory data. The model leverages a multi-layer Transformer network to capture the temporal dependencies of EEG signals and utilizes a somatosensory data feature extractor and cross-modal attention alignment mechanism to enhance the comprehensive evaluation of athletes' cognitive and motor abilities. Results: Experiments conducted on four public datasets demonstrate that our model outperforms several existing state-of-the-art (SOTA) models in terms of accuracy, inference time, and computational efficiency. Discussion: Showcasing its broad applicability in athlete potential evaluation. This study offers a new solution for athlete data analysis and holds significant implications for future multimodal sports performance assessment.