研究目的
To improve the classification accuracy of ERP-based BCIs by proposing a method of multilinear discriminant analysis with subspace constraints that addresses ill-posed and overfitting problems.
研究成果
The proposed SMLDA method improved classification accuracy in ERP-based BCIs by incorporating subspace constraints based on functional connectivity, demonstrating its effectiveness in single-trial ERP processing.
研究不足
The number of parameters in SMLDA is large, requiring careful tuning. The method assumes the same electrode locations for all subjects, which may not hold true in practice.
