The common spatial pattern (CSP) and other spatiospectral feature extraction methods have become the most effective and\nsuccessful approaches to solve the problem of motor imagery electroencephalography (MI-EEG) pattern recognition from\nmultichannel neural activity in recent years. However, these methods need a lot of preprocessing and postprocessing such as\nfiltering, demean, and spatiospectral feature fusion, which influence the classification accuracy easily. In this paper, we utilize\nlinear dynamical systems (LDSs) for EEG signals feature extraction and classification. LDSs model has lots of advantages such as\nsimultaneous spatial and temporal feature matrix generation, free of preprocessing or postprocessing, and low cost. Furthermore,\na low-rank matrix decomposition approach is introduced to get rid of noise and resting state component in order to improve\nthe robustness of the system. Then, we propose a low-rank LDSs algorithm to decompose feature subspace of LDSs on finite\nGrassmannian and obtain a better performance. Extensive experiments are carried out on public dataset from ââ?¬Å?BCI Competition\nIII Dataset IVaââ?¬Â and ââ?¬Å?BCI Competition IV Database 2a.ââ?¬Â The results show that our proposed three methods yield higher accuracies\ncompared with prevailing approaches such as CSP and CSSP.
Loading....