A spatial-frequency-temporal optimized feature sparse representation-based classification method for motor imagery EEG pattern recognition

• Published in: Medical & biological engineering & computing Vol. 55; no. 9; pp. 1589 - 1603
• Main Authors: Miao, Minmin, Wang, Aimin, Liu, Feixiang
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2017; Springer Nature B.V
• Subjects: Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Brain; Classification; Competition; Computer Applications; Datasets; EEG; Entropy; Feature extraction; Feature recognition; Frequency dependence; Human Physiology; Human-computer interface; Image classification; Imaging; Implants; Mental task performance; Original Article; Pattern recognition; Radiology; Src protein; Motor imagery; Sparse regularization; Relative entropy; Sparse representation-based classification; Brain–computer interface
• ISSN: 0140-0118; 1741-0444
• DOI: 10.1007/s11517-017-1622-1

Effective feature extraction and classification methods are of great importance for motor imagery (MI)-based brain–computer interface (BCI) systems. The common spatial pattern (CSP) algorithm is a widely used feature extraction method for MI-based BCIs. In this work, we propose a novel spatial-frequency-temporal optimized feature sparse representation-based classification method. Optimal channels are selected based on relative entropy criteria. Significant CSP features on frequency-temporal domains are selected automatically to generate a column vector for sparse representation-based classification (SRC). We analyzed the performance of the new method on two public EEG datasets, namely BCI competition III dataset IVa which has five subjects and BCI competition IV dataset IIb which has nine subjects. Compared to the performance offered by the existing SRC method, the proposed method achieves average classification accuracy improvements of 21.568 and 14.38% for BCI competition III dataset IVa and BCI competition IV dataset IIb, respectively. Furthermore, our approach also shows better classification performance when compared to other competing methods for both datasets.