Common spatial pattern-based feature extraction from the best time segment of BCI data


TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, vol.24, no.5, pp.3976-3986, 2016 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 24 Issue: 5
  • Publication Date: 2016
  • Doi Number: 10.3906/elk-1502-162
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.3976-3986
  • Keywords: Common spatial pattern, moving window, cursor movement imagery, feature extraction, support vector machines, BRAIN-COMPUTER INTERFACES, 2-D CURSOR CONTROL, MOTOR IMAGERY, EEG, CLASSIFICATION, SIGNALS, FILTER, SYSTEM, RHYTHM
  • Karadeniz Technical University Affiliated: Yes


Feature extraction is one of the most crucial stages in the field of brain computer interface (BCI). Because of its ability to directly influence the performance of BCI systems, recent studies have generally investigated how to modify existing methods or develop novel techniques. One of the most successful and well-known methods in BCI applications is the common spatial pattern (CSP). In existing CSP-based methods, the spatial filters were extracted either by using the whole data trial or by dividing the trials into a number of overlapping/nonoverlapping time segments. In this paper, we developed a CSP-based moving window technique to obtain the most distinguishable CSP features and increase the classifier performance by finding the best time segment of electroencephalogram trials. The extracted features were tested by using support vector machines (SVMs). The performance of the classifier was measured in terms of classification accuracy and kappa coefficient (kappa). The proposed method was successfully applied to the two-dimensional cursor movement imagery data sets, which were acquired from three healthy human subjects in two sessions on different days. The experiments proved that instead of using the whole data length of EEG trials, extracting CSP features from the best time segment provides higher classification accuracy and kappa rates.