Mutual information-based selection of optimal spatial–temporal patterns for single-trial EEG-based BCIs

• Published in: Pattern recognition Vol. 45; no. 6; pp. 2137 - 2144
• Main Authors: Ang, Kai Keng, Chin, Zheng Yang, Zhang, Haihong, Guan, Cuntai
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2012
• Subjects: Bayesian classification; Brain-computer interface (BCI); Classification; Electroencephalogram (EEG); Feature selection; Filtering; Frequency bands; Mutual information; Optimization; Pattern recognition; Segments; Spatial filtering; Temporal logic; Brain-computer interface (BCI); Feature selection; Electroencephalogram (EEG); Bayesian classification; Mutual information
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2011.04.018

The common spatial pattern (CSP) algorithm is effective in decoding the spatial patterns of the corresponding neuronal activities from electroencephalogram (EEG) signal patterns in brain–computer interfaces (BCIs). However, its effectiveness depends on the subject-specific time segment relative to the visual cue and on the temporal frequency band that is often selected manually or heuristically. This paper presents a novel statistical method to automatically select the optimal subject-specific time segment and temporal frequency band based on the mutual information between the spatial–temporal patterns from the EEG signals and the corresponding neuronal activities. The proposed method comprises four progressive stages: multi-time segment and temporal frequency band-pass filtering, CSP spatial filtering, mutual information-based feature selection and naïve Bayesian classification. The proposed mutual information-based selection of optimal spatial–temporal patterns and its one-versus-rest multi-class extension were evaluated on single-trial EEG from the BCI Competition IV Datasets IIb and IIa respectively. The results showed that the proposed method yielded relatively better session-to-session classification results compared against the best submission. ► A statistical method to select optimal spatial–temporal patterns from EEG in BCIs. ► It comprises temporal–spatial filtering, feature selection and classification. ► The subject-specific features are selected based on mutual information. ► Session-to-session results are reported on BCI Competition IV Datasets IIa and IIb. ► It yielded better classification results compared against the best submission.