Motor Imagery EEG Spectral-Spatial Feature Optimization Using Dual-Tree Complex Wavelet and Neighbourhood Component Analysis

• Published in: Ingénierie et recherche biomédicale 2022-06, Vol.43 (3), p.198-209
• Main Authors: Malan, N.S., Sharma, S.
• Format: Article
• Language: English
• Subjects: Brain-computer interface; Dual-tree complex wavelet transform; Electroencephalogram; Motor imagery; Neighbourhood component analysis
• ISSN: 1959-0318
• DOI: 10.1016/j.irbm.2021.01.002

•A novel spectral-spatial motor imagery features optimization algorithm.•Proposed method enhances classification performance.•The DTCWT based filter provides efficient band power compared to IIR filters.•Obtained classification accuracy of 84.02 ± 12.2 and 89.1 ± 7.50, for two BCI datasets. Frequency band optimization improves the performance of common spatial pattern (CSP) in motor imagery (MI) tasks classification because MI-related electroencephalograms (EEGs) are highly frequency specific. Many variants of CSP algorithm divided the EEG into various sub bands and then applied CSP. However, the feature dimension of MI-EEG data increases with addition of frequency sub bands and requires efficient feature selection algorithms. The performance of CSP also depends on filtering techniques. In this study, we designed a dual tree complex wavelet transform based filter bank to filter the EEG into sub bands, instead of traditional filtering methods, which improved the spatial feature extraction efficiency. Further, after filtering EEG into different sub bands, we extracted spatial features from each sub band using CSP and optimized them by a proposed supervised learning framework based on neighbourhood component analysis (NCA). Subsequently, a support vector machine (SVM) is trained to perform classification. An experimental study, conducted on two datasets (BCI Competition IV (Dataset 2b), and BCI competition III (Dataset IIIa)), validated the MI classification effectiveness of the proposed method in comparison with standard algorithms such as CSP, Filter bank CSP (CSP), and Discriminative FBCSP (DFBCSP). The average classification accuracy obtained by the proposed method for BCI Competition IV (Dataset 2b), and BCI Competition III (Dataset IIIa) are 84.02 ± 12.2 and 89.1 ± 7.50, respectively and found significant than that achieved by standard methods. Achieved superior results suggest that the proposed algorithm can improve the performance of MI-based Brain-computer interface devices.