Multi-view optimization of time-frequency common spatial patterns for brain-computer interfaces
| Autor: | Ren Xu, Jing Jin, Chang Liu, Yitao Huang, Andrzej Cichocki, Yangyang Miao |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Support Vector Machine
business.industry Computer science General Neuroscience Feature extraction Feature selection Pattern recognition Electroencephalography Signal Processing Computer-Assisted Filter (signal processing) Time–frequency analysis Motor imagery Brain-Computer Interfaces Imagination Artificial intelligence business Selection (genetic algorithm) Decoding methods Algorithms Brain–computer interface |
| Zdroj: | Journal of neuroscience methods. 365 |
| ISSN: | 1872-678X |
| Popis: | Background Common spatial pattern (CSP) is a prevalent method applied to feature extraction in motor imagery (MI)-based brain-computer interfaces (BCIs) recorded by electroencephalogram (EEG). The selection of time windows and frequency bands prominently affects the performance of CSP algorithms. Concerning the joint optimization of these two parameters, several studies have utilized a unified framework based on different feature selection strategies and achieved considerable improvement. However, during the feature selection process, useful information could be discarded inevitably and the underlying internal structure of features could be neglected. New method In this paper, we proposed a novel framework termed time window filter bank common spatial pattern with multi-view optimization (TWFBCSP-MVO) to further boost the decoding of MI tasks. Concretely, after extracting CSP features from different time-frequency decompositions of EEG signals, a preliminary screening strategy based on variance ratio was devised to filter out the unrelated spatial patterns. We then introduced a multi-view learning strategy for the simultaneous optimization of time windows and frequency bands. A support vector machine classifier was trained to determine the output of the brain. Results An experimental study was conducted on two public datasets to verify the effectiveness of TWFBCSP-MVO. Results showed that the proposed TWFBCSP-MVO could help improve the performance of MI classification. Comparison with existing methods In comparison to other competing methods, the proposed method performed significantly better ( p 0.01 ). Conclusions The proposed method is a promising contestant to improve the performance of practical MI-based BCIs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect