SCSP-3: A Spectrally Augmented Common Spatial Pattern Approach for Robust Motor Imagery-Based Brain-Computer Interface

• Published in: IEEE sensors journal Vol. 24; no. 5; pp. 6634 - 6642
• Main Authors: Khanna, Sunreet, Chowdhury, Anirban, Dutta, Ashish, Subramanian, Venkatesh K.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Band-pass filters; Brain > computer interface (BCI); Classification; common spatial pattern (CSP); electroencephalogram (EEG); Electroencephalography; Feature extraction; Human-computer interface; Imagery; motor imagery (MI); Performance evaluation; Rhythm; Robustness; Sensors; Stroke (medical condition); support vector machine (SVM); Support vector machines; Welch power-spectrum (PS)
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2024.3351880

Common spatial pattern (CSP) is a widely used method for feature extraction in motor imagery (MI)-based brain-computer interface (BCI) development. However, the performance of traditional CSP features often lacks robustness against intersession and intersubject variabilities present in MI-related electroencephalogram (EEG) signals. To address this limitation, we propose a novel approach to CSP-based feature extraction, combining spectral information obtained from Welch power-spectrum (PS) estimation with temporal variations which we named here as SCSP-3. Our SCSP-3 method employs independent learning paths for the temporal and spectral features extracted through CSP. We introduce a postprocessing step that crosses the classification probabilities from these pathways using element-wise products, deriving linearly separable features. The performance of SCSP-3 is evaluated and compared to the traditional CSP approach utilizing a support vector machine (SVM) for classification following a within-subject evaluation scheme. The results demonstrate a significant improvement in average accuracy for SCSP-3 with more generalizability, as it performs equally well with datasets from healthy subjects and stroke patients. This enhanced robustness and generalizability highlight the potential of SCSP-3 as a superior alternative to traditional CSP-based feature extraction methods for achieving consistent performance across different subject categories.