Classification of EEG Signals Using a Multiple Kernel Learning Support Vector Machine

• Published in: Sensors (Basel, Switzerland) Vol. 14; no. 7; pp. 12784 - 12802
• Main Authors: Li, Xiaoou, Chen, Xun, Yan, Yuning, Wei, Wenshi, Wang, Z.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 17.07.2014; MDPI
• Subjects: Adult; Algorithms; Brain - physiology; brain computer interface; Brain-Computer Interfaces; Case-Control Studies; Causality; Classification; Cognition - physiology; Cognitive ability; Discriminant analysis; Electroencephalography; Electroencephalography - instrumentation; Female; Human-computer interface; Humans; Kernels; Learning; Male; mental task; Middle Aged; multiple kernel learning; polynomial kernel; radial basis function kernel; Sensors; Signal processing; Signal Processing, Computer-Assisted - instrumentation; Software; Stroke; stroke patients; Support Vector Machine; Support vector machines; Tasks; Young Adult; China
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s140712784

In this study, a multiple kernel learning support vector machine algorithm is proposed for the identification of EEG signals including mental and cognitive tasks, which is a key component in EEG-based brain computer interface (BCI) systems. The presented BCI approach included three stages: (1) a pre-processing step was performed to improve the general signal quality of the EEG; (2) the features were chosen, including wavelet packet entropy and Granger causality, respectively; (3) a multiple kernel learning support vector machine (MKL-SVM) based on a gradient descent optimization algorithm was investigated to classify EEG signals, in which the kernel was defined as a linear combination of polynomial kernels and radial basis function kernels. Experimental results showed that the proposed method provided better classification performance compared with the SVM based on a single kernel. For mental tasks, the average accuracies for 2-class, 3-class, 4-class, and 5-class classifications were 99.20%, 81.25%, 76.76%, and 75.25% respectively. Comparing stroke patients with healthy controls using the proposed algorithm, we achieved the average classification accuracies of 89.24% and 80.33% for 0-back and 1-back tasks respectively. Our results indicate that the proposed approach is promising for implementing human-computer interaction (HCI), especially for mental task classification and identifying suitable brain impairment candidates.