Feature selection using regularized neighbourhood component analysis to enhance the classification performance of motor imagery signals

• Published in: Computers in biology and medicine Vol. 107; pp. 118 - 126
• Main Authors: Malan, Nitesh Singh, Sharma, Shiru
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.04.2019; Elsevier Limited
• Subjects: Accuracy; Brain-computer interface; Classification; Cognitive tasks; Competition; Computational efficiency; Computational neuroscience; Computing time; Data processing; Datasets; EEG; Electroencephalography; Feature extraction; Genetic algorithm; Genetic algorithms; Genetic analysis; Human-computer interface; Image classification; Image enhancement; Mental task performance; Methods; Motor imagery; Motor task performance; Motors; Neighbourhood component analysis; Parameter modification; Principal component analysis; Principal components analysis; Regularization; Robotics; Signal analysis; Signal classification; Support vector machine; Support vector machines; Temporal resolution; Wavelet transforms; Brain-computer interface; Motor imagery; Support vector machine; Genetic algorithm; Neighbourhood component analysis; Principal component analysis
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.02.009

In motor imagery (MI) based brain–computer interface (BCI) signal analysis, mu and beta rhythms of electroencephalograms (EEGs) are widely investigated due to their high temporal resolution and capability to define the different movement-related mental tasks separately. However, due to the high dimensions and subject-specific behaviour of EEG features, there is a need for a suitable feature selection algorithm that can select the optimal features to give the best classification performance along with increased computational efficiency. The present study proposes a feature selection algorithm based on neighbourhood component analysis (NCA) with modification of the regularization parameter. In the experiment, time, frequency, and phase features of the EEG are extracted using a dual-tree complex wavelet transform (DTCWT). Afterwards, the proposed algorithm selects the most significant EEG features, and using these selected features, a support vector machine (SVM) classifier performs the classification of MI signals. The proposed algorithm has been validated experimentally on two public BCI datasets (BCI Competition II Dataset III and BCI Competition IV Dataset 2b). The classification performance of the algorithm is quantified by the average accuracy and kappa coefficient, whose values are 80.7% and 0.615 respectively. The performance of the proposed algorithm is compared with standard feature selection methods based on Genetic Algorithm (GA), Principal Component Analysis (PCA), and ReliefF and performs better than these methods. Further, the proposed algorithm selects the lowest number of features and results in increased computational efficiency, which makes it a promising feature selection tool for an MI-based BCI system. •RNCA at the feature selection stage enhances the classification performance of the Motor imagery task.•Computational time of the SVM classifier is significantly reduced using RNCA as feature selection approach.•Power spectral density of the EEG carries important information to distinguish between two classes of motor imagery.