A motor-imagery channel-selection method based on SVM-CCA-CS

Abstract

In electroencephalography, multi-channel electroencephalogram (EEG) signals are usually utilized to improve classification accuracy. However, a large set of EEG channels increases the computational complexity, reduces the real-time performance and causes wearability difficulties. Channel selection methods have been widely investigated to reduce the number of channels with an acceptable loss of accuracy for EEG-based motor-imagery recognition. In this paper, we present a novel algorithm, called Support Vector Machine-Canonical Correlation Analysis-Channel Selection (SVM-CCA-CS). First, the energy features of the wavelet packet subnodes of the motor-imagery EEG signals are extracted. Then the weights of feature groups are calculated as initial channel weights, based on the CCA algorithm. The initial channel weights are further adjusted, according to the contribution of each channel to the classification accuracy via SVM, and the top channels with larger weights are eventually selected. The results show that the average accuracy of all subjects can reach 80.03% by using the first 30 channels with the largest weights from among the total of 118 channels. For the right hand and foot motor-imagery tasks, the generally applicable optimal channels are mostly located in the left hemisphere. Our generally applicable channel observation of the whole brain cortex suggests contralateral control correspondence: for unilateral motor imagery, the optimal channels are concentrated in the contralateral hemisphere. This is consistent with the contralateral control of the body by the human brain: the majority of the human motor and sensory fibers tend to control the contralateral limbs and pass through the midline of the body. Our proposed method provides optimal acquisition and analysis of the positions of EEG signals in specific motor-imagery tasks.

EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives

“…The association of multivariate functional groups with target classes can be evaluated by CCA [ 42 ]. The CCA focuses on the different MI-based tasks and distinguishes between different movements.…”

“…Only the specified channels, decreased number of channels, configuration complexity, and computational costs will be necessary for future sessions or applications. Wang et al [ 42 ] submitted an SVM-CCA-CS algorithm and examined the optimum CS on the motor screen for multi-channel EEG signals. The initial extraction of the Wavelet Packet Coefficients and features, the weights of each feature group were determined, and CCA-CS predicted the starting weight of each channel.…”

A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces

“…The spatial distribution and frequencyband's energy are two essential aspects to characterize MI-EEG [11]. Around the design of the spatial filter, a large amount of works have been produced to decode the MI-EEG signals [12]- [14].…”

“…Through the analyses of previous works, we found two significant shortcomings in these works. First, in the CSP framework, many works only focused on 8-30 Hz broadband information but ignoblack narrowband information [12]- [14]. Second, even though some subsequent researches focused on narrowband information based on the filter bank strategy, some potentially useful information was lost due to their crude feature selection [22], [26]- [28].…”

Early intelligent fault diagnosis of rotating machinery based on IWOA-VMD and DMKELM

“…The essence of intelligent fault diagnosis is pattern recognition. Traditional pattern recognition algorithms mainly contains support vector machine (SVM) and backpropagation (BP) networks [23][24]. However, SVM and BP belong to apartment structures, which have weak nonlinear expression between fault characteristics and patterns, and have limited ability to process large amounts of data.…”