An efficient scheme for mental task classification utilizing reflection coefficients obtained from autocorrelation function of EEG signal

Abstract

Classification of different mental tasks using electroencephalogram (EEG) signal plays an imperative part in various brain-computer interface (BCI) applications. In the design of BCI systems, features extracted from lower frequency bands of scalp-recorded EEG signals are generally considered to classify mental tasks and higher frequency bands are mostly ignored as noise. However, in this paper, it is demonstrated that high frequency components of EEG signal can provide accommodating data for enhancing the classification performance of the mental task-based BCI. Instead of using autoregressive (AR) parameters considering AR modeling of EEG data, reflection coefficients obtained from EEG signal are proposed as potential features. From a given frame of EEG data, reflection coefficients are directly extracted by using the autocorrelation values in a recursive fashion, which avoids matrix inversion and computation of AR parameters. Use of reflection coefficients not only provides an effective feature vector for EEG signal classification but also offers very low computational burden. Support vector machine classifier is deployed in leave-one-out cross-validation manner to carry out classification process. Extensive simulation is done on an openly accessible dataset containing five different mental tasks. It is found that the proposed scheme can classify mental tasks with a very high level of accuracy as well as low time complexity in contrast with some of the existing strategies.

Keywords: Autocorrelation function; Autoregressive (AR) model; Brain–computer interface (BCI); Electroencephalogram (EEG); Reflection coefficient.

Fig. 1

Average magnitude spectrum corresponding to a session of mathematical multiplication task obtained from C3 channel of subject 1. The dotted line on both sides of the average spectrum indicates the standard deviation. (Color figure online)

Fig. 2

Statistical information of reflection coefficients of different channels obtained from subject 1 considering mathematical multiplication and visual counting task. a–d correspond to statistical information of 1st, 2nd 3rd and 4th reflection coefficients, respectively

Fig. 3

Effect of channel selection on classification accuracy for all four subjects in case of MC pair of tasks

Fig. 4

Effect of PCA on classification accuracy for all four subjects in case of MC pair of tasks

Fig. 5

Effect of reflection coefficients variation on classification accuracy for all four subjects in case of MC pair of tasks

Fig. 6

Effect of frequency band selection on classification accuracy for all four subjects in case of MC pair of tasks. (Color figure online)

Fig. 7

Classification accuracy obtained from four subjects considering different kernels in SVM classifier. a–d correspond to classification accuracy obtained from 1st, 2nd, 3rd and 4th subject considering different kernels respectively. (Color figure online)