Research Article
Mental Task Classification Scheme Utilizing
Correlation Coefficient Extracted from Interchannel
Intrinsic Mode Function
Md. Mostafizur Rahman and Shaikh Anowarul Fattah
Bangladesh University of Engineering and Technology (BUET), Dhaka 1000, Bangladesh
Correspondence should be addressed to Shaikh Anowarul Fattah; fattah@eee.buet.ac.bd
Received 8 June 2017; Accepted 10 September 2017; Published 10 December 2017
Academic Editor: Yudong Cai
Copyright © 2017 Md. Mostafzur Rahman and Shaikh Anowarul Fattah. Tis is an open access article distributed under the
Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided
the original work is properly cited.
In view of recent increase of brain computer interface (BCI) based applications, the importance of efcient classifcation of various
mental tasks has increased prodigiously nowadays. In order to obtain efective classifcation, efcient feature extraction scheme is
necessary, for which, in the proposed method, the interchannel relationship among electroencephalogram (EEG) data is utilized.
It is expected that the correlation obtained from diferent combination of channels will be diferent for diferent mental tasks,
which can be exploited to extract distinctive feature. Te empirical mode decomposition (EMD) technique is employed on a test
EEG signal obtained from a channel, which provides a number of intrinsic mode functions (IMFs), and correlation coefcient is
extracted from interchannel IMF data. Simultaneously, diferent statistical features are also obtained from each IMF. Finally, the
feature matrix is formed utilizing interchannel correlation features and intrachannel statistical features of the selected IMFs of EEG
signal. Diferent kernels of the support vector machine (SVM) classifer are used to carry out the classifcation task. An EEG dataset
containing ten diferent combinations of fve diferent mental tasks is utilized to demonstrate the classifcation performance and a
very high level of accuracy is achieved by the proposed scheme compared to existing methods.
1. Introduction
Electroencephalogram (EEG) signal is used extensively
nowadays by the researchers to handle diferent applications
of brain-computer interface (BCI). EEG-based BCI systems
employ electrical activity of brain to classify diferent EEG
signals corresponding to various mental tasks precisely.
One way to classify the signals efectively is to acquire
discriminative features from that signal. As a matter of
fact, diferent schemes to extract distinctive features are
available in literature. For example, in [1], spectral power and
asymmetry ratio based feature extraction scheme is proposed
where an additional band (24–37 Hz) is used along with con-
ventional lower spectral bands for mental task classifcation.
Tis method ofers comparatively satisfactory classifcation
performance but lacks consistency for all cases. In [2], similar
feature extraction scheme used in [1] is proposed; however,
the diference is that it utilizes an additional high frequency
band (40–100 Hz) to obtain those features. In [3], a dictionary
consisting of power spectral density and common spatial pat-
tern (CSP) algorithm is introduced to classify various mental
tasks. Autoregressive (AR) model based feature extraction
scheme is reported in [4] where sixth-order AR system is
considered to extract feature. Moreover, in [5], multivariate
AR models are taken into consideration and four diferent
representations of AR coefcients are tested to classify mental
task. In [6], feature extraction scheme based on sparse
autoregressive model is investigated, which involves complex
computation to exclude autoregressive coefcients that are
useless in the prediction stage. In [7], a feature extraction
method based on generalized Higuchi fractal dimension
spectrum along with AR parameters is proposed. Wavelet
transform and empirical mode decomposition (EMD) based
classifcation methods are proposed in [8], where feature
selection method is utilized for better classifcation per-
formance. In [9], Stockwell transform based algorithm is
Hindawi
BioMed Research International
Volume 2017, Article ID 3720589, 11 pages
https://doi.org/10.1155/2017/3720589