An efficient feature extraction scheme for classification of mental tasks based on inter-channel correlation in wavelet domain utilizing EEG signal
Introduction
Classification of various mental tasks, such as geometrical figure rotation, mathematical multiplication, mental letter composing, visual counting, base-line resting plays an essential role to handle various applications of brain–computer interface. For the purpose of classification of these mental tasks, electroencephalogram (EEG) is one of the most promising tools, which is widely used now-a-days. Different methods are available in literature where distinctive features are extracted from EEG signals and then used for mental task classification. For example, in [1], [2], spectral power and asymmetry ratio based feature extraction scheme is proposed. These methods offer comparatively satisfactory classification performance but lacks consistency for all cases. In [3], a dictionary consisting of power spectral density and common spatial pattern algorithm is introduced to classify various mental tasks. Mental task classification approach based on autoregressive (AR) modelling is reported in [4], [5], [6], [7]. Among these methods, in [7], generalized Higuchi fractal dimension spectrum apart from AR parameters is used as feature. In [8], instead of AR parameters, reflection coefficients are used for feature extraction. In [9], discrete wavelet transform (DWT) and empirical mode decomposition (EMD) based feature extraction approach is proposed where feature selection method is utilized for better classification performance. Besides DWT and EMD, wavelet packet decomposition is investigated for the decomposition of EEG signal for motor-imagery (MI) based brain–computer interface (BCI) system in [10]. In [11], interaction dynamics of neuronal oscillations are analyzed using wavelet transforms and shown that wavelet based coherence features provide better performance in classifying neuronal oscillations. In [12], both conventional Fourier and wavelet coherence is applied to sensory-evoked electrical brain activity and relatively better performance is obtained when coherence was calculated using wavelet approach rather than classical Fourier approach. A parametric feature extraction and classification method introduced in [13] use fast Fourier transform to obtain features for BCI system. In [14], stockwell transform based feature extrraction method utilizing statistical parameter is introduced. Cross-correlation based approach of classifying MI tasks is presented in [15] where a subset of possible channel pairs are considered to obtain cross correlation sequence. In these channel pairs, one signal is chosen as fixed reference signal obtained from a particular channel of a particular MI task, as a result, the effect of obtaining cross correlation sequence from all possible combination of channel pairs is not considered. Moreover, reference signal selection is not universal for all sorts of mental and MI tasks and requires empirical selection of a channel signal from different types of tasks. Most of the reported feature extraction except [15] are performed on the data taken from various channels while the inter-channel relationship has not been utilized. It is considered that stimulation of a particular location of brain depends on the types of mental tasks performed. With a view to capturing the difference between both stimulated and non-stimulated EEG signals of brains obtained from various channels placed in the skull, measuring inter-channel relationship in some efficient spectro-temporal domains may play a significant role. Thus, development of a proficient method capable of detecting and classifying different types of mental tasks utilizing the inter-channel relationship is still undiscovered.
One of the objectives of this paper is to exploit the distinctive nature of inter-channel relationship to obtain effective features. Both multi-level wavelet decomposition and node reconstruction of EEG data are utilized to obtain the proposed inter-channel correlation features. Moreover, in the proposed method, unlike [15], reference signal selection based on empirical reasoning is not required and only the information obtained from the channels of the test frame is utilized to extract correlation features. Effect of using statistical features obtained from various wavelet approaches along with proposed inter-channel correlation features on classification performance is also investigated. SVM classifier is used to carry out classification process utilizing a publicly available EEG dataset on various mental tasks.
Section snippets
Data acquisition
In this paper, a widely used publicly available EEG dataset on various mental tasks collected by Keirn and Aunon are utilized [16]. EEG signals obtained from positions C3, C4, P3, P4, O1, and O2, defined by the 10–20 system of electrode placement, are used considering A1 and A2 as reference signal. Data are band pass filtered using an analog filter with band limit of 0.1–100 Hz. Finally the data are sampled at 250 Hz with 12 bit quantizer. The recording is carried out for 10 s during each
Proposed method
The proposed mental task classification scheme can be divided into four major steps: wavelet domain analyses, inter-channel relation, feature extraction and classification. These steps are described in detail in the following subsections.
Simulation results and discussion
In this section, classification performance of various feature extraction methods is investigated considering proposed four methods and some methods available in literature. Effect of using inter-channel correlation feature on classification accuracy is investigated in detail. A comparative analysis on feature dimension and computation time is also performed among various feature extraction methods. In the proposed method, instead of directly using channel data, corresponding wavelet signals
Conclusion
In this paper, an efficient feature extraction scheme based on wavelet domain inter-channel correlation is proposed. Consistent classification performance is obtained irrespective of mental tasks and irrespective of subjects in comparison to some of the existing methods. It is to be noted that use of correlation feature drastically improves classification accuracy in all cases, namely WD, WPD, WNR and WPNR. Although feature dimension increases due to use of inter-channel correlation feature
Credit author statement
Md. Mostafizur Rahman: Conceptualization, Methodology, Software, Data curation, Writing – Original draft preparation, Visualization, Investigation, Validation.
Shaikh Anowarul Fattah: Conceptualization, Writing – Reviewing and Editing, Supervision.
References (19)
- et al.
Classification of neural signals from sparse autoregressive features
Neurocomputing
(2013) - et al.
Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system
Biomed. Signal Process. Control
(2017) - et al.
Interaction dynamics of neuronal oscillations analysed using wavelet transforms
J. Neurosci. Methods
(2007) - et al.
Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform
Appl. Math. Comput.
(2007) - et al.
Best basis-based wavelet packet entropy feature extraction and hierarchical EEG classification for epileptic detection
Expert Syst. Appl.
(2011) Utilizing gamma band to improve mental task based brain-computer interface design
IEEE Trans. Neural Syst. Rehabil. Eng.
(2006)- et al.
Improving mental task classification by adding high frequency band information
J. Med. Syst.
(2010) - et al.
EEG signal classification based on sparse representation in brain computer interface applications
2015 22nd Iranian Conference on Biomedical Engineering (ICBME)
(2015) - et al.
Classification of mental tasks from EEG signals using extreme learning machine
Int. J. Neural Syst.
(2006)
Cited by (8)
A novel feature extraction method using chemosensory EEG for Parkinson's disease classification
2023, Biomedical Signal Processing and ControlCitation Excerpt :Recently, several methods for extracting features from EEG recordings and classifying them using machine learning algorithms have been proposed. Various researchers have examined specifically feature extraction and machine learning methods that have been applied to EEG analysis [5–9]. For instance, the conventional feature extraction methods like Fast Fourier Transform (FFT) and auto-regressive (AR) method have been reviewed and compared [10].
A Novel Methodology to study the Cognitive Load Induced EEG Complexity Changes: Chaos, Fractal and Entropy based approach
2021, Biomedical Signal Processing and ControlCitation Excerpt :Here, H0 = μ = μ1…N; HA = μ ≠ μ1…N. This study employed and evaluated the Support Vector Machine, Random Forest and Decision Tree classification model based on supervised learning with nonlinear features [59] This study further includes systematic comparison of the performance of classification model over the defined feature space based on confusion matrix and accuracy score [60]. One feature vector X1 is the frequency band beta, alpha, theta and delta set as categorical variables.
Mental Health Monitoring Using Deep Learning Technique for Early-Stage Depression Detection
2023, SN Computer ScienceState-of-the-art mental tasks classification based on electroencephalograms: a review
2023, Physiological MeasurementA practical low-dimensional feature vector generation method based on wavelet transform for psychophysiological signals
2023, Turkish Journal of Electrical Engineering and Computer SciencesDeep Learning Models in EEG Signals: Comparative Analysis
2023, Lecture Notes in Networks and Systems