Abstract
Feature extraction is an important step in the process of electroencephalogram (EEG) signal classification. The authors propose a “pattern recognition” approach that discriminates EEG signals recorded during different cognitive conditions. Wavelet based feature extraction such as, multi-resolution decompositions into detailed and approximate coefficients as well as relative wavelet energy were computed. Extracted relative wavelet energy features were normalized to zero mean and unit variance and then optimized using Fisher's discriminant ratio (FDR) and principal component analysis (PCA). A high density EEG dataset validated the proposed method (128-channels) by identifying two classifications: (1) EEG signals recorded during complex cognitive tasks using Raven's Advance Progressive Metric (RAPM) test; (2) EEG signals recorded during a baseline task (eyes open). Classifiers such as, K-nearest neighbors (KNN), Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Naïve Bayes (NB) were then employed. Outcomes yielded 99.11% accuracy via SVM classifier for coefficient approximations (A5) of low frequencies ranging from 0 to 3.90 Hz. Accuracy rates for detailed coefficients were 98.57 and 98.39% for SVM and KNN, respectively; and for detailed coefficients (D5) deriving from the sub-band range (3.90–7.81 Hz). Accuracy rates for MLP and NB classifiers were comparable at 97.11–89.63% and 91.60–81.07% for A5 and D5 coefficients, respectively. In addition, the proposed approach was also applied on public dataset for classification of two cognitive tasks and achieved comparable classification results, i.e., 93.33% accuracy with KNN. The proposed scheme yielded significantly higher classification performances using machine learning classifiers compared to extant quantitative feature extraction. These results suggest the proposed feature extraction method reliably classifies EEG signals recorded during cognitive tasks with a higher degree of accuracy.
Highlights
Clinicians use the electroencephalogram (EEG) as a standard neuroimaging tool for the study of neuronal dynamics within the human brain
0.96 0.96 0.89 0.79 achieved 93.33 and 92.50% accuracies for D5 details coefficients, respectively, as shown in Tables 6, 7. These results indicate that the proposed approach is strong enough to perform on public dataset for classification of cognitive tasks
The authors reported the results of previous studies for comparison of only two cognitive tasks, i.e., mental multiplication and mental letter composing, for example 81.5% classification accuracy reported by Keirn and Aunon (1990) for classification of mental multiplication from mental letter composing
Summary
Clinicians use the electroencephalogram (EEG) as a standard neuroimaging tool for the study of neuronal dynamics within the human brain. Data extracted from EEG results reflect the process of an individual’s information processing (Grabner et al, 2006). Recent technological advances have increased the scope of EEG recording abilities by using dense groups of electrodes including arrays of 128, 256, and 512 electrodes attached to the cranium. EEG Signals Analysis massive data sets is cumbersome (Übeyli, 2009) for existing EEGbased analysis techniques. Optimized feature extraction of relevant EEG data is essential to improve the quality of cognitive performance evaluations, especially since it directly impacts a classifier’s performance (Iscan et al, 2011). More expressive features enhance classification performance; feature extraction has become the most critically significant step in EEG data classification
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call