Open AccessMulticlass classification of motor imagery EEG signals using ensemble classifiers & cross-correlation
Author(s) -
D. Hari Krishna,
I. A. Pasha,
T. Satya Savithri
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i2.6.10144
Subject(s) - pattern recognition (psychology) , artificial intelligence , support vector machine , motor imagery , naive bayes classifier , similarity (geometry) , computer science , linear discriminant analysis , electroencephalography , brain–computer interface , binary classification , random subspace method , correlation , signal (programming language) , random forest , speech recognition , mathematics , psychology , geometry , psychiatry , image (mathematics) , programming language
To communicate without any muscle movement and purely based on brain signal has been the goal of Brain computer interfacing (BCI). Recent BCI based studies reported more and more accurate detection of brain states. This paper proposes a study that detects EEG signal belonging todifferent imaginary motor activities (Right leg, right hand, left leg and left hand). The Electroencephalogram (EEG) signal has been conditioned by band pass filter (BPF) to improve signal to noise ratio (SNR). The proposed method is based on similarity between signals to extract features. For measuring the similarity between signals, Cross correlation (CC) is used. An ensemble set of five classifiers (Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes (NB) and Binary Decision Tree) was used collectively. As the similarity measurement was binary in nature, one versus rest (OVR) approach was used for multi class classification. Random subset of features was used to train the ensemble of classifiers. The classification label was obtained by using majority voting. An average accuracy of 89.57% was observed among all 10 subjects.