Four-Class Motor Imagery EEG Signal Classification using PCA, Wavelet and Two-Stage Neural Network

Md Asadur Rahman,Md Kazem,Farzana Khanam,Mohammad Khurshed,Mohiuddin Ahmad

doi:10.14569/ijacsa.2019.0100562

Md Asadur Rahman, Md Kazem + Show 3 more

Open Access

https://doi.org/10.14569/ijacsa.2019.0100562

Copy DOI

Abstract

Electroencephalogram (EEG) is the most significant signal for brain-computer interfaces (BCI). Nowadays, motor imagery (MI) movement based BCI is highly accepted method for. This paper proposes a novel method based on the combined utilization of principal component analysis (PCA), wavelet packet transformation (WPT), and two-stage machine learning algorithm to classify four-class MI EEG signal. This work includes four-class MI events by an imaginary lifting of the left hand, right hand, left foot, and Right Foot. The main challenge of this work is to discriminate the similar lobe EEG signal pattern such as left foot VS left hand. Another critical problem is to identify the MI movements of two different feet because their activation level is very low and show an almost similar pattern. This work firstly uses the PCA to reduce the signal dimensions of the left and right lobe of the brain. Then, WPT is used to extract the feature from the different class EEG signal. Finally, the artificial neural network is trained into two stages – 1st stage identifies the lobe from the signal pattern and the 2nd stage identifies whether the signal is of MI hand or MI foot movement. The proposed method is applied to the 4-class MI movement related EEG signals of 15 participants and found excellent classification accuracy (>74% on average). The outcomes of the proposed method prove its effectiveness in practical BCI implementation.

Highlights

Brain-computer interface (BCI) creates a communication system between computer and brain functionality to control the other devices
We have proposed a novel method for the aforementioned multiple class EEG signal classification utilizing a principal component analysis (PCA), wavelet packet transformation (WPT), and two-stage artificial neural network (ANN)
The proposed method was applied on the testing data set and we found that the proposed algorithm can improve classification performance than the WPT-single ANN model

Summary

Introduction

Brain-computer interface (BCI) creates a communication system between computer and brain functionality to control the other devices. BCI can be used to control devices like a wheelchair, room light, fan, etc. There are many modalities such as Electrocorticogram, Electroencephalogram (EEG), Functional near-infrared Spectroscopy, Magneto-encephalogram, Functional Magnetic Resonance Imaging, etc. Among these modalities, EEG is the most familiar and cheapest technique to record brain signal [1]. EEG is a non-invasive way to record neuro-electric signal which is often called an EEG signal. Since a number of brain stimuli have been proposed for implementing the BCI system. MI has a special benefit because it needs no additional setup like visual stimuli [3]

Methods

Results

Conclusion