International Journal of Electrical and Computer Engineering (IJECE) Vol. 5, No. 1, February 2015, pp. 92~101 ISSN: 2088-8708  92 Journal homepage: http://iaesjournal.com/online/index.php/IJECE Left and Right Hand Movements EEG Signals Classification Using Wavelet Transform and Probabilistic Neural Network A.B.M. Aowlad Hossain, Md. Wasiur Rahman, Manjurul Ahsan Riheen Department of Electronics and Communication Engineering Khulna University of Engineering & Technology, Bangladesh Article Info ABSTRACT Article history: Received Oct 7, 2014 Revised Dec 11, 2014 Accepted Dec 26, 2014 Electroencephalogram (EEG) signals have great importance in the area of brain-computer interface (BCI) which has diverse applications ranging from medicine to entertainment. BCI acquires brain signals, extracts informative features and generates control signals from the knowledge of these features for functioning of external devices. The objective of this work is twofold. Firstly, to extract suitable features related to hand movements and secondly, to discriminate the left and right hand movements signals finding effective classifier. This work is a continuation of our previous study where beta band was found compatible for hand movement analysis. The discrete wavelet transform (DWT) has been used to separate beta band of the EEG signal in order to extract features. The performance of a probabilistic neural network (PNN) is investigated to find better classifier of left and right hand movements EEG signals and compared with classical back propagation based neural network. The obtained results shows that PNN (99.1%) has better classification rate than the BP (88.9%). The results of this study are expected to be helpful in brain computer interfacing for hand movements related bio- rehabilitation applications. Keyword: Artificial neural network Backpropagation algorithm Discrete wavelet transform Electroencephalogram Feature extraction Probabilistic neural network Copyright © 2015 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: A.B.M. Aowlad Hossain, Department of Electronics and Communication Engineering Khulna University of Engineering & Technology Khulna-9203, Bangladesh. Email: aowlad0403@ece.kuet.ac.bd 1. INTRODUCTION Over a million individuals are suffering from disability annually as a result of stroke, traumatic brain or spinal cord injuries [1]. A major portion of disable people have reported troubles with hand function [2], [3]. Failure of hand function causes severe problems in leading of life for the affected persons. Recent researches show that BCI is a new hope in treatmenting the disabilities. EEG signal is the most trendy resource of interpreting the brain activities in the realm of non-invasive BCI. They are well studied and there is evident that they can be used in artificial hand movements [4]. EEG is graphical representation of electrical activities of brain which is recorded using electrodes locating on the scalp. EEG have certain bands with separate frequency ranges [5]: theta waves varies in the range of 4 Hz to 7 Hz and its amplitude generally arround 20 μV, alpha wave varies with in the range of 8 to 13 Hz and about 30-50 μV amplitude. For beta wave, the frequencies vary between 13 Hz to 30 Hz and usually have a low voltage between 5-30 μV. Different bands carry information of different brain activities. EEG signals are extensively studied by numerous researches to classify different mental or brain activities [6]-[9]. Few studies have been proposed on hand movement classifications using support vector machine (SVM), linear discrimination analysis, adaptive Gaussian coefficients, C-SVM and combination of EEG and MEG. However, most of them are computationally complex and not so effective for real time applications [10]-[14]. In this context, selection of appropriate and compatible feature is very crucial for effective