International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 International Conference on Industrial Automation and Computing (ICIAC- 12-13 th April 2014) Jhulelal Institute Of Technology ,Lonara,Nagpur 54 | Page EEG Feature Extraction Using Wavelet Techniques For Brain Computer Interface Kirti A. Joshi, Dr. Narendra Bawane Electronics Department, RTMNU University Nagpur, India kir_aj@yahoo.com S.B. Jain Institute of Technology, Management and Research. Kalmeshwar Road, Nagpur, India narendra.bawane@yahoo.com ABSTRACT: The aim of this study was to compare methods for feature extraction and classification of EEG signals for a brain–computer interface (BCI) according to different mental task conditions. EEG data was obtained either from BCI data base or from EEG experimental recording. There were different methods for feature Extraction like temporal methods, frequential methods, and Time-frequency representations. Among these methods wavelet which was type of Time frequency representation method most popularly used for feature extraction. Keywords:- Signal amplitude, Autoregressive parameters, Power spectral density, Short-time Fourier transform, Wavelets, I. INTRODUCTION Brain–computer interface (BCI) provides a direct communication channel between a subject‘s brain and a computer by using electroencephalogram (EEG) signals. The EEG signals are brain signals which will give the information regarding different mental task conditions such as movement imagination, geometric figure rotation, Arithmetic Tasks, relax etc. These are given below. 1.1 Movement Imagination:- The subject was asked to plan movement of the right hand, movement of legs forward- backward etc 1.2 Geometric Figure Rotation:- The subject was given 30 seconds to see a complex three dimensional object, after which the object was removed. The subject was instructed to visualize the object being rotated about an axis. 1.3 Arithmetic Task:- The subject was asked to perform trivial and nontrivial multiplication. An example of a trivial calculation is to multiply 2 by 3 and nontrivial task is to multiply 49 by 78. The subject was instructed not to vocalize or make movements while solving the problem. 1.4 Relaxed: - The subject was asked to relax with eyes closed. No mental or physical task to be performed at this stage. II. EEG SIGNAL Electroencephalogram is defined as electrical signal of an alternating type recorded from the scalp surface carried by metal electrodes and conducting media. EEG signal generally recorded by 10-20 electrode placement system. This is done by using the electrodes. Many BCIs use a special electrode cap, in which whole for electrodes are already in the right places, according to the international 10-20 system. It saves time because the electrodes do not have to be attached one by one. Typically, less than 10 electrodes are used in online BCIs with sampling rates of 100-400 Hz. Figure 1: Electrode Placement System III. DATA PROCESSING 3.1 Temporal methods RESEARCH ARTICLE OPEN