• Shubhangi Gupta
• Jaipreet Kaur Bhatti

Brain Computer Interface establishes an artificial communication channel between human brain and external world. It enables the patient of complete body paralysis to control assistive applications such as movements of robotic arm or a wheel chair by using the power of human thoughts embedded in Electroencephalogram signals. In present work, a methodology is proposed for pre-processing, feature extraction and classification of Electroencephalogram signals for implementation of Brain Computer Interface. Motor Imagery signals for different mental activities are recorded and filtered out for noise reduction and artifact cancellation in the first step. In the second step, useful features are calculated from processed Electroencephalogram signals to prepare the feature vector. This feature vector is given as an input to the Artificial Neural Network classifier for training purposes in the third step. Appropriately trained classifier algorithm can further be used for translating Electroencephalogram signals to meaningful commands in real time.

Brain Computer Interface (BCI), Electroencephalogram (EEG), Support Vector Machine (SVM), Classification

"Pre-processing, Feature Extraction and Classification of EEG signals for Brain Computer Interface ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.4, Issue 5, page no.161-166, May-2017, Available :http://www.jetir.org/papers/JETIR1705036.pdf

"Pre-processing, Feature Extraction and Classification of EEG signals for Brain Computer Interface ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.4, Issue 5, page no. pp161-166, May-2017, Available at : http://www.jetir.org/papers/JETIR1705036.pdf