Classification of extension and flexion positions of thumb, index and middle fingers using EEG Signal

Abstract

The primary aim of the piece of work is to classify the extension and flexion positions of thumb, index finger and middle finger by the use of EEG Signal. The EEG Signal of a human subject is recorded and used for offline training of a feedforward neural network which is used to learn the relation between EEG and finger motion. Six features have been extracted per sample of EEG signal over 10 channels, that is, signal from 10 different regions of the brain. Analysis of the data from these 10 channels revealed a certain few important channels which have been then selected for feature extraction and training of neural network. Observations show that flexion and extension positions of these three fingers are classified successfully. This idea can be developed further to combine these classified positions to perform tasks such as object translation and rotation using a finger exoskeleton.