Online classification of imagined hand movement using a consumer grade EEG device

Abstract

Brain-Computer Interaction (BCI) is a technology developed with the purpose of building a pathway between the brain and computer which is independent of neuromuscular functions. Potential applications in rehabilitation of patients with motor disabilities and video gaming make BCI an important field of research. A task like controlling a prosthetic limb using BCI is challenging. Performing this with readily available consumer grade EEG devices complicates the matters further due to lower accuracies. This paper presents the work related to an online classifier for imagined hand movement implemented using Emotiv Epoc for EEG data capturing. The system attempts to discriminate between left and right hand movement imagination by analysing the recordings of two electrodes placed over the motor-cortex. Auto-Regression (AR) based signal processing techniques are employed to derive features that enable classification. Especially, a cumulative score based method is used for identification of user specific frequencies. The system is evaluated in an experiment involving 8 subjects where an average accuracy of 70.375% is achieved