Using Deep Learning for Human Computer Interface via Electroencephalography

Abstract

In this paper, several techniques used to perform EEG signal pre-processing, feature extraction and signal classification have been discussed, implemented, validated and verified; efficient supervised and unsupervised machine learning models, for the EEG motor imagery classification are identified. Brain Computer Interfaces are becoming the next generation controllers not only in the medical devices for disabled individuals but also in the gaming and entertainment industries. In order to build an effective Brain Computer Interface, it is important to have robust signal processing and machine learning modules which operate on the EEG signals and estimate the current thought or intent of the user. Motor Imagery (imaginary hand and leg movements) signals are acquired using the Emotiv EEG headset. The signal have been extracted and supplied to the machine learning (ML) stage, wherein, several ML techniques are applied and validated. The performances of various ML techniques are compared and some important observations are reported. Further, Deep Learning techniques like autoencoding have been used to perform unsupervised feature learning. The reliability of the features is presented and analyzed by performing classification by using the ML techniques. It is shown that hand engineered ‘ad-hoc’ feature extraction techniques are less reliable than the automated (‘Deep Learning’) feature learning techniques. All the findings in this research, can be used by the BCI research community for building motor imagery based BCI applications such as Gaming, Robot control and autonomous vehicles.