An efficient EEG signal classification technique for Brain-Computer Interface using hybrid Deep Learning

Kishore Medhi

doi:10.1016/j.bspc.2022.104005

An efficient EEG signal classification technique for Brain-Computer Interface using hybrid Deep Learning

2022-09-01

14

PRE

AI

DOI：10.1016/j.bspc.2022.104005

Original

Original request for help

Save

Abstract

En 中文

Differently-abled individuals always need support from others for their day-to-day activities. Brain Computer Interface (BCI) has the potential to help those people in carrying out the basic activities. Artificial Intelligence (AI) and Internet of Things (IoT) ecosystem make the BCI technique more useful and efficient. Deep Learning (DL) algorithms can be used for proper identification of body activities from the brain signal. In this paper, we have developed a hybrid DL architecture for the efficient analysis of the EEG signal. To extract the important multi-domain features, we have efficiently selected and used the CNN filters in the proposed architecture. For further improvement of the system performance, the redundant features were removed using the feature reduction technique. In our experiment, we used real-time EEG datasets collected from the physionet biosignal database. The obtained results established that the proposed method outperformed the existing techniques in terms of accuracy, precision, recall, F1-score, and Matthew Correlation Coefficient. Finally, we developed an IoT-based BCI prototype and successfully conducted all the experiments to validate the scheme in a real-time environment.

Keywords:

Brain Computer Interaction

EEG

Deep learning

IoT

An efficient EEG signal classification technique for Brain-Computer Interface using hybrid Deep Learning

Abstract

Journal

Organization