A multi-functional BCI system for exigency assistance and environment control based on ML and IoT

Abstract

Brain-Computer Interface (BCI) is a modality to create an interface which sustains bidirectional communication between the brain and computers. Major disadvantages in implementing such systems are the bulky design and system cost. This study implements a simple multifunction BCI system for the environment control and exigency assistance by just using single channel Electroencephalogram (EEG). In the proposed model, the environment is controlled through Internet of Things (IoT) as per individual's cognitive state while for exigency assistance served as per Event Related Potential (ERP) observed during oddball paradigm. Arduino microcontroller (AMC) hardware is designed for controlling environment. Different Machine Learning (ML) algorithms observed for training the classifiers. Weighted k-Nearest Neighbour (Wk-NN) algorithm trained classifier delivers the best result, with accuracy of 98.3% to detect ERP and 95% accuracy for cognitive state detection. The simple, low cost prototype system was tested for environment control and assistance.