Title: Gustatory stimulus-based electroencephalogram signal classification

Authors: Kalyana Sundaram Chandran; Marichamy Perumalsamy

Addresses: Mepco Schlenk Engineering College, Sivakasi, Tamil Nadu, India ' P.S.R Engineering College, Sivakasi, Tamil Nadu, India

Abstract: Brain computer interface (BCI) gives a prompt correspondence between human brain and personal computer (PC) and makes an interpretation for controlling the outside gadgets. Taste composition (TASCO)-based EEG signal classification is used to differentiate normogeusia and hypogeusia. EEG signal of TASCO is pre-processed by utilising FIR band pass channel to mitigate the artefacts of noise. In this proposed work, the discrete wavelet transform (DWT) is used as the feature extraction method. DWT breaks down the separated EEG signal into its related frequency bands and the measurable features of the detailed coefficient of the alpha wave are analysed in time domain. The extracted features like mean absolute value (MAV) and variance are classified using a multilayer perceptron neural network classifier which provides high accuracy. In this paper, sour TASCO is analysed to identify the gall bladder problem in a human and improve the accuracy of the system as much as 95% compared to conventional methods.

Keywords: brain computer interface; BCI; discrete wavelet transform; DWT; electroencephalography; EEG; FIR band pass filter; gustatory stimuli; multilayer perceptron; MLP; taste composition; taste disorders; neural network.

DOI: 10.1504/IJBET.2021.119930

International Journal of Biomedical Engineering and Technology, 2021 Vol.37 No.3, pp.308 - 322

Received: 22 Jun 2018
Accepted: 26 Oct 2018
Published online: 04 Jan 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article