Hybrid Neuro-Fuzzy Learning Models for Classification of Motion Sickness Levels Using Biosignals

Abstract

Motion sickness is all around as long as there is existence of humans and motion. This sickness has been common in numerous people and due to which it has become the focus area of neurological, psychological and physiological researchers. Most common group of this motion sickness pertains to the category of visual sensitivity; also called visual dependence, wherein people become sick due to visual motion. In this research paper, classification of the levels of motion sickness is done by developing classifiers: (1) k-Nearest neighbour (kNN) classifier (2) Fuzzy c-means classifier (3) ELMAN neural classifier (4) Fuzzy-Wavelet neural network classifier. All the developed classifier models are based on variants of machine learning approaches and are designed to overcome the limitation of the conventional binary classification approach. In this work, electroencephalogram (EEG) data, centre of pressure and trajectories of head and waist motion data of 20 people were recorded and the developed classifier models were applied over them to attain the classification accuracy. Features of these multiple biosignals are denoised and extracted over which the classifier models were tested. The proposed technique is simulated in MATLAB simulation environment for the considered candidate data samples. Numerical simulation was carried out and the results prove the superiority and effectiveness of the developed classifiers over the various existing classifier models.