Optimised multi‐wavelet domain for decomposed electrooculogram‐based eye movement classification

Abstract

The human eye movement tracking is possible with the assistance of the electrooculography (EOG) signals. The human eye tracking system allows researchers to analyse the participant's eye movements during certain activities. This study offers the EOG signals to control the human–computer interface systems with the help of Empirical Mean Curve Decomposition (EMCD) decomposition model. At first, the input EOG signal is provided as input to the EMCD decomposition model, later the resultant signal is given to principal component analysis for dimensional reduction, and then the dimensional reduced signal is offered to multi-wavelet decomposition model. The resultant dimensionally reduced multi-wavelet decomposed signal is passed to the proposed Feature Mapping (FM) model, using the k-means clustering model. Then, the Grey Wolf Optimization (GWO) algorithm is utilised to tune the margin. Next to mapping, the obtained features are provided to the nearest neighbour classifier, to obtain the eye movement. Next to the implementation, the proposed method is compared with the existing methods, and it is witnessed that the proposed methodology gives the superior performance in correspondence with accuracy, sensitivity, specificity, precision, false positive rate, false negative rate, negative predictive value, false discovery rate, F1 score and Mathews correlation coefficient.