An Intelligent Computational Model to predict Eye Behaviour using EMD based Feature Extraction Technique

Abstract

Monitoring human health using electroencephalogram (EEG) signal has become prominent research in recent times. The proposed research work focuses on assessing the EEG signal by incorporating EMD (Empirical Mode Decomposition) technique and deep learning model to forecast the future state of eyes based on understanding the characteristics of interactivity (open eyes and closed eyes). The relevance of the study is that it demonstrates how we can assess human body wellness by observing the status of the eyes for an extended period of time. The proposed method provides numerous beneficial supports for enhancing the accuracy of the information retrieval system. In this research work, we first extract the features of EEG data by combining EMD and then build DNN (Deep Neural Network) model for testing the real data set. The proposed model gives remarkable result than existing model in terms of accuracy, precision, recall, sensitivity and specificity. The proposed approach produces an accuracy of 96%, precision of 97%, recall of 93%, sensitivity of 93% and specificity of 97%.