Efficient Classification of Horizontal And Vertical EOG Signals For Human Computer Interaction

Abstract Human-computer interaction (HCI) using Electrooculography (EOG) has been a growing area of research in recent years. The HCI provides communication channels between the human and the external device. Today, EOG is one of the most important biomedical signals for measuring and analyzing the direction of eye movements. The EOG is used to produce both activities in vertical and horizontal directions of human eye movements. In this paper, different human eye movement tasks from vertical and horizontal directions are studied. The dataset of EOG signals were obtained from Electroencephalography (EEG) electrodes from 27 healthy people, 14 males and 13 females. This process resulted from two dipole signals, the vertical-EOG signals and the horizontal-EOG signals. These signals were filtered by band-pass at 0.5–5Hz. A total of 54 datasets from these 27 healthy individuals, each lasting 30 seconds, were given. The Bo-Hjorth parameter was implemented for feature extraction on the preprocessed EOG signals. For classification, Decision Tree (DT), K-Nearest Neighbor (KNN), Ensemble Classifier (EC), Kernel Naive Bayes (KNB) and Support Vector Machine (SVM)) were utilized. The obtained results reveal that the best classifiers on horizontal and vertical signals are the Support Vector Machine (SVM), the Cosine KNN and the Ensemble Subspace Discriminant with having 100% percentage accuracies. Through designing the proposed algorithm for feature extraction, the highest performance of classification can be obtained for rehabilitation purposes and other applications that help the handicapped to take decisions for better life quality, by providing possible human interaction with a computer.