A novel method for recognizing eye movements using NN classifier

Recent researches are made in Electrooculography (EOG) signal to control the Human-Computer Interface (HCI) system by classifying the signal. Since then, the investigations were extended to understand the characteristics of EOG. This paper proposes a novel model for recognizing the eye movements using EOG signals. Furthermore, we have proposed a statistical procedure for the dimensionality reduction of the EOG signal. In addition, we have depicted Neural Network (NN) classifier for classifying the EOG signal. The proposed methodology is compared to the existing method and it is observed that the proposed methodology gives the better performance in terms of Accuracy, Specificity, Precision, False Negative Rate (FNR), False Positive Rate (FPR), Sensitivity, Negative Predictive Value (NPV), False Discovery Rate (FDR), Mathews Correlation Coefficient (MCC) and F1_Score.