A Comparative Study of EEG Signal Based Eye State Detection Using Deep Learning

Eye state detection refers to the technology and techniques used to determine the state or condition of a person's eyes, such as whether they are open or closed, focused or unfocused, or exhibiting specific eye movements. Many disciplines, including medicine, neurology, and human-computer interaction, depend on the accurate and reliable detection of eye open and eye close states. Findings indicating eye-state behavior, such as blinking frequency, may indicate stress reaction have recently sparked interest in determining eye-state using EEG signals. In this study the performance of three deep learning-based algorithms (Gated Recurrent Unit, Long Short-Term Memory and Recurrent Neural Network) for eye state detection have been investigated. Principal Component Analysis has been used for dimensionality reduction. Finally, results are compared on EEG data collected from UCI machine-learning repository.