Eye-Tracking Movements - A Comparative Study.

Eye tracking has been a topic of interest in research in recent years because it provides convenience to a wide range of applications. It is acknowledged as an important non-traditional method of human–computer interaction. Eye tracking is a useful tool for determining where and when people devote visual attention to a scene, and it helps to understand cognitive functioning. Nowadays, eye-tracking technology is making its way from the lab to the real world, collecting more data at a faster rate and with a greater variety of data kinds. Eye tracking will become closer to big data if the current trend continues. A real-time model is created using machine learning methodology, which tests a high-accuracy hypothesis. Eye tracking with parameters looks into a participant’s eye movements while presenting them with a variety of options. Using machine learning to analyze eye movements and extract attributes to assess eye behavior. K-nearest neighbor, Naive Bayes, decision trees, and random forests are machine learning algorithms that produce models with improved accuracy. In this paper, we have reviewed different eye-tracking technologies to obtain eye movement parameters and classifiers for categorization, such as machine learning and deep learning toward recognition of cognitive processes involved in learning.