A Robust Machine Learning Model for Prediction: The Electroencephalography
Rohit Bajaj, Chahil Chaudhary, Himanshu Bhardwaj, Lokesh Pawar, Himanshu Gupta, Deepika Sharma
Abstract
A typical time series classification issue that has recently received a lot of attention is eye state identification. To classify the states of the eyes, electroencephalography (EEG), a method for detecting human cognition, is frequently employed. For the first time, a depth factorization machine model was used to evaluate an EEG signal, and the outcomes were based on user involvement characteristics. The objective of this study is to create a trustworthy machine learning model for determining EEG eye states. As there is the scope of improvement while using the traditional machine learning models so we propose a robust model that is more reliable as it works in all scenarios (best, worst, average). The performance of the proposed model is quite satisfiable.