Enhanced Drowsiness Prediction through EEG Signal Analysis using Hybrid Machine Learning Model
Neelesh Gupta, Pushpalata Verma, Richa Verma, Tikeshwar Gajpal, Jaideep Patel, Rovin Tiwari
Abstract
The reason for this examination is to give a clever strategy to foreseeing sluggishness by utilizing electroencephalogram (EEG) signal examination related to a mixture AI model. There are a few unique fields where sluggishness identification is vital, including medical services and transportation wellbeing. There is many times an absence of accuracy and strength in customary strategies. With the end goal of this examination, we utilize the broad transient data that is accumulated by EEG signals to plan a drowsiness forecast framework that is more reliable. The methodology that we use integrates approaches for highlight extraction with a cross breed AI model that joins profound learning and conventional AI calculations. In addition to the fact that the half breed model further develops interpretability and speculation, yet it likewise prevails with regards to catching perplexing examples in EEG information. To exhibit the viability of our recommended technique, we completed tests on an EEG dataset that was available to the overall population and gotten empowering discoveries. Because of its unrivaled exhibition as far as exactness and flexibility, the proposed model shows its true capacity for certifiable applications in the space of languor expectation and alleviation.