Competitive Multi-Verse Optimization with Deep Learning Based Sleep Stage Classification

Sleep plays a vital role in optimum working of the brain and body. Numerous people suffer from sleep-oriented illnesses like apnea, insomnia, etc. stage classification is primary process quantitative examination polysomnographic recording. scoring mainly based on experts’ knowledge which laborious time consuming. Hence, it can be essential to design automated sleep model using machine learning (ML) deep (DL) approaches. In this view, study focuses Competitive Multi-verse Optimization with Deep Learning Based Stage Classification (CMVODL-SSC) Electroencephalogram (EEG) signals. The proposed CMVODL-SSC intends effectively categorize different stages EEG Primarily, data pre-processing performed convert actual into useful format. Besides, cascaded long short term memory (CLSTM) employed perform process. At last, CMVO algorithm utilized for optimally tuning hyperparameters involved CLSTM model. order report enhancements model, wide range simulations was carried out results ensured better performance average accuracy 96.90%.