Supervised Machine Learning Algorithm using Sleep Cycle Classification

Electroencephalogram (EEG) signals provide useful information for diagnosing sleep disorders such as restless legs syndrome, insomnia, snoring, and sleep hypoventilation. The use of an automatic sleep stage classification system based on EEG signals has therefore garnered a lot of research interest recently. The current techniques for classifying sleep are not enough to examine the temporal transformation, waveform patterns, and texture patterns of EEG signals. In the projected work we used a supervised machine learning algorithm to detect the sleep cycle. The authors used publicly available datasets for training and testing. The accuracy of the supervised model is 95% and the testing accuracy is 89%. Algorithm is find the better solution for the sleep cycle classification.