Machine learning-Based sleep stage prediction using EEG signals recorded in PSG

Sleep problems are very common nowadays. Many conventional methods are there for analysing this types of problems. But these methods are often time consuming, expensive and also human interventions are needed. So the need automatic diagnostic tool is very much important. Different artificial intelligence technologies like deep learning ensure the full utilization of data with very less information loss. In this paper a diagnostic tool is proposed by using the methods in machine learning. Signals were pre-processed in the first module, and the feature extraction is done by power spectral density technique (PSD). In the final section, features that had been extracted were put into an ensemble classifier, also known as a rotational support vector machine (RotSVM). The accuracy & sensitivity for the sleep stages classification is also calculated. According to classification performance results, 1D channel EEG can be used to create a sleep monitoring system that is useful for the hospitals and home care monitoring systems.