A comparative study between SVM and fuzzy inference system for the automatic prediction of sleep stages and the assessment of sleep quality

This paper compares two supervised learning algorithms for predicting the sleep stages based on the human brain activity. The first step of the presented work regards feature extraction from real human electroencephalography (EEG) data together with its corresponding sleep stages that are utilized for training a support vector machine (SVM), and a fuzzy inference system (FIS) algorithm. Then, the trained algorithms are used to predict the sleep stages of real human patients. Extended comparison results are demonstrated which indicate that both classifiers could be utilized as a basis for an unobtrusive sleep quality assessment.