Classification of Sleep Stages via Machine Learning Algorithms

Abstract

Sleep is a natural form of rest for humans. People need sleep to perform their daily functions. Insufficient or unstable sleep may adversely affect the function of many systems in human body. Sleep disorders can be seen common and cause serious health problems that affect quality of life. From past to present, it has become imperative to classify sleep stages in order to accurately analyze and diagnose these disorders. This classification is made by people who are experts in the field of sleep. However, this process is a very laborious task that requires high attention, and since it is done by a human, it is quite normal to make wrong classifications. As a solution to this, it is possible to make these classifications with machine learning techniques to obtain more accurate results. In this study, we compared different classification methods with each other and examined the channel-based accuracy of the method that gives the highest accuracy based on channels. The accuracy of the Fine Gaussian SVM Method was 98.9% and the F1-score was 98.95, the accuracy of the Weighted KNN Method was 97.9% and the F1-score was 97.89, the accuracy of the Wide Neural Network Method was 97.4% and the F1-score was 97.09, the accuracy of the Cubic SVM Method was 96.2% and the F1-score was 96.36. When we examine the Fine Gaussian SVM Method with the highest accuracy based on channels, we found accuracy of only Fpz-CZ channel is 98.1%, accuracy of only Pz-Oz channel is 94.5%.