A comparison of different machine learning algorithms using single channel EEG signal for classifying human sleep stages

Abstract

In recent years, the estimation of human sleep disorders from Electroencephalogram (EEG) signals have played an important role in developing automatic detection of sleep stages. A few methods exist in the market presently towards this aim. However, sleep physicians may not have full assurance and consideration in such methods due to concerns associated with systems accuracy, sensitivity and specificity. This paper presents a novel and efficient technique that can be implemented in a microcontroller device to identify sleep stages in an effort to assist physicians in the diagnosis and treatment of related sleep disorders by enhancing the accuracy of the developed algorithm using a single channel of EEG signals. First, the dataset of EEG signal is filtered and decomposed into delta, theta, alpha, beta and gamma subbands using Butterworth band-pass filters. Second, a set of sample statistical discriminating features are derived from each frequency band. Finally, sleep stages consisting of Wakefulness, Rapid Eye Movement (REM) and Non-Rapid Eye Movement (NREM) are classified using several supervised machine learning classifiers including multi-class Support Vector Machines (SVM), Decision Trees (DT), Neural Networks (NN), K-Nearest Neighbors (KNN) and Naive Bayes (NB). This paper combines REM with Stage 1 NREM due to data similarities. Performance is then compared based on single channel EEG signals that were obtained from 20 healthy subjects. The results show that the proposed technique using DT classifier efficiently achieves high accuracy of 97.30% in differentiating sleeps stages. Also, a comparison of our method with some recent available works in the literature reiterates the high classification accuracy performance.

Human Sleep Scoring Based on K-Nearest Neighbors

“…This is a nonparametric classification technique that completely avoids assumptions about probability densities [4,5,32], and it is usually considered when there is no prior knowledge on the distribution of data. Sleep staging has been investigated by use of K-NN classifiers [4,22]. K-NN is widely used for both classification and regression.…”

“…Sleep analysis by monitoring the activities of the human by electroencephalogram (EEG), electromyography (EMG), and electrooculography (EOG) helps in identifying sleep-related problems [2]. The EEG method is considered one of the best techniques to record the human brain activity [3][4][5]. Sleep comprises a sequence of distinct physiological stages that can be distinguished from EEG related features.…”

A novel IoT-based wireless system to monitor heart rate

“…After some research, we decided to use Naive Bayes classification because it produces highly accurate results, it is simple, and easy to implement [18]. Naive Bayes is a probabilistic classifier that is popular in real time prediction applications.…”

“…(11) we need to find the probability of having a certain set of features and the probability of class C 1 , using Eqs. (17) and (18), in that order, where N is the number of classes.…”

“…Finally, we can calculate the probability of belonging to class C 1 given a set of features as follows using Eqs. (16), (17) and (18) in Eq. (19).…”