Vol.:(0123456789) SN Computer Science (2021) 2:157 https://doi.org/10.1007/s42979-021-00528-5 SN Computer Science ORIGINAL RESEARCH A Study of Human Sleep Stage Classifcation Based on Dual Channels of EEG Signal Using Machine Learning Techniques Santosh Kumar Satapathy 1  · D. Loganathan 1 Received: 25 January 2021 / Accepted: 16 February 2021 / Published online: 20 March 2021 © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. part of Springer Nature 2021 Abstract Sleep staging is one of the important methods for the diagnosis of the diferent types of sleep-related diseases. Manual inspec- tion of sleep scoring is a very time-consuming process, labor-intensive, and requires more human interpretations, which may produce biased results. Therefore, in this paper, we propose an efcient automated sleep staging system to improve sleep staging accuracy. In this work, we extracted both linear and non-linear properties from the input signal. Next to that, a set of optimal features was selected from the extracted feature vector by using a feature reduction technique based on the ReliefF weight algorithm. Finally, the selected features were classifed through four machine learning techniques like support vector machine, K-nearest neighbor, decision tree, and random forest. The proposed methodology performed using dual- channel EEG signals from the ISRUC-Sleep dataset under the AASM sleep scoring rules. The performance of the proposed methodology compared with the existing similar methods. In this work, we considered the 10-Fold cross validation strategy; our proposed methods reported the highest classifcation accuracy of 91.67% with the C4-A1 channel, and 93.8% with the O2-A1 channel using the Random forest classifcation model. The result of the proposed methodology outperformed the earlier contribution for two-class sleep states classifcation. The proposed dual-channel sleep staging method can be helpful for the clinicians during the sleep scoring and treatment for the diferent sleep-related diseases. Keywords EEG signal · Sleep Stages · Classifcation · Machine learning Introduction Motivation Maintaining proper health and mental stableness is critical for overall health and well-being. Despite several relevant studies, sleep quality continues as a critical public challenge. Nowadays, people of all age groups are afected by improper sleep quality. Consequently, this scenario can later lead to neurological disorder diseases [1, 2]. Sleep disorders spread over with all categories of the population independently of diferent genders. This public challenge afects the quality of life in physical and mental health. Multiple insomnia, parasomnias, sleep-related breathing, hypersomnia, brux- ism, narcolepsy, circadian rhythms are relevant examples of sleep-related disorders. Some of these disorders can be treated with proper analysis of early symptoms where ensure adequate sleep quality is essential for the patient’s recovery. Moreover, numerous sleep disorders can be nowadays clini- cally diagnosed through computer-aided technologies [3]. Sleep monitoring is one of the most signifcant activities in the assessment of sleep-related disturbances and other neural problems. Sleep is a dynamic process and includes diferent sleep states such as the wake stage, the non-rapid eye move- ment (NREM), and the rapid eye movement (REM) sleep. Furthermore, the NREM sleep states are divided into four stages, namely NREM stage 1 (N1), stage 2 (N2), stage 3 (N3), stage 4 (N4) [4]. The wake-sleep stage is the awaken- ing period before sleep. The NREM sleep stages are sequen- tially indicative of light to deep sleep. Stage N1 is light sleep where the eyes move slowly, and the muscle movements are slow. The sleep starts from stage N2, where the eye movement stops, and brain activities decrease. The N3 and This article is part of the topical collection “Data Science and Communication” guest-edited by Kamesh Namudri, Naveen Chilamkurti, Sushma S J and S. Padmashree. * Santosh Kumar Satapathy santosh.satapathy@pec.edu 1 Department of Computer Science and Engineering, Pondicherry Engineering College, Puducherry, India