Affiliations: [a]
Department of Information Technology, Sona college of Technology, Salem | [b]
School of Computing Science and Engineering, Vellore Institute of Technology, Bhopal, India
| [c]
Department of ECE, Panimalar Engineering College Chennai, India
| [d]
School of Art and Design, Zhengzhou University of Industry Technology, XinZheng, China
Correspondence:
[*]
Corresponding author. Chuang Chen, School of Art and Design, Zhengzhou University of Industry Technology, XinZheng, 451100, China. E-mail: [email protected].
Abstract: The quality of sleep plays a crucial role in physical well-being, and individuals are becoming increasingly concerned about sleep quality and its associated health issues. Although various sleep monitoring devices exist, there remains a need for a highly accurate sleep state identification algorithm. To address this, we present a paper that utilizes machine learning techniques to identify human sleep states based on electroencephalogram (EEG) signals collected by an EEG instrument. We propose a model that incorporates two nonlinear characteristic parameters, MSE and PSE, extracted from artificially designed EEG signals as input. Additionally, we employ a Support Vector Machine (SVM) classifier algorithm to accurately identify sleep states, eliminating uncertainties associated with manually designed feature parameters. Experimental results demonstrate the superior accuracy of our proposed model for sleep state analysis, offering valuable insights for improving sleep quality and addressing related health concerns.
Keywords: Sleeping quality, health, electroencephalograph, support vector machine, machine
learning
