文献类型：期刊文献

英文题名：Automatic Sleep Staging Method Based on EEG Signal and its Optimized Feature Space

作者：Yang, Meng[1]; Li, Ruichen[1]; Wang, Bei[1]; Zhang, Tao[2]

机构：[1] East China University of Science and Technology, School of Information Science and Engineering, Shanghai, 200237, China; [2] Tsinghua University, Department of Automation, Beijing, 100084, China

年份：2022

起止页码：208

外文期刊名：ICIIBMS 2022 - 7th International Conference on Intelligent Informatics and Biomedical Sciences

收录：EI(收录号：20230113340582)

语种：英文

外文关键词：Matrix algebra - Neural networks - Sleep research

摘要：Sleep is essential for physical and mental health. One's overnight sleep is usually evaluated into different sleep stages consisting of several sleep cycles. Computerized sleep staging would be an efficient tool but the performance is still required to be developed. In this study, an automatic sleep staging method is realized based on EEG signal and its optimized feature space. Several characteristic features are extracted from sleep EEG as an original feature space. A non-negative matrix factorization method based on kernel function and sparse improvement is developed to optimize the feature space for sleep staging. A classification model is constructed based on BP neural network and the parameters are estimated by PSO algorithm. Totally 10 overnight sleep recordings were tested. The proposed method achieved an average classification accuracy of 81% which is rather satisfactory as an assistant tool for application. ? 2022 IEEE.