ZHANG Yan,SUN Jing,HU Jiancheng,et al.Sleep Stage Classification Using Single-channel EOG based on SVM and Wavelet Packet Transform[J].Journal of Chengdu University of Information Technology,2021,36(01):1-6.[doi:10.16836/j.cnki.jcuit.2021.01.001]
基于支持向量机和小波包变换的EOG信号睡眠分期
- Title:
- Sleep Stage Classification Using Single-channel EOG based on SVM and Wavelet Packet Transform
- 文章编号:
- 2096-1618(2021)01-0001-06
- Keywords:
- electrooculogram; SVM; wavelet packet transform; AR coefficients; smooth rules
- 分类号:
- TN911.6
- 文献标志码:
- A
- 摘要:
- 针对多通道信号或者多生理参数进行睡眠分期的不足,提出一种利用支持向量机(SVM)和小波包分解相结合对单通道眼电信号进行自动评分的方法。利用改进阈值的双树复小波变换对信号进行去噪处理,将数据以30 s数据为一个处理单位,使用小波包变换对每个单位眼电信号进行分解,再对小波包子带提取AR系数和小波包能量等特征。采用支持向量机(SVM)对不同30 s睡眠单位进行分类,获得初始分类结果,之后使用平滑规则对分类结果进行连续性处理并得到最终分类结果。结果表明所提的方法对睡眠评分能够得到精度为91.19%,Kappa系数为0.82,属于完全一致性。
- Abstract:
- Aiming at the deficiency of multi-channel signals or multi-physiological parameters in sleep staging, an automatic scoring method for single-channel Electrooculogram using support vector machine(SVM)and wavelet packet decomposition is proposed. Firstly, the signal is denoised by the modified threshold dual-tree complex wavelet transform. The data is then processed in units of 30 seconds. Then, the wavelet packet transform is used to decompose each unit of Electrooculogram, and the characteristics such as AR coefficients and wavelet packet energy are extracted from the wavelet packet sub-bands. Finally, support vector machine(SVM)was used to classify different 30-second sleep units to obtain the initial classification results, and then smoothing rules were used to continuously process the classification results and obtain the final classification results. The results showed that the accuracy of sleep score by the proposed method was 91.19% and the Kappa coefficient was 0.82, which was completely consistent.
参考文献/References:
[1] Hori T,Sugita Y,Koga E,et al.Proposed supplements and amendments to A Manual of Standardized Terminology,Techniques and Scoring System for Sleep Stages of Human Subjects,the Rechtschaffen & Kales(1968)standard[J].Psychiatry Clin Neurosci,2001,55(3):305-310.
[2] Schulz H,Phasic or transient.Comment on the terminology of the AASM manual for the scoring of sleep and associated events[J].Journal of Clinical Sleep Medicine Jcsm Official Publication of the American Academy of Sleep Medicine,2007,3(7):752.
[3] Guohun Zhu,Yan Li,Peng Paul Wen.Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal[J].IEEE journal of biomedical and health informatics,2014,18(6):1813-1821.
[4] Ghimatgar H,Kazemi K,Helfroush M S,et al.An automatic single-channel EEG-based sleep stage scoring method based on hidden Markov Model[J].Journal of Neuroence Methods,2019,324:108320.
[5] Berthomier C,Drouot X,Herman-Stoïca M,et al.Automatic analysis of single-channel sleep EEG:validation in healthy individuals[J].Sleep,2007; 30(11):1587-1595.
[6] Malafeev A,Omlin X,Wierzbicka A,et al.Automatic artefact detection in single-channel sleep EEG recordings[J].J Sleep Res,2019,28(2):12679.
[7] Rahman MM,Bhuiyan MIH,Hassan AR.Sleep stage classification using single-channel EOG[J].Comput Biol Med,2018,102:211-220.
[8] Jussi Virkkala,Joel Hasan,Alpo Värri,et al.Automatic sleep stage classification using two-channel electro-oculography[J].Journal of neuroscience methods,2007,166:109-115.
[9] 黄佳妹,石玉,闫光豹.基于改进阈值的双树复小波眼电信号去噪方法[J].测控技术,2015(8):16-18.
[10] Shubham Dodia, Damodar Reddy Edla, Annushree Bablani, et al. An efficient EEG based deceit identification test using wavelet packet transform and linear discriminant analysis[J].Journal of neuroscience methods,2019,314:31-40.
[11] 李昕,孙小棋,王欣,等.基于自回归小波包熵特征融合算法的情感识别研究[J]. 生物医学工程学杂志, 2017(6):831-836.
[12] 任雁,王洋.基于自回归模型的信号特征提取研究[J].电声技术, 2009(5).
[13] 安亚利,周水生,陈丽,等.鲁棒支持向量机及其稀疏算法[J].西安电子科技大学学报, 2019, 46(1):64-72.
[14] 郑树泉.工业智能技术与应用[M].上海:上海科学技术出版社,2019.
[15] 白亮,老松杨,胡艳丽.支持向量机训练算法比较研究[J].计算机工程与应用,2005(17):79.
[16] Liang S F,Kuo C E,Hu Y H,et al.A rule-based automatic sleep staging method[J].Journal of Neuroence Methods,2012,205(1):169-176.
[17] Liang S F,Kuo C E,Hu Y H,et al.A rule-based automatic sleep staging method[J].Journal of Neuroence Methods,2012,205(1):169-176.
[18] B Kemp,AH Zwinderman,B Tuk,et al.Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG[J].IEEE-BME,2000,47(9):1185-1194.
[19] 郭轶斌, 郭威, 秦宇辰,等.基于Kappa系数的一致性检验及其软件实现[J].中国卫生统计,2016(1):169-170.
[20] 唐万, 胡俊, 张晖,等.Kappa系数:一种衡量评估者间一致性的常用方法[J].上海精神医学,2015(1):62-67.
[21] Landis JR,Koch GG.The measurement of observer agreement for categorical data[J].Biometrics,1977,33(1):159-174.
相似文献/References:
[1]杨 頔,文成玉.结合关联规则的情感分析模型研究[J].成都信息工程大学学报,2019,(05):501.[doi:10.16836/j.cnki.jcuit.2019.05.011]
YANG Di,WEN Chengyu.Research on Emotional Analysis Model based on Association Rules[J].Journal of Chengdu University of Information Technology,2019,(01):501.[doi:10.16836/j.cnki.jcuit.2019.05.011]
备注/Memo
收稿日期:2020-08-06
基金项目:四川省科技厅重点研发资助项目(2020YFG0052)