电子学报 ›› 2017, Vol. 45 ›› Issue (1): 225-231.DOI: 10.3969/j.issn.0372-2112.2017.01.031

• 学术论文 • 上一篇    下一篇

基于序列连通度的睡眠分期算法研究

刘志勇, 孙金玮   

  1. 哈尔滨工业大学电气工程及自动化学院, 黑龙江哈尔滨 150001
  • 收稿日期:2015-07-21 修回日期:2015-10-21 出版日期:2017-01-25
    • 通讯作者:
    • 孙金玮
    • 作者简介:
    • 刘志勇,男,1987年1月出生,河南延津人.61135部队助理工程师.哈尔滨工业大学电气学院在读博士研究生,研究方向为生物医学信号处理.E-mail:liuzhiyong563@hit.edu.cn
    • 基金资助:
    • 哈尔滨工业大学理工医交叉学科基础研究培育计划 (No.HIT.IBRSEM.2013005); 哈尔滨市科技创新人才研究专项资金 (No.2015RAXXJ038)

Sleep Staging from the Visibility Graph Algorithm of Series

LIU Zhi-yong, SUN Jin-wei   

  1. Harbin Institute of Technology, School of Electrical Engineering and Automatic, Harbin, Heilongjiang 150001, China
  • Received:2015-07-21 Revised:2015-10-21 Online:2017-01-25 Published:2017-01-25

摘要:

准确的睡眠分期有利于帮助人们改善睡眠质量.本文提出了一种基于序列连通度分析的特征参数提取算法,提取了连通度分布斜率,连通距离均值,平均连通距离均值以及改进的加权连通度均值等特征参数,采用最小二乘支持向量机对其进行训练和学习,建立了睡眠脑电的数学模型.结果表明,相对于目前已有的序列加权连通度算法,本文算法对于不同睡眠状态的分期正确率提高了约5.72%,特别是对于浅睡眠状态的分类正确率提高约9.65%.

关键词: 脑电信号, 序列连通度, 最小二乘支持向量机

Abstract:

Monitoring the sleep quality accurately can play an effective supporting role in helping people improve the quality of sleep.In the present study,a novel feature extraction algorithm is proposed based on the natural visibility graph and horizontal visibility graph methods.The slope of visibility degree distribution,the mean of visibility distance,the mean of averaged visibility distance and the mean of improved weighted visibility graph were extracted,and trained by the least square-support vector machines (LS-SVM) classifier.The mathematical model between electroencephalogram (EEG) and sleep state was established and verified by different samples.The results demonstrated that the classification accuracy of different states improved about 5.72% compared to the existing weighted visibility graph,the classification accuracy of shallow sleep states improved about 9.65%.

Key words: EEG(Electroencephalogram), visibility graph, LS-SVM(Least square-support vector machines)

中图分类号: