计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (8): 5-8.

• 博士论坛 • 上一篇    下一篇

基于支持向量机的睡眠结构分期研究

葛家怡1,周 鹏1,赵 欣1,刘海婴1,2,王明时1   

  1. 1.天津大学 精密仪器与光电子工程学院,天津 300072
    2.明尼苏达大学 放射系,美国
  • 收稿日期:2007-10-29 修回日期:2007-12-06 出版日期:2008-03-11 发布日期:2008-03-11
  • 通讯作者: 葛家怡

Study of sleep architecture stage based on Support Vector Machines

GE Jia-yi1,ZHOU Peng1,ZHAO Xin1,LIU Hai-ying1,2,WANG Ming-shi1   

  1. 1.College of Precision Instrument and Optoelectronics Engineering,Tianjin University,Tianjin 300072,China
    2.Department of Radiology,University of Minnesota,USA
  • Received:2007-10-29 Revised:2007-12-06 Online:2008-03-11 Published:2008-03-11
  • Contact: GE Jia-yi

摘要: 为了提高睡眠结构分期的准确度,克服分类时样本不足对分类的影响,使用MIT-BIH数据库整晚睡眠脑电数据作为研究样本,提取了时域、频域和非线性共16个参数作为分类特征,用支持向量机的一对一多类分类方法,采用顺序最小优化算法,以径向基函数作为核函数对样本分类。分类结果与专家的分类标注对比,分类准确率达到92%以上。支持向量机可作为睡眠分期的一种实用算法。

Abstract: In order to increase the accuracy of sleep architecture stage and overcome the influence in classification brought by samples shortage,all night sleep EEG data from MIT-BIH database are accepted as the research sample and totally 16 parameters including time-domain,frequency-domain and nonlinear picked up for sleep classification using 1-against-1 multi-classification method of Support Vector Machines using Sequential Minimal Optimization algorithm and selecting radial basis function as the kernel function.In contrast to expert’s manually-scored classification label,the classification result is more than 92%.It shows that Support Vector Machines can be a kind of effective algorithm in sleep stage.