• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Arabian Journal for Science and Engineering >Automated Detection of Sleep Stages Using Energy-Localized Orthogonal Wavelet Filter Banks
【24h】

Automated Detection of Sleep Stages Using Energy-Localized Orthogonal Wavelet Filter Banks

机译：使用能量局部正交小波滤波器组自动检测睡眠阶段

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Sleep is an integral part of human life which provides the body with much-needed rest which facilitates recovery and promoteshealth. Sleep disorders, however, lead to a reduced quality of sleep and as a result, affect the standard of human life. It isimportant to classify sleep stages in order to detect sleep disorders. Electroencephalogram (EEG) signals are obtained frompatients under observation. But, classifying these EEG signals into various sleep stages is an arduous task. It becomes moredifficultwhen one tries to classifyEEGsignals visually. Even sleep specialists struggle to classify theEEGsignals into differentsleep stages by visual inspection. Several approaches have been adopted by scientists across the world to mitigate these errorsby using EEG and polysomnogram signals. In this paper, an automated method has been proposed for scoring various sleepstages employing EEG signals. We have employed a two-band energy-localized filter in the time-frequency domain, whichdecomposed six sub-bands using five-levelwavelet decomposition. Subsequently,we compute discriminatory features namelyfuzzy entropy and log energy from the decomposed coefficients. The extracted features are fed to various supervised machinelearning classifiers. Our proposed approach yielded an accuracy of 91.5% and 88.5% for six-class classification task usingsmall and large datasets, respectively.
机译：睡眠是人类生活中不可或缺的一部分，可为身体提供急需的休息，从而促进康复并促进健康。但是，睡眠障碍会导致睡眠质量下降，从而影响人们的生活水平。重要的是对睡眠阶段进行分类以检测睡眠障碍。脑电图（EEG）信号从观察中的患者获得。但是，将这些EEG信号分为各种睡眠阶段是一项艰巨的任务。当人们试图以视觉方式对EEG信号进行分类时，这一点变得更加困难。甚至睡眠专家也难以通过视觉检查将EEG信号划分为不同的睡眠阶段。世界各地的科学家已采用多种方法通过使用EEG和多导睡眠图信号来减轻这些误差。在本文中，已经提出了一种自动方法，用于使用EEG信号对各种睡眠阶段进行评分。我们在时频域中使用了一个两频带能量局部滤波器，该滤波器使用五级小波分解分解了六个子频带。随后，我们根据分解后的系数计算出鉴别特征，即模糊熵和对数能量。提取的特征被馈送到各种监督的机器学习分类器。我们提出的方法对于使用小型和大型数据集的六类分类任务的准确率分别为91.5％和88.5％。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号