首页> 外文会议>International Symposium on Communications, Control and Signal Processing >Identification of Congestive Heart Failure Using Soft Decision Sub- Band Decomposition and Artificial Neural Networks
【24h】

Identification of Congestive Heart Failure Using Soft Decision Sub- Band Decomposition and Artificial Neural Networks

机译:利用软判定子带分解和人工神经网络鉴定充血性心力衰竭

获取原文

摘要

A new identification method for screening patients with congestive heart failure (CHF) from normal controls is investigated in this paper using spectral analysis and artificial neural networks. This method is based on approximate spectral density estimation of RRI data using the soft decision sub-band decomposition technique. The data used in this work is obtained from MIT databases. A trial data set of 17 CHF and 53 normal subjects is used to obtain the classification features. The classification features are the spectral density of 6 different regions covering the whole spectrum of the RRI data obtained by 32 bands of the soft decision algorithm. The trial data set is used to train the neural network, which then used to test another test set of MIT data consisting of 12 CHF and 12 normal subjects. The accuracy of the classification is about 92%.
机译:本文使用光谱分析和人工神经网络研究了来自正常对照的充血性心力衰竭(CHF)筛查患者的新鉴定方法。该方法基于使用软判决子带分解技术的RRI数据的近似频谱密度估计。本工作中使用的数据是从MIT数据库获得的。使用17 CHF和53正常对象的试用数据集来获得分类功能。分类特征是6种不同区域的频谱密度,其覆盖由软决策算法的32个频带获得的RRI数据的整个频谱。试用数据集用于训练神经网络,然后训练,然后用于测试由12个CHF和12个正常对象组成的MIT数据的另一个测试集。分类的准确性约为92%。

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