计算机应用 ›› 2019, Vol. 39 ›› Issue (3): 930-934.DOI: 10.11772/j.issn.1001-9081.2018081677

• 应用前沿、交叉与综合 • 上一篇    

基于深度长短时记忆神经网络模型的心律失常检测算法

杨朔1,2, 蒲宝明2, 李相泽3, 王帅1,2, 常战国1,2   

  1. 1. 中国科学院大学 计算机与控制工程学院, 北京 100049;
    2. 中国科学院 沈阳计算技术研究所, 沈阳 110168;
    3. 东北大学 计算机科学与工程学院, 沈阳 110819
  • 收稿日期:2018-08-13 修回日期:2018-10-05 出版日期:2019-03-10 发布日期:2019-03-11
  • 通讯作者: 杨朔
  • 作者简介:杨朔(1993-),男,山东菏泽人,硕士研究生,主要研究方向:信号处理、机器学习;蒲宝明(1966-),男,辽宁沈阳人,研究员,博士生导师,硕士,主要研究方向:信号处理、人工智能;李相泽(1981-),男,辽宁沈阳人,讲师,博士研究生,主要研究方向:信号处理;王帅(1990-),男,山东济宁人,博士研究生,主要研究方向:计算机视觉、机器学习、信号处理;常战国(1992-),男,河南三门峡人,硕士研究生,主要研究方向:机器学习、人工智能。

Cardiac arrhythmia detection algorithm based on deep long short-term memory neural network model

YANG Shuo1,2, PU Baoming2, LI Xiangze3, WANG Shuai1,2, CHANG Zhanguo1,2   

  1. 1. School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100049, China;
    2. Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang Liaoning 110168, China;
    3. School of Computer Science and Engineering, Northeastern University, Shenyang Liaoning 110819, China
  • Received:2018-08-13 Revised:2018-10-05 Online:2019-03-10 Published:2019-03-11

摘要:

针对传统基于形态特征的心电检测算法存在特征提取不准确和高复杂性等问题,提出了一种多层的长短时记忆(LSTM)神经网络结构。结合传统LSTM模型在时序数据处理上的优势,该模型增加了反向和深度计算,避免了人工提取波形特征,提高了网络的学习能力。通过给定心拍序列和分类标签进行监督学习,然后实现对未知心拍的心律失常检测。通过对MIT-BIH数据库中的心律失常数据集进行实验验证,模型的总体准确率为98.34%。相比支持向量机(SVM),该模型的准确率和F1值均有提高。

关键词: 心律失常, 心电, 长短时记忆神经网络, 时序数据, 支持向量机

Abstract:

Aiming at the problems of inaccurate feature extraction and high complexity of traditional ElectroCardioGram (ECG) detection algorithms based on morphological features, an improved Long Short-Term Memory (LSTM) neural network was proposed. Based on the advantage of traditional LSTM model in time series data processing, the proposed model added reverse and depth calculations which avoids extraction of waveform features artificially and strengthens learning ability of the network. And supervised learning was performed in the model according to the given heart beat sequences and category labels, realizing the arrhythmia detection of unknown heart beats. The experimental results on the arrhythmia datasets in MIT-BIH database show that the overall accuracy of the proposed method reaches 98.34%. Compared with support vector machine, the accuracy and F1 value of the model are both improved.

Key words: cardiac arrhythmia, ElectroCardioGram (ECG), Long Short-Term Memory (LSTM) neural network, time series data, Support Vector Machine (SVM)

中图分类号: