基于集成学习的室性早博识别方法

doi:10.3969/j.issn.0372-2112.2017.02.032

电子学报 ›› 2017, Vol. 45 ›› Issue (2): 501-507.DOI: 10.3969/j.issn.0372-2112.2017.02.032

基于集成学习的室性早博识别方法

周飞燕^1,2, 金林鹏^1,2, 董军¹

1. 中国科学院苏州纳米技术与纳米仿生研究所, 江苏苏州 215123;
2. 中国科学院大学, 北京 100049

收稿日期:2015-09-25 修回日期:2016-02-25 出版日期:2017-02-25
- 通讯作者:
- 董军
- 作者简介:
- 周飞燕,女,1986年4月出生,广西崇左人.博士研究生,研究方向为计算机辅助心血管疾病诊断.E-mail:fyzhou2013@sinano.ac.cn;金林鹏,男,1984年6月出生,浙江瑞安人.博士,研究方向为机器学习.E-mail:lpjin2012@sinano.ac.cn

PVC Recognition Algorithm Based on Ensemble Learning

ZHOU Fei-yan^1,2, JIN Lin-peng^1,2, DONG Jun¹

1. Suzhou Institute of Nano-tech and Nano-bionics, Chinese Academy of Sciences, Suzhou, Jiangsu 215123, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2015-09-25 Revised:2016-02-25 Online:2017-02-25 Published:2017-02-25

摘要/Abstract

摘要：

本文提出了一种集成学习方法以提升室性早搏的识别性能.MIT-BIH两个通道的数据分别经过卷积神经网络进行室性早搏心拍分类，然后按照融合规则对分类结果进行融合决策，其准确率、灵敏度和特异性分别为99.91%、98.76%、99.97%，优于已有算法的室性早搏心拍分类结果.此外，面向临床应用，本文还利用卷积神经网络和诊断规则相结合的方法实现了病人间室性早搏识别实验，在有14万多条记录的数据集上，取得的准确率、灵敏度及特异性分别为97.87%、87.94%、98.02%，验证了该算法的有效性.

关键词: 室性早搏, 卷积神经网络, 诊断规则

Abstract:

In order to improve the recognition performance of premature ventricular contraction (PVC),this paper reports an algorithm based on ensemble learning.First,the tow-lead ECG signals from the MIT-BIH Arrhythmia database are classified into PVC and non PVC beats using lead convolutional neural network (LCNN) classifier.Then the results are fused with some rules.The accuracy,sensitivity and specificity of the proposed algorithm are 99.91%,98.76% and 99.97%,respectively,which are better than that of other existing algorithms for PVC beats classification.In addition,this paper realizes an inter-patient PVC recognition experiment by combining LCNN and diagnostic rules for clinical application.The effectiveness of the proposed algorithm has been confirmed by the accuracy (97.87%),sensitivity (87.94%) and specificity (98.02%) with the data set over 140000 ECG records.

Key words: premature ventricular contraction (PVC), lead convolutional neural network (LCNN), diagnosis rules

中图分类号:

TP391

周飞燕, 金林鹏, 董军. 基于集成学习的室性早博识别方法[J]. 电子学报, 2017, 45(2): 501-507.

ZHOU Fei-yan, JIN Lin-peng, DONG Jun. PVC Recognition Algorithm Based on Ensemble Learning[J]. Acta Electronica Sinica, 2017, 45(2): 501-507.

参考文献

[1] KHAZAEE Ali.Combining SVM and PSO for PVC detection[J].International Journal of Advances in Engineering Sciences,2013,3(4):1-5.
[2] HUANG Dong,LIAO Zhengquan,LI Changbin,et al.ECG PVC classification algorithm based on fusion SVM and wavelet transform[J].International Journal of Signal Processing,Image Processing and Pattern Recognition,2015,8(1):193-201.
[3] INAN O T,GIOVANGRANDI L,KOVACS G T A.Robust neural-network-based classification of premature ventricular contractions using wavelet transform and timing interval features[J].IEEE Transactions on Biomedical Engineering,2006,53(12):2507-2515.
[4] MITTAL Ankita,AHLAWAT Meena.Detection of cardiac arrhythmias using different neural networks:a review[J].International Journal of Advanced Research in Computer and Communication Engineering,2014,3(6):6992-6995.
[5] 孟兆辉,张永红,白净.模糊算法在心律失常病类判别中的应用[J].电子学报,2001,29(9):1246-1248. MENG Zhaohui,ZHANG Yonghong,BAI Jing.A fuzzy method for classification of arrhythmias[J].Acta Electronica Sinica,2001,29(9):1246-1248.(in Chinese)
[6] LEK-UTHAI Apiwat,ITTATIRUT Supat,TEERAMONGKONRASMEE Arporn.Algorithm development for real-time detection of premature ventricular contraction[A].TENCON 2014-2014 IEEE Region 10 Conference[C].Bangkok:IEEE,2014:1-5.
[7] KANWAR Geeta,DEWANGAN Naveen Kumar,DEWANGAN Kiran.A review:detection of premature ventricular contraction beat of ECG[J].International Journal of Advanced Research in Electrical,Electronics and Instrumentation Engineering,2015,4(2):939-942.
[8] YE Can,KUMAR B V K Vijaya,COIMBRA Miguel Tavares.Heartbeat classification using morphological and dynamic features of ECG signals[J].IEEE Transactions on Biomedical Engineering,2012,59(10):2930-2941.
[9] Association for the Advancement of Medical Instrumentation.ANSI/AAMI EC57:2012 Standard:Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms[S].USA:AAMI Press,2012.
[10] 金林鹏,董军.面向临床心电图分析的深层学习算法研究[J].中国科学:信息科学,2015,45(3):398-416. JIN Linpeng,DONG Jun.Deep learning research on clinical electrocardiogram analysis[J].Science China:Information Sciences,2015,45(3):398-416.(in Chinese)
[11] AHLSTROM M L,TOMPKINS W J.Digital filters for real-time ECG signal processing using microprocessors[J].IEEE Transactions on Biomedical Engineering,1985,32(9):708-713.
[12] 高清维,李海鹰,庄镇泉,等.基于平稳小波变换的心电信号噪声消除方法[J].电子学报,2003,31(2):238-240. GAO Qingwei,LI Haiying,ZHUANG Zhenquan,et al.De-noising of ECG signal based on stationary wavelet transform[J].Acta Electronica Sinica,2003,31(2):238-240.(in Chinese)
[13] 杨向林,严洪,许志,等.基于Hilbert-Huang变换的ECG消噪[J].电子学报,2011,39(4):819-824. YANG Xianglin,YAN Hong,XU Zhi,et al.ECG de-noising based on Hilbert-Huang transform[J].Acta Electronica Sinica,2011,39(4):819-824.(in Chinese)
[14] VALENTINI Giorgio,MASULLI Francesco.Ensembles of learning machines[A].Proceedings of the 13th Italian Workshop on Neural Nets-revised Papers[C].London:Springer Berlin Heidelberg,2002:3-20.
[15] ZHOU Zhi-Hua,WU Jianxin,TANG Wei.Ensembling neural networks:many could be better than all[J].Artificial Intelligence,2002,137:239-263.
[16] KITTLER Josef,HATEF Mohamad,DUIN Robert P W,et al.On combining classifiers[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(3):226-238.
[17] 徐拥军,钟玉秋,曾文斌.一种基于心电向量的心电波形特征点定位方法[P].中国专利:201410068351.6,2014-02-27.
[18] MIT-BIH Arrhythmia Database[EB/OL].http://www.physionet.org/physiobank/database/mitdb/.2015.6[2015-09-25].
[19] ZHANG Jiawei,LIU Xia,DONG Jun.CCDD:an enhanced standard ECG database with its management and annotation tools[J].International Journal on Article Intelligence Tools,2012,21(5):1-26.
[20] DONG Jun,ZHANG Jiawei,ZHU Honghai,et al.Wearable ECG monitors and its remote diagnosis service platform[J].IEEE Intelligent Systems,2012,27:36-43.
[21] 朱洪海.心电图自动识别的关键算法及多体征监护系统研制[D].北京:中国科学院大学,2013. ZHU Honghai.Key algorithms on Computer-Aided Electrocardiogram Analysis and Development of Remote Multi-signs Monitoring System[D].Beijing:University of Chinese Academy of Sciences,2013.(in Chinese)
[22] 王丽苹.融合领域知识的心电图分类方法研究[D].上海:华东师范大学,2012. WANG Liping.Study on Approach of ECG Classification with Domain Knowledge[D].Shanghai:East China Normal University,2012.(in Chinese)
[23] HAKACOVA Nina,TRAGARDH-JOHANSSON Elin,WAGNER Galen S,et al.Computer-based rhythm diagnosis and its possible influence on nonexpert electrocardiogram readers[J].Journal of Electrocardiology,2012,45(1):18-22.

基于集成学习的室性早博识别方法

PVC Recognition Algorithm Based on Ensemble Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[2]	毛国君, 王者浩, 黄山, 王翔. 基于剪边策略的图残差卷积深层网络模型[J]. 电子学报, 2022, 50(9): 2205-2214.
[3]	袁海英, 曾智勇, 成君鹏. 面向灵活并行度的稀疏卷积神经网络加速器[J]. 电子学报, 2022, 50(8): 1811-1818.
[4]	张志文, 刘天歌, 聂鹏举. 基于实景数据增强和双路径融合网络的实时街景语义分割算法[J]. 电子学报, 2022, 50(7): 1609-1620.
[5]	王相海, 赵晓阳, 王鑫莹, 赵克云, 宋传鸣. 非抽取小波边缘学习深度残差网络的单幅图像超分辨率重建[J]. 电子学报, 2022, 50(7): 1753-1765.
[6]	丁毅, 沈薇, 李海生, 钟琼慧, 田明宇, 李洁. 面向CNN的区块链可信隐私服务计算模型[J]. 电子学报, 2022, 50(6): 1399-1409.
[7]	张波, 陆云杰, 秦东明, 邹国建. 一种卷积自编码深度学习的空气污染多站点联合预测模型[J]. 电子学报, 2022, 50(6): 1410-1427.
[8]	廖勇, 李玉杰. 一种轻量化低复杂度的FDD大规模MIMO系统CSI反馈方法[J]. 电子学报, 2022, 50(5): 1211-1217.
[9]	张云, 化青龙, 姜义成, 徐丹. 基于混合型复数域卷积神经网络的三维转动舰船目标识别[J]. 电子学报, 2022, 50(5): 1042-1049.
[10]	崔亚奇, 何友, 唐田田, 熊伟. 一种深度学习航迹关联方法[J]. 电子学报, 2022, 50(3): 759-763.
[11]	伍邦谷, 张苏林, 石红, 朱鹏飞, 王旗龙, 胡清华. 基于多分支结构的不确定性局部通道注意力机制[J]. 电子学报, 2022, 50(2): 374-382.
[12]	陈文俊, 杨春玲. 图像压缩感知的特征域优化及自注意力增强神经网络重构算法[J]. 电子学报, 2022, 50(11): 2629-2637.
[13]	魏钰轩, 陈莹. 基于自适应层信息熵的卷积神经网络压缩[J]. 电子学报, 2022, 50(10): 2398-2408.
[14]	肖斌, 陈嘉博, 毕秀丽, 张俊辉, 李伟生, 王国胤, 马旭. 基于一维卷积神经网络与循环神经网络串联的心音分析方法[J]. 电子学报, 2022, 50(10): 2425-2432.
[15]	周登文, 李文斌, 李金新, 黄志勇. 一种轻量级的多尺度通道注意图像超分辨率重建网络[J]. 电子学报, 2022, 50(10): 2336-2346.