基于VMD和KNN的心电信号分类算法
|
摘要
心电信号反映了心脏的活动状态,在诊断心脏疾病和指导心脏手术方面有重要参考价值,为提高心电信号的分类准确率,降低识别难度,提出了一种基于变分模态分解(VMD)和K最近邻(KNN)相结合的心电信号分类算法。使用MIT-BIH心律失常库中的数据,选取5类心电波形作为主要分类对象,从多个记录中截取心电信号作为样本数据,确定最优分解层数,利用VMD分解提取各模态的能量特征作为分类特征,最后运用KNN算法对信号进行分类识别并与支持向量机(SVM)和BP神经网络等分类方法进行了对比。实验结果表明,该方法在少量样本的情况下依然可以实现对心电信号的快速准确分类。
ECG signal reflects the active state of the heart and has important reference value in diagnosing heart diseases and guiding heart surgery,in order to improve the accuracy of ECG classification and to reduce the difficulty of recognition,an ECG signal classification algorithm based on variational mode decomposition( VMD) and K-nearest neighbor( KNN) is proposed. Using the data from the MIT-BIH arrhythmia database,five types of ECG waveforms were selected as the main classification objects,intercepting ECG signals from multiple records as sample data,determining the optimal decomposition layer number and extracting the energy features of each mode as a classification feature by VMD. Finally,the KNN algorithm is used to classify signals and compared with the other methods such as support vector machine( SVM) and BP neural network. The experimental results show that this method can quickly and accurately classify the ECG signal even in the case of smaller number of samples.
ECG signal reflects the active state of the heart and has important reference value in diagnosing heart diseases and guiding heart surgery,in order to improve the accuracy of ECG classification and to reduce the difficulty of recognition,an ECG signal classification algorithm based on variational mode decomposition( VMD) and K-nearest neighbor( KNN) is proposed. Using the data from the MIT-BIH arrhythmia database,five types of ECG waveforms were selected as the main classification objects,intercepting ECG signals from multiple records as sample data,determining the optimal decomposition layer number and extracting the energy features of each mode as a classification feature by VMD. Finally,the KNN algorithm is used to classify signals and compared with the other methods such as support vector machine( SVM) and BP neural network. The experimental results show that this method can quickly and accurately classify the ECG signal even in the case of smaller number of samples.
引文
[1]明东,柯余峰,何峰,等.基于生理信号的脑力负荷检测及自适应自动化系统研究:40年回顾与最新进展[J].电子测量与仪器学报,2015,29(1):1-13.MING D,KE Y F,HE F,et al.Psychophysiological measures based studies on mental workload assessment and adaptive automation:Review of the last 40 years and the latest developments[J].Journal of Electronic Measurement and Instrumentation,2015,29(1):1-13.
[2]王彦磊,杨翠微,余建国.心电标测系统中激动时刻提取方法的比较研究[J].仪器仪表学报,2015,36(3):661-667.WANG Y L,YANG C W,YU J G.Comparative research on extracting methods of activation time in cardiac mapping system[J].Chinese Journal of Scientific Instrument,2015,36(3):661-667.
[3]韩君泽.心电信号自动检测与诊断方法的研究[D].哈尔滨:哈尔滨工业大学,2013.HAN J Z.Research on automatic ECG detection and diagnosis method[D].Harbin:Harbin Institute of Technology,2013.
[4]WANG J S,CHIANG W C,HSU Y L,et al.ECGarrhythmia classification using a probabilistic neural network with a feature reduction method[J].Neurocomputing,2013,116(10):38-45.
[5]BENALI R,BEREKSI R F,HADJ S Z.Automatic classification of heartbeats using wavelet neural network[J].Journal of Medical Systems,2012,36(2):883-892.
[6]颜昊霖,安勇,王宏飞,等.基于深度信念网的心电自动分类[J].计算机工程与设计,2017,38(5):1331-1334.YAN H L,AN Y,WANG H F,et al.ECG heartbeat classification based on deep belief networks[J].Computer Engineering and Design,2017,38(5):1331-1334.
[7]向玲,张力佳.变分模态分解在转子故障诊断中的应用[J].振动.测试与诊断,2017,37(4):793-799,847.XIANG L,ZHANG L J.Application of variational mode decomposition in fault diagnosis of rotors[J].Journal of Vibration,Measurement&Diagnosis,2017,37(4):793-799,847.
[8]樊存佳,汪友生,边航.一种改进的KNN文本分类算法[J].国外电子测量技术,2015,34(12):39-43.FAN C J,WANG Y SH,BIAN H.Improved KNN text classification algorithm[J].Foreign Electronic Measurement Technology,2015,34(12):39-43.
[9]石明江,罗仁泽,付元华.小波和能量特征提取的旋转机械故障诊断方法[J].电子测量与仪器学报,2015,29(8):1114-1120.SHI MJ,LUO R Z,FU Y H.Fault diagnosis of rotating machinery based on wavelet and energy feature extraction[J].Journal of Electronic Measurement and Instrumentation,2015,29(8):1114-1120.
[10]崔善政,郭艳珍,梁钊,等.变分模态分解在去除心电图信号基线漂移中的应用[J].电子测量与仪器学报,2018,32(2):167-171.CUI SH ZH,GUO Y ZH,LIANG ZH,et al.Applicantion of variational mode decomposition in removing the ECG signal baseline drift[J].Journal of Electronic Measurement and Instrumentation,2018,32(2):167-171.
[11]张金玲,郑鑫.平稳小波变换和新阈值函数用于心电信号去噪[J].北京邮电大学学报,2017,40(1):28-31.ZHANG J L,ZHENG X.Stationary wavelet transform and new threshold function used in ECG signal denoising[J].Journal of Beijing University of Posts and Telecommunications,2017,40(1):28-31.
[12]LI H,CAO L,CAO L,et al.A new ECG signal classification based on WPD and Ap En feature extraction[J].Circuits Systems&Signal Processing,2016,35(1):339-352.
[13]曾芸,武和雷.基于小波包的频带能量特征提取及智能诊断[J].计算技术与自动化,2008,27(4):115-117,127.ZENG Y,WU H L.The energy characteristics on the frequency bands extracted eased on the wavelet packet and intelligent diagnosis[J].Computing Technology and Automation,2008,27(4):115-117,127.
[14]黄良沛,吴超威,王靖.小波包分析和BP神经网络在滚动轴承故障模式识别中的应用[J].电子测量技术,2016,39(4):164-168.HUANG L P,WU CH W,WANG J.Fault pattern recognition of rolling bearing using wavelet package analysis and BP neural network[J].Electronic Measurement Technology,2016,39(4):164-168.
[15]焦卫东,林树森.整体改进的基于支持向量机的故障诊断方法[J].仪器仪表学报,2015,36(8):1861-1870.JIAO W D,LIN SH S.Overall-improved fault diagnosis approach based on support vector machine[J].Chinese Journal of Scientific Instrument,2015,36(8):1861-1870.
[2]王彦磊,杨翠微,余建国.心电标测系统中激动时刻提取方法的比较研究[J].仪器仪表学报,2015,36(3):661-667.WANG Y L,YANG C W,YU J G.Comparative research on extracting methods of activation time in cardiac mapping system[J].Chinese Journal of Scientific Instrument,2015,36(3):661-667.
[3]韩君泽.心电信号自动检测与诊断方法的研究[D].哈尔滨:哈尔滨工业大学,2013.HAN J Z.Research on automatic ECG detection and diagnosis method[D].Harbin:Harbin Institute of Technology,2013.
[4]WANG J S,CHIANG W C,HSU Y L,et al.ECGarrhythmia classification using a probabilistic neural network with a feature reduction method[J].Neurocomputing,2013,116(10):38-45.
[5]BENALI R,BEREKSI R F,HADJ S Z.Automatic classification of heartbeats using wavelet neural network[J].Journal of Medical Systems,2012,36(2):883-892.
[6]颜昊霖,安勇,王宏飞,等.基于深度信念网的心电自动分类[J].计算机工程与设计,2017,38(5):1331-1334.YAN H L,AN Y,WANG H F,et al.ECG heartbeat classification based on deep belief networks[J].Computer Engineering and Design,2017,38(5):1331-1334.
[7]向玲,张力佳.变分模态分解在转子故障诊断中的应用[J].振动.测试与诊断,2017,37(4):793-799,847.XIANG L,ZHANG L J.Application of variational mode decomposition in fault diagnosis of rotors[J].Journal of Vibration,Measurement&Diagnosis,2017,37(4):793-799,847.
[8]樊存佳,汪友生,边航.一种改进的KNN文本分类算法[J].国外电子测量技术,2015,34(12):39-43.FAN C J,WANG Y SH,BIAN H.Improved KNN text classification algorithm[J].Foreign Electronic Measurement Technology,2015,34(12):39-43.
[9]石明江,罗仁泽,付元华.小波和能量特征提取的旋转机械故障诊断方法[J].电子测量与仪器学报,2015,29(8):1114-1120.SHI MJ,LUO R Z,FU Y H.Fault diagnosis of rotating machinery based on wavelet and energy feature extraction[J].Journal of Electronic Measurement and Instrumentation,2015,29(8):1114-1120.
[10]崔善政,郭艳珍,梁钊,等.变分模态分解在去除心电图信号基线漂移中的应用[J].电子测量与仪器学报,2018,32(2):167-171.CUI SH ZH,GUO Y ZH,LIANG ZH,et al.Applicantion of variational mode decomposition in removing the ECG signal baseline drift[J].Journal of Electronic Measurement and Instrumentation,2018,32(2):167-171.
[11]张金玲,郑鑫.平稳小波变换和新阈值函数用于心电信号去噪[J].北京邮电大学学报,2017,40(1):28-31.ZHANG J L,ZHENG X.Stationary wavelet transform and new threshold function used in ECG signal denoising[J].Journal of Beijing University of Posts and Telecommunications,2017,40(1):28-31.
[12]LI H,CAO L,CAO L,et al.A new ECG signal classification based on WPD and Ap En feature extraction[J].Circuits Systems&Signal Processing,2016,35(1):339-352.
[13]曾芸,武和雷.基于小波包的频带能量特征提取及智能诊断[J].计算技术与自动化,2008,27(4):115-117,127.ZENG Y,WU H L.The energy characteristics on the frequency bands extracted eased on the wavelet packet and intelligent diagnosis[J].Computing Technology and Automation,2008,27(4):115-117,127.
[14]黄良沛,吴超威,王靖.小波包分析和BP神经网络在滚动轴承故障模式识别中的应用[J].电子测量技术,2016,39(4):164-168.HUANG L P,WU CH W,WANG J.Fault pattern recognition of rolling bearing using wavelet package analysis and BP neural network[J].Electronic Measurement Technology,2016,39(4):164-168.
[15]焦卫东,林树森.整体改进的基于支持向量机的故障诊断方法[J].仪器仪表学报,2015,36(8):1861-1870.JIAO W D,LIN SH S.Overall-improved fault diagnosis approach based on support vector machine[J].Chinese Journal of Scientific Instrument,2015,36(8):1861-1870.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |