基于小波变换的心电信号预处理与特征识别算法
|
摘要
心血管疾病是人类死亡的主要原因之一,按世界卫生组织的统计,全世界每年死于心脏病的人约有1200万,占整个死亡人数的25%。随着现代人生活水平的不断提高,一些不健康的生活方式也会导致心脏病朝着年轻化发展。而心脏病特点是发病快,死亡率高,治疗难度大,治疗费用高。为了克服心脏病对人类的危害,早期发现,早期诊断,早期治疗可以显著降低死亡率。而家庭监护为这一切提供了可能。在家庭监护中,方便的心电图记录和心电自动诊断是人们关心的重点。本论文针对家庭便携式监护仪拟研究心电特征的检测方法。
心电图是心脏搏动的电位变化图。它的各种波形和间隔代表着心脏的电气特征,医生根据心电图的波形来判断心脏活动的异常,从而诊断心脏疾病,并且可以用来监测病人的身体状况,评估病情和治疗成效。因此,用计算机来分析心电图的特征波形就显得尤为重要,分析得是否准确和迅速直接关系到患者的治疗。
QRS复合波是心电图中最明显的波也是心电信号分析的基础,QRS波的定位是否准确直接关系到后续的监测。每个人的QRS波的形态有所差异,并且同一个人的QRS波也根据个人状态而表现出很大的差异性,因此,准确监测QRS波存在很大的难度。如何既能保持检测的准确性又能保证检测的时效性是很多研究人员面临的课题。
小波变换方法的出现为信号检测提供了全新的方法。小波变换具有多尺度,多分辨分析的特点,可将信号进行多尺度分解,并把不同频带的信号现实在分解的不同尺度上。这样可以根据不同信号信息所在的频带来进行具体的分析。
本文首先介绍了心电图的一些相关内容,各种波形的特点以及噪声的种类。对本实验中所使用的MIT-BIH心电数据库和小波变换的相关基础知识也作了简单的介绍。本文详细说明了使用小波变换方法对心电图进行降噪处理和特征识别。首先,对心电图进行消噪操作,尝试使用多种方法进行降噪。然后,利用三次样条小波在心电图特征点识别方面的突出优势,对心电图进行8层分解,对R波识别和定位;在此基础上,找出R波的起止点的位置;并且定位P和T波的位置;确定RR间期。本文的重点是对R波进行准确的定位,计算RR间期和确定QRS波的起止点。并在此基础上尝试对P、T波进行检测。P、T波的检测是心电图检测的难点所在。最后,在算法评估中,我们将心电图原始数据与所检测到的数据相对比,进行统计分析,评估算法的准确率。
Cardiac diseases are thought as a kind of major diseases which become more and more serious to human health.According to the Statistics of the WHO,it is about more than 1.2 million people died of Cardiac diseases,account for 25%of the total mortality. As the improving of the living standard,some unhealthy lifestyle would lead the diseases to the trend of rejuvenation.The characteristics of Cardiac diseases are:onset fast,high mortality rate,difficult to treat,expensive treatment cost.In order to overcome the danger of the diseases,early detection,diagnosis,and treatment will greatly decrease mortality rate.Family monitoring make it possible.In the family monitoring,to record the ECG conveniently and detect automatically are the most important.
Electrocardiogram is a pictorial representation of the electrical activity of heart beats.Because of the direct relationship between the ECG waveform and interval of the heart beats,it is possible that doctor can diagnose cardiac disease and monitor patient conditions from the unususal ECG waveforms.
QRS complex detection is the base of automatic analysis of ECG,which is mostly the first step of analysis and affects the following steps greatly.The difficulties of QRS detection lie in two factors:firstly,the physiological variability of QRS complex. Secondly,the various types of noises that can present in the ECG,for instance the power line noise,muscle noise,baseline drift.
Using Multriesolution wavelet Analysis decomposed the ECG signal on multiscals, different frequency-bands of the signal were showed on different scales.Analysis signals in different frequency-bands.
Based on the wavelet transform,this thesis introduces an algorithm to detect QRS complex.In particular,the quadratic spline wavelet has been adopted.The thesis first reviews wavelet transform briefly,and de-noise the ECG signal;then develops a QRS detention algorithm,which is then tested by using the MIH-BIH arrhythmia database. The result of experiments shows that the performance of models based on Quadratic
Spline Wavelet is superior,and it can detect QRS complex exactly.We use this algorithm to identify and locate the R-Wave of the ECG.Based on the R-peak,find the R-start and R-end;and then locate the P-wave and T-wave;calculate the R-R intervals. The thesis emphasis on R-wave detection,R-R interval calculation,R-start and R-end determination.And then attempt to detect P-wave and T-wave.P and T detection is the nodus of ECG-detection.In the evaluation of the algorithm,contrast the detected data with original data,make statistical analysis,determine the accuracy of the algorithm.
心电图是心脏搏动的电位变化图。它的各种波形和间隔代表着心脏的电气特征,医生根据心电图的波形来判断心脏活动的异常,从而诊断心脏疾病,并且可以用来监测病人的身体状况,评估病情和治疗成效。因此,用计算机来分析心电图的特征波形就显得尤为重要,分析得是否准确和迅速直接关系到患者的治疗。
QRS复合波是心电图中最明显的波也是心电信号分析的基础,QRS波的定位是否准确直接关系到后续的监测。每个人的QRS波的形态有所差异,并且同一个人的QRS波也根据个人状态而表现出很大的差异性,因此,准确监测QRS波存在很大的难度。如何既能保持检测的准确性又能保证检测的时效性是很多研究人员面临的课题。
小波变换方法的出现为信号检测提供了全新的方法。小波变换具有多尺度,多分辨分析的特点,可将信号进行多尺度分解,并把不同频带的信号现实在分解的不同尺度上。这样可以根据不同信号信息所在的频带来进行具体的分析。
本文首先介绍了心电图的一些相关内容,各种波形的特点以及噪声的种类。对本实验中所使用的MIT-BIH心电数据库和小波变换的相关基础知识也作了简单的介绍。本文详细说明了使用小波变换方法对心电图进行降噪处理和特征识别。首先,对心电图进行消噪操作,尝试使用多种方法进行降噪。然后,利用三次样条小波在心电图特征点识别方面的突出优势,对心电图进行8层分解,对R波识别和定位;在此基础上,找出R波的起止点的位置;并且定位P和T波的位置;确定RR间期。本文的重点是对R波进行准确的定位,计算RR间期和确定QRS波的起止点。并在此基础上尝试对P、T波进行检测。P、T波的检测是心电图检测的难点所在。最后,在算法评估中,我们将心电图原始数据与所检测到的数据相对比,进行统计分析,评估算法的准确率。
Cardiac diseases are thought as a kind of major diseases which become more and more serious to human health.According to the Statistics of the WHO,it is about more than 1.2 million people died of Cardiac diseases,account for 25%of the total mortality. As the improving of the living standard,some unhealthy lifestyle would lead the diseases to the trend of rejuvenation.The characteristics of Cardiac diseases are:onset fast,high mortality rate,difficult to treat,expensive treatment cost.In order to overcome the danger of the diseases,early detection,diagnosis,and treatment will greatly decrease mortality rate.Family monitoring make it possible.In the family monitoring,to record the ECG conveniently and detect automatically are the most important.
Electrocardiogram is a pictorial representation of the electrical activity of heart beats.Because of the direct relationship between the ECG waveform and interval of the heart beats,it is possible that doctor can diagnose cardiac disease and monitor patient conditions from the unususal ECG waveforms.
QRS complex detection is the base of automatic analysis of ECG,which is mostly the first step of analysis and affects the following steps greatly.The difficulties of QRS detection lie in two factors:firstly,the physiological variability of QRS complex. Secondly,the various types of noises that can present in the ECG,for instance the power line noise,muscle noise,baseline drift.
Using Multriesolution wavelet Analysis decomposed the ECG signal on multiscals, different frequency-bands of the signal were showed on different scales.Analysis signals in different frequency-bands.
Based on the wavelet transform,this thesis introduces an algorithm to detect QRS complex.In particular,the quadratic spline wavelet has been adopted.The thesis first reviews wavelet transform briefly,and de-noise the ECG signal;then develops a QRS detention algorithm,which is then tested by using the MIH-BIH arrhythmia database. The result of experiments shows that the performance of models based on Quadratic
Spline Wavelet is superior,and it can detect QRS complex exactly.We use this algorithm to identify and locate the R-Wave of the ECG.Based on the R-peak,find the R-start and R-end;and then locate the P-wave and T-wave;calculate the R-R intervals. The thesis emphasis on R-wave detection,R-R interval calculation,R-start and R-end determination.And then attempt to detect P-wave and T-wave.P and T detection is the nodus of ECG-detection.In the evaluation of the algorithm,contrast the detected data with original data,make statistical analysis,determine the accuracy of the algorithm.
引文
1 M.L.Ahltorm,W.J.Tompkins.Automated High-Speed Analysis of Holter Tapes with Microcomputers.IEEE Trans.Biomed,Eng,1983,30(10):651-657
2 谢明国,聂志伟,向华,等.用小波变换结合神经网络检测ECG信号的P波.生物医学工程杂志,1999,16(3):23-26
3 Cuiweili.Detection of ECG characteristic points using wavelet transforms.IEEE Trans on BME,1995,42(1):21-28
4 J.S.Sahambi.Using wavelet transforms for ECG characterization.IEEE Eng.Med.Biol,1996,16(1):77-83
5 王超文.小波变换应用于QRS波检测的研究:[D].天津大学:2000
6 王涛.异位心搏的监测方法及心电图数据压缩技术的研究:[D].中国科技大学:1999
7 Qiuzhen Xue,Yuhen Hu,Willis J.Tompkins.A weight patern study of neural networks with ECG signal patern recognition.IEEE Engineering in Medicine&Biology Society International Conference(2015-2016),1989
8 季忠,秦树人.微弱生物医学信号特征提取的原理与实践.北京:科学出版社,2007年6月
9 F.W.Stallman,H.V.Pipberger.Automatic Recognition of Electrocardiographic Waves by Digital Computer.Circulation Research.1961.11-38
10 R.A.Dufault,A.C.Wilcox,P-Wave Detection in the Surface ECGvia the LMS Algorithm Proc.IEEE/EMBS.1987.9thConf:245-248
11 Zhu Yisheng,Nitish V.Thakor.P-Wave Detection by an Adaptive QRS-T Cancellation Technique.Proc.IEEE/EMBS.1987.9th Conf:249-252
12 J.Slocum.E.Bytom,L.McCarthy,et.al.Computer Detection of Atrioventricular Dissociation from Surface Electrocardiograms during Wide QRS Complex Tachycardias.Circulation,1985,Vol.75,No.5:1028-1036
13 F.Grilzali,G.Frangakis,et.al.Detection of the P and T Wave in an ECG Comput.&Biomed.Res,1989,Vol.22:83-91
14 I.S.N.Murthy,GS.S.Durga Prasad.Analysis of ECG from Pole-Zero Model.IEEE Trans.on BME.1992,Vol.39:No.7:741-751
15 Cuiwei Li,Chongxun Zheng,et.al.Detection of ECG Characteristic Points Using Wavelet Transforms.IEEE.Trans.on BME,1995,Vol.42,No.1:21-28
16 J.S.Sahambi,S.N.Tandon,R.K.P.Bhatt.Using Wavelet Transforms for ECG Characterization.IEEE/Eng.Med.&Biol,1997,Jan/Feb:77-83
17 谢国明等.利用小波变换法结合神经网络检测ECG信号的P波.生物医学工程学杂志,1999.16(3):320-323
1 杨红燕,蒋阅峰.基于DSP和CF卡的动态心电监护系统:[J].中国医疗器械杂志,2004,28(3):175-178
2 梁小容,万相奎,叶顺流,等.基于LINUX的嵌如式心电监护仪:[J].重庆大学学报,2004,27(10):14-17
3 巫琦.监护仪的临床应用和发展:[J].医疗装备,2004,17(3):10-12
4 Support of prevention medicine techniques with the help of telemedical monitoring 2005
5 召英俊,杨雪.便携式医疗监护仪的研制.仪器仪表学报,2005年,第25卷第8期增刊
6 许剑,卢剑刚.多参数无线医疗系统的设计与开发.研究与论著,2005年,29卷第6期
7 http//:www.xxlinux.com
8 李全利,仲伟峰,徐军.单片机原理及应刚.清华大学出版社
9 徐建军 《MCS-51系列单片机应用及接口技术》,人民邮电出版社
10 黄勇 王孝国.嵌入式开发查询手册.人民邮电出版社,2007年5月
11 王琳琳 王剑刚.基于PTR2000多参数无线监护系统的研究.医疗设备信息,2004年,19卷11期
12 李勇.基于PTR2000的体温和脉搏两生理参数监测系统的实现.中国科技信息,2005年,23期
13 黄勇 王孝国.嵌入式开发查询手册.人民邮电出版社,2007年5月
14 李小华,李雪琳,徐俊荣.基于DSP的数字助听器的研究.95年生物电子学:[C],医学传感器等联合学术会议文集.北京:1995.438-439
15 候刚,徐俊荣.用于植入式多道电子耳涡的一种数字实时语音特征分析系统的研究:[M],生物医学工程前沿,合肥:中国科技大学出版社,1993,471-476
16 严洪,宏峰,胡耄祺.航天医学与医学工程,1999年第1期第12卷
17 侯立亚,李燕峥,吴水才,张松,白燕萍.基于ARM的心电采集系统的设计.医疗卫生装备,2006年,第27卷第1期
18 赵寒星,刘涛.从51到ARM—32位嵌入式系统入门.北京航空航天大学出版社
19 http://www.arm88.com
20 蒋阅峰,扬红燕.基于ARM处理器和CF卡的动态心电监护系统.电子测量与仪器学报,2006年6月,第20卷第3期
21 http://www.publish.it168.com ARM简介及编程
22周立功,张华.深入浅出ARM7—LPC213x\214x.北京航空航天大学出版社
23唐富华,康景利,郭银景,等.基于嵌入式技术的移动医疗监护系统的研制.计算机工程与应用,2005,13:201
24杨宣兵,高潮,郭永彩,郭孝恩.基于单片机的遍携式无线家庭监护仪的设计
25周洪建,等.心电监护系统的设计.医疗卫生装备:[J].2000,(6)
26程兵,等.移动式生物电记录系统的红外无线通讯.北京生物医学工程:[J].1999,(2)
27钱志鸿,杨帆,周求湛.蓝牙技术原理开发与应用.北京航空航天大学出版社
28金纯,等.蓝牙技术.电子工业出版社
29(美)多德.通信技术导论.清华大学出版社
30李伟,吴效明.基于蓝牙技术的嵌入式多生理参数监护仪.微计算机信息(嵌入式与SOC),2006年,第22卷第1-2期
31蒋贵龙,王哈力,赵岩.基于蓝牙技术的动态心电监护系统的开发.电子科技,2006年,第12期
2 谢明国,聂志伟,向华,等.用小波变换结合神经网络检测ECG信号的P波.生物医学工程杂志,1999,16(3):23-26
3 Cuiweili.Detection of ECG characteristic points using wavelet transforms.IEEE Trans on BME,1995,42(1):21-28
4 J.S.Sahambi.Using wavelet transforms for ECG characterization.IEEE Eng.Med.Biol,1996,16(1):77-83
5 王超文.小波变换应用于QRS波检测的研究:[D].天津大学:2000
6 王涛.异位心搏的监测方法及心电图数据压缩技术的研究:[D].中国科技大学:1999
7 Qiuzhen Xue,Yuhen Hu,Willis J.Tompkins.A weight patern study of neural networks with ECG signal patern recognition.IEEE Engineering in Medicine&Biology Society International Conference(2015-2016),1989
8 季忠,秦树人.微弱生物医学信号特征提取的原理与实践.北京:科学出版社,2007年6月
9 F.W.Stallman,H.V.Pipberger.Automatic Recognition of Electrocardiographic Waves by Digital Computer.Circulation Research.1961.11-38
10 R.A.Dufault,A.C.Wilcox,P-Wave Detection in the Surface ECGvia the LMS Algorithm Proc.IEEE/EMBS.1987.9thConf:245-248
11 Zhu Yisheng,Nitish V.Thakor.P-Wave Detection by an Adaptive QRS-T Cancellation Technique.Proc.IEEE/EMBS.1987.9th Conf:249-252
12 J.Slocum.E.Bytom,L.McCarthy,et.al.Computer Detection of Atrioventricular Dissociation from Surface Electrocardiograms during Wide QRS Complex Tachycardias.Circulation,1985,Vol.75,No.5:1028-1036
13 F.Grilzali,G.Frangakis,et.al.Detection of the P and T Wave in an ECG Comput.&Biomed.Res,1989,Vol.22:83-91
14 I.S.N.Murthy,GS.S.Durga Prasad.Analysis of ECG from Pole-Zero Model.IEEE Trans.on BME.1992,Vol.39:No.7:741-751
15 Cuiwei Li,Chongxun Zheng,et.al.Detection of ECG Characteristic Points Using Wavelet Transforms.IEEE.Trans.on BME,1995,Vol.42,No.1:21-28
16 J.S.Sahambi,S.N.Tandon,R.K.P.Bhatt.Using Wavelet Transforms for ECG Characterization.IEEE/Eng.Med.&Biol,1997,Jan/Feb:77-83
17 谢国明等.利用小波变换法结合神经网络检测ECG信号的P波.生物医学工程学杂志,1999.16(3):320-323
1 杨红燕,蒋阅峰.基于DSP和CF卡的动态心电监护系统:[J].中国医疗器械杂志,2004,28(3):175-178
2 梁小容,万相奎,叶顺流,等.基于LINUX的嵌如式心电监护仪:[J].重庆大学学报,2004,27(10):14-17
3 巫琦.监护仪的临床应用和发展:[J].医疗装备,2004,17(3):10-12
4 Support of prevention medicine techniques with the help of telemedical monitoring 2005
5 召英俊,杨雪.便携式医疗监护仪的研制.仪器仪表学报,2005年,第25卷第8期增刊
6 许剑,卢剑刚.多参数无线医疗系统的设计与开发.研究与论著,2005年,29卷第6期
7 http//:www.xxlinux.com
8 李全利,仲伟峰,徐军.单片机原理及应刚.清华大学出版社
9 徐建军 《MCS-51系列单片机应用及接口技术》,人民邮电出版社
10 黄勇 王孝国.嵌入式开发查询手册.人民邮电出版社,2007年5月
11 王琳琳 王剑刚.基于PTR2000多参数无线监护系统的研究.医疗设备信息,2004年,19卷11期
12 李勇.基于PTR2000的体温和脉搏两生理参数监测系统的实现.中国科技信息,2005年,23期
13 黄勇 王孝国.嵌入式开发查询手册.人民邮电出版社,2007年5月
14 李小华,李雪琳,徐俊荣.基于DSP的数字助听器的研究.95年生物电子学:[C],医学传感器等联合学术会议文集.北京:1995.438-439
15 候刚,徐俊荣.用于植入式多道电子耳涡的一种数字实时语音特征分析系统的研究:[M],生物医学工程前沿,合肥:中国科技大学出版社,1993,471-476
16 严洪,宏峰,胡耄祺.航天医学与医学工程,1999年第1期第12卷
17 侯立亚,李燕峥,吴水才,张松,白燕萍.基于ARM的心电采集系统的设计.医疗卫生装备,2006年,第27卷第1期
18 赵寒星,刘涛.从51到ARM—32位嵌入式系统入门.北京航空航天大学出版社
19 http://www.arm88.com
20 蒋阅峰,扬红燕.基于ARM处理器和CF卡的动态心电监护系统.电子测量与仪器学报,2006年6月,第20卷第3期
21 http://www.publish.it168.com ARM简介及编程
22周立功,张华.深入浅出ARM7—LPC213x\214x.北京航空航天大学出版社
23唐富华,康景利,郭银景,等.基于嵌入式技术的移动医疗监护系统的研制.计算机工程与应用,2005,13:201
24杨宣兵,高潮,郭永彩,郭孝恩.基于单片机的遍携式无线家庭监护仪的设计
25周洪建,等.心电监护系统的设计.医疗卫生装备:[J].2000,(6)
26程兵,等.移动式生物电记录系统的红外无线通讯.北京生物医学工程:[J].1999,(2)
27钱志鸿,杨帆,周求湛.蓝牙技术原理开发与应用.北京航空航天大学出版社
28金纯,等.蓝牙技术.电子工业出版社
29(美)多德.通信技术导论.清华大学出版社
30李伟,吴效明.基于蓝牙技术的嵌入式多生理参数监护仪.微计算机信息(嵌入式与SOC),2006年,第22卷第1-2期
31蒋贵龙,王哈力,赵岩.基于蓝牙技术的动态心电监护系统的开发.电子科技,2006年,第12期