心電信號(hào)的檢測(cè)與模式分類方法的研究
發(fā)布時(shí)間：2018-08-05 18:19
【摘要】：心電信號(hào)是一種低頻、微弱的生物電信號(hào),它客觀地反映了心臟的工作狀態(tài),其蘊(yùn)涵著心臟的生理、病理信息對(duì)心臟疾病的診斷具有重要的參考價(jià)值。由于心電信號(hào)的幅值較小,頻率較低,對(duì)信號(hào)進(jìn)行檢測(cè)時(shí)易受外界環(huán)境的干擾。有些干擾信號(hào)頻率高,幅值大,往往會(huì)掩蓋正常的心電信號(hào),使心電波形無法識(shí)別。此外,心臟病患者的心電波形因病情而異,只有通過對(duì)心電信號(hào)的特征波形加以檢測(cè)和分析,才可以診斷相應(yīng)的心臟疾病。目前,心率失常疾病的診斷主要依靠醫(yī)生的心臟醫(yī)學(xué)知識(shí)和臨床工作經(jīng)驗(yàn),由于心電數(shù)據(jù)量較大且異常波形并不連續(xù)出現(xiàn),如果從事大量心電波形識(shí)別工作,易產(chǎn)生疲勞從而造成錯(cuò)判和誤判而耽誤患者的病情。因此,如何濾除心電信號(hào)中的各種干擾,對(duì)心電信號(hào)的特征信息加以提取及對(duì)各種不同的心電數(shù)據(jù)進(jìn)行分類是心電醫(yī)學(xué)界研究的重點(diǎn)。本文主要從以下四個(gè)方面進(jìn)行研究： (1)針對(duì)心電信號(hào)的產(chǎn)生機(jī)理和特點(diǎn),通過設(shè)計(jì)前置放大電路,右腿驅(qū)動(dòng)電路對(duì)心電信號(hào)加以采集。針對(duì)采集過程中的噪聲,設(shè)計(jì)相應(yīng)的濾波器組,并對(duì)濾波后心電信號(hào)的進(jìn)行放大。通過A/D轉(zhuǎn)換電路、按鍵電路、串口通信電路、LCD顯示電路和數(shù)據(jù)存儲(chǔ)電路對(duì)心電信號(hào)進(jìn)行轉(zhuǎn)換存儲(chǔ)、顯示并與PC機(jī)進(jìn)行通信。 (2)對(duì)于硬件電路中所不能濾除的噪聲,對(duì)其特性進(jìn)行分析,并設(shè)計(jì)了小波閾值去噪數(shù)字濾波器、固定步長LMS自適應(yīng)去噪數(shù)字濾波器、可變步長LMS自適應(yīng)去噪數(shù)字濾波器及RLS自適應(yīng)去噪數(shù)字濾波器對(duì)干擾信號(hào)再次濾除。通過在MIT-BIH心率失常數(shù)據(jù)庫中第101號(hào)心電數(shù)據(jù)加入三種干擾信號(hào)基線漂移,肌電干擾,工頻干擾進(jìn)行仿真實(shí)驗(yàn),再對(duì)四種濾波器從去噪后圖形和去噪性能參數(shù)對(duì)比可知,RLS自適應(yīng)去噪數(shù)字濾波器的濾波效果明顯優(yōu)于其他三種濾波器。 (3)為了方便心電信號(hào)特征信息的提取,提出了一種基于二次樣條母小波函數(shù)的心電信號(hào)QRS復(fù)合波檢測(cè)算法。采用二次樣條小波函數(shù)對(duì)心電信號(hào)作4尺度分解,分別獲取各個(gè)尺度下的小波系數(shù),在尺度3下,通過一定的閾值搜索小波系數(shù)模極大值對(duì)之間的過零點(diǎn),確定R波位置。通過調(diào)整閾值以刪除誤檢點(diǎn),補(bǔ)償漏檢點(diǎn),從而提高對(duì)R波的檢測(cè)率。再從尺度1上R波過零點(diǎn)前后尋找局部模極大值對(duì),分別確定QRS復(fù)合波的Q波,S波及QRS復(fù)合波起始位置和終止位置。通過MIT-BIH心率失常數(shù)據(jù)庫中的心電數(shù)據(jù)對(duì)本文算法進(jìn)行驗(yàn)證,并與其他QRS復(fù)合波檢測(cè)算法相對(duì)比。結(jié)果表明本文算法對(duì)QRS復(fù)合波檢測(cè)具有較高的準(zhǔn)確率。 (4)設(shè)計(jì)了多種分類器對(duì)不同類別的心電信號(hào)加以分類。由于心電樣本數(shù)據(jù)過于冗多,因此采用主成分分析法(PCA),線性判別法(LDA)以及主成分分析與線性判別融合法(PCA-LDA)對(duì)數(shù)據(jù)進(jìn)行降維。實(shí)驗(yàn)證明線性判別法降維效果明顯優(yōu)于其他兩種方法。接著設(shè)計(jì)了支持向量機(jī)(SVM),最小二乘支持向量機(jī)(LS-SVM),極限學(xué)習(xí)機(jī)(ELM)三種分類器,并分別以交叉驗(yàn)證法、遺傳算法(GA)及粒子群算法(PSO)對(duì)支持向量機(jī),最小二乘支持向量機(jī)的控制參數(shù)進(jìn)行優(yōu)化。最后通過實(shí)例對(duì)三種分類器的性能進(jìn)行評(píng)價(jià),結(jié)果表明：支持向量機(jī)分類精度最高,而極限學(xué)習(xí)機(jī)訓(xùn)練和測(cè)試時(shí)間最短。
[Abstract]:ECG signal is a low frequency, weak bioelectrical signal, which objectively reflects the working state of the heart. It contains the physiology of the heart. The pathological information has important reference value for the diagnosis of heart disease. Because the amplitude of the ECG signal is small and the frequency is low, it is easy to be disturbed by the external environment when the signal is detected. Some interference is disturbed. The signal frequency is high and the amplitude is large. It often covers the normal ECG signal and makes the heart wave shape unable to identify. In addition, the heart wave shape of heart disease patients varies according to the condition. Only through the detection and analysis of the characteristic waveform of the ECG signal, the corresponding heart disease can be diagnosed. At present, the diagnosis of the arrhythmia disease is mainly depended on the doctor. The heart medical knowledge and clinical experience, due to the large amount of ECG data and abnormal waveform is not continuous, if a large number of ECG waveform identification work, easy to cause fatigue and misjudge and delay the patient's condition. Therefore, how to filter all kinds of interference in the ECG signal and add the characteristic information to the ECG signal To extract and classify various ECG data is the focus of ECG medical research. This paper mainly studies from the following four aspects:
(1) in view of the mechanism and characteristics of the generation of ECG signal, the right leg drive circuit is designed to collect the ECG signal by designing the preamplifier circuit, and the corresponding filter bank is designed for the noise in the acquisition process, and the ECG signal after the filter is amplified. The A/D circuit, the key circuit, the serial communication circuit, the LCD display circuit and the display circuit are used. The data storage circuit converts and stores ECG signals, displays and communicates with PC.
(2) for the noise that can not be filtered in the hardware circuit, the characteristics are analyzed, and the wavelet threshold denoising digital filter is designed, the LMS adaptive de-noising digital filter is fixed, the variable step length LMS adaptive denoising digital filter and the RLS adaptive denoising digital filter are used to filter the interference signal again. The heart rate is passed in the heart rate. The number 101st ECG data in the abnormal database is added to the baseline drift of three kinds of interference signals, EMI and frequency interference, and then the comparison of the figure and the denoising performance parameters of the four filters from the denoising shows that the filtering effect of the RLS adaptive denoising digital filter is obviously better than the other three kinds of filter.
(3) in order to facilitate the extraction of the feature information of the ECG signal, a QRS composite wave detection algorithm based on the two spline mother wavelet function is proposed. The wavelet coefficients of each scale are obtained by using the two spline wavelet function to decompose ECG signals in 4 scales, and the wavelet coefficients are searched by a certain threshold in the scale 3. The R wave position is determined by the zero crossing point between the maximum value. The detection rate of the R wave is improved by adjusting the threshold to delete the false detection point and compensating the leakage point. Then the local modulus maximum value is found before and after the R wave over zero on the scale 1, and the Q wave of the QRS complex wave, the S wave and the starting position and the termination position of the QRS compound wave are respectively determined. The heart rate is lost through MIT-BIH. The ECG data in the normal database are verified by this algorithm and compared with other QRS complex wave detection algorithms. The results show that the proposed algorithm has a high accuracy for the QRS composite wave detection.
(4) a variety of classifiers are designed to classify different types of ECG signals. Because the data of ECG samples are too redundant, the main component analysis (PCA), linear discriminant (LDA), principal component analysis and linear discriminant fusion (PCA-LDA) are used to reduce the data. The experimental results show that the linear discriminant method is better than the other two. Then we design three classifiers for support vector machine (SVM), least squares support vector machine (LS-SVM) and limit learning machine (ELM), and optimize the control parameters of support vector machine and least squares support machine by cross validation, genetic algorithm (GA) and particle swarm optimization (PSO). Finally, three classifiers are selected by an example. Performance evaluation shows that the support vector machine classification accuracy is the highest, while the extreme learning machine training and testing time is the shortest.
【學(xué)位授予單位】：浙江師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN911.23
本文編號(hào)：2166603
[Abstract]:ECG signal is a low frequency, weak bioelectrical signal, which objectively reflects the working state of the heart. It contains the physiology of the heart. The pathological information has important reference value for the diagnosis of heart disease. Because the amplitude of the ECG signal is small and the frequency is low, it is easy to be disturbed by the external environment when the signal is detected. Some interference is disturbed. The signal frequency is high and the amplitude is large. It often covers the normal ECG signal and makes the heart wave shape unable to identify. In addition, the heart wave shape of heart disease patients varies according to the condition. Only through the detection and analysis of the characteristic waveform of the ECG signal, the corresponding heart disease can be diagnosed. At present, the diagnosis of the arrhythmia disease is mainly depended on the doctor. The heart medical knowledge and clinical experience, due to the large amount of ECG data and abnormal waveform is not continuous, if a large number of ECG waveform identification work, easy to cause fatigue and misjudge and delay the patient's condition. Therefore, how to filter all kinds of interference in the ECG signal and add the characteristic information to the ECG signal To extract and classify various ECG data is the focus of ECG medical research. This paper mainly studies from the following four aspects:
(1) in view of the mechanism and characteristics of the generation of ECG signal, the right leg drive circuit is designed to collect the ECG signal by designing the preamplifier circuit, and the corresponding filter bank is designed for the noise in the acquisition process, and the ECG signal after the filter is amplified. The A/D circuit, the key circuit, the serial communication circuit, the LCD display circuit and the display circuit are used. The data storage circuit converts and stores ECG signals, displays and communicates with PC.
(2) for the noise that can not be filtered in the hardware circuit, the characteristics are analyzed, and the wavelet threshold denoising digital filter is designed, the LMS adaptive de-noising digital filter is fixed, the variable step length LMS adaptive denoising digital filter and the RLS adaptive denoising digital filter are used to filter the interference signal again. The heart rate is passed in the heart rate. The number 101st ECG data in the abnormal database is added to the baseline drift of three kinds of interference signals, EMI and frequency interference, and then the comparison of the figure and the denoising performance parameters of the four filters from the denoising shows that the filtering effect of the RLS adaptive denoising digital filter is obviously better than the other three kinds of filter.
(3) in order to facilitate the extraction of the feature information of the ECG signal, a QRS composite wave detection algorithm based on the two spline mother wavelet function is proposed. The wavelet coefficients of each scale are obtained by using the two spline wavelet function to decompose ECG signals in 4 scales, and the wavelet coefficients are searched by a certain threshold in the scale 3. The R wave position is determined by the zero crossing point between the maximum value. The detection rate of the R wave is improved by adjusting the threshold to delete the false detection point and compensating the leakage point. Then the local modulus maximum value is found before and after the R wave over zero on the scale 1, and the Q wave of the QRS complex wave, the S wave and the starting position and the termination position of the QRS compound wave are respectively determined. The heart rate is lost through MIT-BIH. The ECG data in the normal database are verified by this algorithm and compared with other QRS complex wave detection algorithms. The results show that the proposed algorithm has a high accuracy for the QRS composite wave detection.
(4) a variety of classifiers are designed to classify different types of ECG signals. Because the data of ECG samples are too redundant, the main component analysis (PCA), linear discriminant (LDA), principal component analysis and linear discriminant fusion (PCA-LDA) are used to reduce the data. The experimental results show that the linear discriminant method is better than the other two. Then we design three classifiers for support vector machine (SVM), least squares support vector machine (LS-SVM) and limit learning machine (ELM), and optimize the control parameters of support vector machine and least squares support machine by cross validation, genetic algorithm (GA) and particle swarm optimization (PSO). Finally, three classifiers are selected by an example. Performance evaluation shows that the support vector machine classification accuracy is the highest, while the extreme learning machine training and testing time is the shortest.
【學(xué)位授予單位】：浙江師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN911.23
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 李方偉;張浩;;一種新的變步長LMS自適應(yīng)濾波算法及其仿真[J];重慶郵電大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年05期
2 姚成;司玉娟;郎六琪;韓松洋;;改進(jìn)的基于小波變換的QRS波檢測(cè)算法[J];吉林大學(xué)學(xué)報(bào)(信息科學(xué)版);2011年05期
3 殷文錚;杜旭;;基于簡(jiǎn)化型RLS算法的延遲改進(jìn)型噪聲抵消系統(tǒng)模型與實(shí)現(xiàn)[J];電聲技術(shù);2006年02期
4 袁海洋;何敏;王威廉;;DWA:一種新的心電實(shí)時(shí)檢測(cè)算法[J];電子測(cè)量與儀器學(xué)報(bào);2009年09期
5 何國輝;甘俊英;;PCA-LDA算法在性別鑒別中的應(yīng)用[J];計(jì)算機(jī)工程;2006年19期
6 童佳斐;董軍;;分類器組合在心電圖分類中的應(yīng)用[J];計(jì)算機(jī)應(yīng)用;2010年04期
7 劉學(xué)勝;;基于PCA和SVM算法的人臉識(shí)別[J];計(jì)算機(jī)與數(shù)字工程;2011年07期
8 李巍華,廖廣蘭,史鐵林;核函數(shù)主元分析及其在齒輪故障診斷中的應(yīng)用[J];機(jī)械工程學(xué)報(bào);2003年08期
9 唐發(fā)明,王仲東,陳綿云;支持向量機(jī)多類分類算法研究[J];控制與決策;2005年07期
10 趙薔;宋笑雪;郭新明;李紅;;一種基于PCA-LDA的衛(wèi)星遙感圖像的分類方法[J];計(jì)算機(jī)應(yīng)用與軟件;2013年02期
，本文編號(hào)：2166603
本文鏈接：http://sikaile.net/kejilunwen/wltx/2166603.html
最近更新
教材專著
