基于深度學(xué)習(xí)的心電信號(hào)降噪和T波自動(dòng)檢測(cè)研究
發(fā)布時(shí)間：2018-12-15 16:47
【摘要】：心臟性猝死具有突發(fā)性、高發(fā)病率和高致死率的特點(diǎn),是心血管領(lǐng)域關(guān)注的熱點(diǎn)問(wèn)題。在遠(yuǎn)程醫(yī)療背景下,動(dòng)態(tài)心電監(jiān)護(hù)是心臟性猝死預(yù)測(cè)的有效方法。心臟性猝死發(fā)生前,動(dòng)態(tài)心電圖的Q-T形態(tài)和間期時(shí)常伴有異常改變,從而使Q-T段的識(shí)別和分析成為了心臟性猝死早期預(yù)測(cè)的關(guān)鍵。其中T波信號(hào)微弱,易受噪聲干擾,而且形態(tài)多變,因此在遠(yuǎn)程醫(yī)療背景下心臟性猝死預(yù)測(cè)的研究中,心電信號(hào)降噪和T波檢測(cè)逐漸成為研究的重點(diǎn)和難點(diǎn)。本文考慮人體個(gè)體差異特征,以及遠(yuǎn)程醫(yī)療背景下信號(hào)噪聲多、干擾大等因素,利用遠(yuǎn)程醫(yī)療背景下心電信號(hào)具有大數(shù)據(jù)特征的優(yōu)勢(shì),引入深度學(xué)習(xí),研究心電信號(hào)降噪和T波自動(dòng)檢測(cè)算法。主要工作如下:(1)心電信號(hào)中部分噪聲的頻譜和主要信號(hào)頻譜存在重疊現(xiàn)象,傳統(tǒng)的降噪方法很難將其濾除干凈。為此,本文利用遠(yuǎn)程醫(yī)療背景下心電信號(hào)具有大數(shù)據(jù)特征的優(yōu)勢(shì),提出了基于降噪自動(dòng)編碼器構(gòu)建深度神經(jīng)網(wǎng)絡(luò)的心電信號(hào)降噪算法。通過(guò)堆疊多個(gè)降噪自動(dòng)編碼器,可以抽象輸入信號(hào)的深層次特征。利用降噪自動(dòng)編碼器提取信號(hào)魯棒性特征的能力,完成從含噪聲信號(hào)中重構(gòu)原始信號(hào)的得任務(wù)�；谛碾娦盘�(hào)之間的相似性構(gòu)建訓(xùn)練數(shù)據(jù),調(diào)整網(wǎng)絡(luò)參數(shù),使得構(gòu)建的神經(jīng)網(wǎng)絡(luò)完成心電信號(hào)降噪。(2)針對(duì)基于降噪自動(dòng)編碼器的心電信號(hào)降噪算法中,部分降噪信中含有的鋸齒狀噪聲殘留情況,采用小波自適應(yīng)閾值和壓縮降噪自動(dòng)編碼器優(yōu)化降噪模型。通過(guò)在損失函數(shù)中增加隱含層輸出信號(hào)對(duì)輸入信號(hào)雅可比矩陣的Frobenius范數(shù)平方項(xiàng),來(lái)抑制網(wǎng)絡(luò)隱含層過(guò)大變動(dòng)對(duì)輸出的影響,從而提高了網(wǎng)絡(luò)降噪的性能。同時(shí),小波自適應(yīng)閾值法濾除部分噪聲,使得較低的樣本維度可以包含盡量全面的信號(hào)和噪聲特征,進(jìn)而降低網(wǎng)絡(luò)各層的節(jié)點(diǎn)數(shù),簡(jiǎn)化算法的計(jì)算復(fù)雜度。(3)現(xiàn)有T波檢測(cè)算法中,T波形態(tài)檢測(cè)和特征點(diǎn)檢測(cè)之間是互相影響的,如果得知T波形態(tài)就可以提高T波的關(guān)鍵特征點(diǎn)檢測(cè)精度,但是不知道T波關(guān)鍵特征點(diǎn)的信息又無(wú)法判斷T波形態(tài)。為了解決T波形態(tài)檢測(cè)和特征點(diǎn)檢測(cè)之間的矛盾關(guān)系,本文考慮人體作為復(fù)雜的生物體具有個(gè)體差異的基本特征,提出了基于形態(tài)指導(dǎo)的T波自動(dòng)檢測(cè)算法,采用稀疏自動(dòng)編碼器提取T波形態(tài)特征,并將其分為單峰直立、單峰倒置、負(fù)正雙向和正負(fù)雙向四種類型。隨后,根據(jù)每一類T波形態(tài)的特征,采用傾斜高斯函數(shù)進(jìn)行數(shù)學(xué)建模。通過(guò)分析模板和T波段的相關(guān)性,實(shí)現(xiàn)T波的特征點(diǎn)檢測(cè)。為了驗(yàn)證本文的研究成果,將所提的心電信號(hào)降噪算法和T波自動(dòng)檢測(cè)算法應(yīng)用于所在科研團(tuán)隊(duì)自主研發(fā)的智慧心電監(jiān)測(cè)平臺(tái)中。經(jīng)過(guò)實(shí)際采集的心電信號(hào)測(cè)試表明,本文提出的心電信號(hào)降噪算法可以在濾除復(fù)雜噪聲的同時(shí)保持心電信號(hào)的主要特征波形。并且,本文提出的基于形態(tài)指導(dǎo)的傾斜高斯模板算法,實(shí)現(xiàn)了自動(dòng)檢測(cè)T波峰值和終點(diǎn)值。研究成果大大提高了遠(yuǎn)程醫(yī)療環(huán)境下心電監(jiān)測(cè)系統(tǒng)的智能性。
[Abstract]:Sudden, high and high incidence of sudden cardiac death is a hot issue in the field of cardiovascular attention. In the remote medical background, dynamic ECG monitoring is an effective method of the prediction of sudden cardiac death. Before the occurrence of sudden cardiac death, the Q-T shape and interval of the dynamic electrocardiogram are often accompanied by abnormal changes, so that the identification and analysis of the Q-T segment is the key to the early prediction of sudden cardiac death. In the research of the prediction of sudden cardiac death in the remote medical background, the noise reduction and T-wave detection of the cardiac electrical signal are becoming the focus and the difficulty of the research. In this paper, the characteristics of human individual difference and the multiple factors of signal noise and large interference in the background of remote medical treatment are considered. In this paper, the advantage of the high data characteristic of the ECG signal under the background of remote medical care is used, and the depth study is introduced to study the noise reduction and T-wave automatic detection algorithm of the cardiac electrical signal. The main work is as follows: (1) The spectrum of some noise in the ECG signal and the main signal spectrum are overlapped, and the traditional noise reduction method is difficult to filter out. In this paper, based on the advantage of the high data characteristic of the ECG signal in the remote medical background, this paper puts forward the noise reduction algorithm of the ECG signal based on the noise reduction automatic encoder to construct the depth neural network. By stacking a plurality of noise reduction automatic encoders, the deep-level features of the input signal can be abstracted. The ability of the noise reduction automatic encoder to extract the robust feature of the signal is utilized to complete the task of reconstructing the original signal from the noise-containing signal. The training data is constructed based on the similarity between the electrocardiosignals and the network parameters are adjusted, so that the constructed neural network completes the noise reduction of the electrocardiosignal. (2) In the noise reduction algorithm of the ECG signal based on the noise reduction automatic encoder, the noise residual condition of the saw-tooth noise contained in the partial noise reduction signal is optimized, and a small-wave adaptive threshold and a compression noise reduction automatic coder are adopted to optimize the noise reduction model. By adding the implicit layer output signal to the Frobenius norm square of the input signal Jacobian matrix in the loss function, the influence of the over-large fluctuation on the output of the network hidden layer is suppressed, and the performance of the network noise reduction is improved. At the same time, the small-wave adaptive threshold method filters out some of the noise, so that the lower sample dimension can contain as much as possible signal and noise characteristics as much as possible, thus reducing the number of nodes of each layer of the network and simplifying the calculation complexity of the algorithm. (3) In the existing T-wave detection algorithm, the T-wave shape detection and the characteristic point detection are mutually affected, and if the T-wave form is known, the detection accuracy of the key characteristic points of the T-wave can be improved, but the T-wave shape cannot be judged by knowing the information of the key characteristic point of the T-wave. In order to solve the contradiction between T-wave shape detection and feature point detection, this paper takes into consideration the basic characteristics of human body as a complex organism, and puts forward a T-wave automatic detection algorithm based on morphological guidance. It can be divided into unimodal, unimodal, negative and positive two-way and positive and negative two-way. Then, according to the characteristics of each class of T-wave shape, the oblique Gaussian function is used for mathematical modeling. By analyzing the correlation between the template and the T-band, the feature point detection of the T-wave is realized. In order to verify the research results in this paper, the proposed method of ECG signal reduction and T-wave automatic detection is applied to the intelligent ECG monitoring platform developed by the research team. The results of the real-time ECG signal show that the noise reduction algorithm proposed in this paper can keep the main characteristic waveform of the ECG signal while the complex noise is filtered out. In addition, based on the form-based oblique Gaussian template algorithm, the T-wave peak value and the end-point value are automatically detected. The research results have greatly improved the intelligence of the ECG monitoring system in the remote medical environment.
【學(xué)位授予單位】：燕山大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：R540.4;TN911.4
[Abstract]:Sudden, high and high incidence of sudden cardiac death is a hot issue in the field of cardiovascular attention. In the remote medical background, dynamic ECG monitoring is an effective method of the prediction of sudden cardiac death. Before the occurrence of sudden cardiac death, the Q-T shape and interval of the dynamic electrocardiogram are often accompanied by abnormal changes, so that the identification and analysis of the Q-T segment is the key to the early prediction of sudden cardiac death. In the research of the prediction of sudden cardiac death in the remote medical background, the noise reduction and T-wave detection of the cardiac electrical signal are becoming the focus and the difficulty of the research. In this paper, the characteristics of human individual difference and the multiple factors of signal noise and large interference in the background of remote medical treatment are considered. In this paper, the advantage of the high data characteristic of the ECG signal under the background of remote medical care is used, and the depth study is introduced to study the noise reduction and T-wave automatic detection algorithm of the cardiac electrical signal. The main work is as follows: (1) The spectrum of some noise in the ECG signal and the main signal spectrum are overlapped, and the traditional noise reduction method is difficult to filter out. In this paper, based on the advantage of the high data characteristic of the ECG signal in the remote medical background, this paper puts forward the noise reduction algorithm of the ECG signal based on the noise reduction automatic encoder to construct the depth neural network. By stacking a plurality of noise reduction automatic encoders, the deep-level features of the input signal can be abstracted. The ability of the noise reduction automatic encoder to extract the robust feature of the signal is utilized to complete the task of reconstructing the original signal from the noise-containing signal. The training data is constructed based on the similarity between the electrocardiosignals and the network parameters are adjusted, so that the constructed neural network completes the noise reduction of the electrocardiosignal. (2) In the noise reduction algorithm of the ECG signal based on the noise reduction automatic encoder, the noise residual condition of the saw-tooth noise contained in the partial noise reduction signal is optimized, and a small-wave adaptive threshold and a compression noise reduction automatic coder are adopted to optimize the noise reduction model. By adding the implicit layer output signal to the Frobenius norm square of the input signal Jacobian matrix in the loss function, the influence of the over-large fluctuation on the output of the network hidden layer is suppressed, and the performance of the network noise reduction is improved. At the same time, the small-wave adaptive threshold method filters out some of the noise, so that the lower sample dimension can contain as much as possible signal and noise characteristics as much as possible, thus reducing the number of nodes of each layer of the network and simplifying the calculation complexity of the algorithm. (3) In the existing T-wave detection algorithm, the T-wave shape detection and the characteristic point detection are mutually affected, and if the T-wave form is known, the detection accuracy of the key characteristic points of the T-wave can be improved, but the T-wave shape cannot be judged by knowing the information of the key characteristic point of the T-wave. In order to solve the contradiction between T-wave shape detection and feature point detection, this paper takes into consideration the basic characteristics of human body as a complex organism, and puts forward a T-wave automatic detection algorithm based on morphological guidance. It can be divided into unimodal, unimodal, negative and positive two-way and positive and negative two-way. Then, according to the characteristics of each class of T-wave shape, the oblique Gaussian function is used for mathematical modeling. By analyzing the correlation between the template and the T-band, the feature point detection of the T-wave is realized. In order to verify the research results in this paper, the proposed method of ECG signal reduction and T-wave automatic detection is applied to the intelligent ECG monitoring platform developed by the research team. The results of the real-time ECG signal show that the noise reduction algorithm proposed in this paper can keep the main characteristic waveform of the ECG signal while the complex noise is filtered out. In addition, based on the form-based oblique Gaussian template algorithm, the T-wave peak value and the end-point value are automatically detected. The research results have greatly improved the intelligence of the ECG monitoring system in the remote medical environment.
【學(xué)位授予單位】：燕山大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：R540.4;TN911.4
【相似文獻(xiàn)】
相關(guān)會(huì)議論文 前5條
1 王s，
本文編號(hào)：2380983
本文鏈接：http://sikaile.net/yixuelunwen/xxg/2380983.html
最近更新
教材專著
