技术领域technical field
本发明涉及一种获取心音信号源成分的方法，特别涉及一种利用同步采集的四通道心音来获取心音信号源成分的获取方法。The invention relates to a method for acquiring heart sound signal source components, in particular to an acquisition method for acquiring heart sound signal source components by using synchronously collected four-channel heart sound.
背景技术Background technique
心音信号携带着人体心脏活动重要的生理信息，如心率、心律、心房、心室和心脏瓣膜的运动和功能状态等。随着科技的进步，心音听诊开始由传统心音听诊转向智能心音听诊，所谓心音智能听诊即利用电子设备把心音信号转化成电信号来处理，从“信号”的角度来获取和进一步分析心音信号的各种特征，从而达到听诊的目的。心音信号具有极高的医学价值，获得的心音信号应尽可能多地保留心音的全部信息，失真越小越好。实际上，在体表所采集的心音信号并不是心脏对应的哪些原始心音成分，而是心音各种成分的混合物，心音从产生及到达体表，经历了一个复杂的传播过程。获取心音的原始成分将是一项非常有意义的工作，其优越性在于能够有效、无损地包含心脏的各种信息，是心音发生源定位的重要基础。Heart sound signals carry important physiological information of human heart activity, such as heart rate, heart rhythm, movement and functional status of atria, ventricles and heart valves. With the advancement of science and technology, heart sound auscultation began to shift from traditional heart sound auscultation to intelligent heart sound auscultation. The so-called intelligent heart sound auscultation uses electronic equipment to convert heart sound signals into electrical signals for processing, and obtains and further analyzes heart sound signals from the perspective of "signals". Various features, so as to achieve the purpose of auscultation. The heart sound signal has extremely high medical value, and the obtained heart sound signal should retain all the information of the heart sound as much as possible, and the smaller the distortion, the better. In fact, the heart sound signal collected on the body surface is not the original heart sound components corresponding to the heart, but a mixture of various components of the heart sound. The heart sound has experienced a complex propagation process from its generation to the body surface. Obtaining the original components of heart sounds will be a very meaningful work. Its advantage is that it can effectively and non-destructively contain various information of the heart, which is an important basis for locating the source of heart sounds.
国内外关于心音信号原始成分的获取研究不多，但可以分为两类：一是将微型传感器直接插入心脏内部来采集心音，这种获取心音的方法难度高、风险大，因而只从动物身上获取了心音的原始成分；二是利用盲源分离即独立成分分析的方法来获取心音原始成分，但只能获得心音的部分原始成分。因此，我们需要一种获取方法简单、风险小且获取的心音信号不失真的心音信号源成分获取方法。There are not many studies on the acquisition of the original components of the heart sound signal at home and abroad, but they can be divided into two categories: one is to directly insert the micro sensor into the heart to collect the heart sound. The original components of the heart sound are obtained; the second is to use the method of blind source separation or independent component analysis to obtain the original components of the heart sound, but only part of the original components of the heart sound can be obtained. Therefore, we need a heart sound signal source component acquisition method with simple acquisition method, low risk and no distortion of the acquired heart sound signal.
发明内容Contents of the invention
发明目的：本发明提出了一种利用同步采集多通道心音来获取成分单一、不失真的心音信号源成分的方法。Purpose of the invention: The present invention proposes a method for acquiring heart sound signal source components with a single component and without distortion by synchronously collecting multi-channel heart sounds.
技术方案：本发明所述的获取心音信号源成分的方法，包括以下步骤：Technical solution: The method for obtaining heart sound signal source components according to the present invention comprises the following steps:
(1)通过多通道同步采集n路心音信号；(1) Collect n-channel heart sound signals synchronously through multiple channels;
(2)对n路心音信号进行去噪和分段处理；(2) denoising and segmentation processing are carried out to n road heart sound signals;
(3)构建心音信号在胸腔内部传递过程的数学模型；(3) Construct the mathematical model of heart sound signal transmission process inside the thorax;
(4)基于四阶累积量算法获取心音信号源成分。(4) Obtain the heart sound signal source components based on the fourth-order cumulant algorithm.
步骤(1)所述的n路心音信号主要包括主动脉瓣心音信号、肺动脉瓣心音信号、二尖瓣心音信号、三尖瓣心音信号。The n-channel heart sound signals in step (1) mainly include aortic valve heart sound signals, pulmonary valve heart sound signals, mitral valve heart sound signals, and tricuspid valve heart sound signals.
步骤(2)所述的分段处理主要分为心音S1和心音S2两段。期中心音S1分为心肌收缩、心脏瓣膜关闭、血液撞击心室壁及血液撞击大动脉壁4个源成分；心音S2分为主动脉瓣关闭和肺动脉瓣关闭2个源成分。The segmentation processing described in step (2) is mainly divided into two segments of heart sound S1 and heart sound S2 . Heart soundS1 is divided into four source components: myocardial contraction, heart valve closure, blood impingement on ventricular wall, and blood impingement on aortic wall; heart soundS2 is divided into two source components: aortic valve closure and pulmonary valve closure.
步骤(3)所述的数学模型由以下公式获得：The described mathematical model of step (3) obtains by following formula:
其中，aij为心音在胸腔内部的传递过程中的混叠系数，wij为心音在胸腔内部的传递过程中的回声系数；Among them, aij is the aliasing coefficient in the transmission process of the heart sound in the thoracic cavity, and wij is the echo coefficient in the transmission process of the heart sound in the thoracic cavity;
写成矩阵形式为：Written in matrix form as:
Y＝AX+WYY=AX+WY
即：which is:
Y＝(I-W)-1AX＝BXY=(IW)-1 AX=BX
其中,B＝(I-W)-1。Among them, B=(IW)-1 .
所述步骤(4)包括以下步骤：Described step (4) comprises the following steps:
(41)将观测信号Y进行球化处理，计算球化矩阵W：(41) Perform spherical processing on the observed signal Y, and calculate the spherical matrix W:
令C＝YYT＝UΛUT，C为Y的协方差阵，有：Let C=YYT ＝UΛUT , C is the covariance matrix of Y, there are:
其中，球化矩阵Among them, the spherical matrix
(43)计算Z的四维累计量矩阵QZ(M)：(43) Calculate the four-dimensional cumulant matrix QZ (M) of Z:
设M为任意4×4矩阵，则：Let M be any 4×4 matrix, then:
(44)求“混合—球化”矩阵：(44) Find the "mixing-spherification" matrix:
令V＝WB，则有：Let V=WB, then:
VVT＝VTV＝I4VVT = VT V = I4
其中V＝[v1,v2,v3,v4]，vm＝[vm1,vm2,vm3,vm4]T，where V = [v1 , v2 , v3 , v4 ], vm = [vm1 , vm2 , vm3 , vm4 ]T ,
则有：Then there are:
Qz(M)＝λMQz (M) = λM
即：which is:
[Qz(M)]ij＝λMij[Qz (M)]ij = λMij
式中λ＝k4(xm)是心音源成分的峰度，M称为Qz(M)的特征矩阵In the formula, λ=k4 (xm ) is the kurtosis of the heart sound source component, and M is called the characteristic matrix of Qz (M)
Qz(M)是对角阵，即满足：Qz (M) is a diagonal matrix, which satisfies:
Qij＝QjiQij =Qji
而and
Qz(m)＝k4(xm)MQz (m) = k4 (xm )M
(44)求解估计矩阵，获得心音信号的源成分：(44) Solve the estimated matrix to obtain the source components of the heart sound signal:
用V阵对Qz(M)作二次型处理将得到对角阵Λ(M)，则可以求得矩阵B的估计矩阵即：Quadratic processing of Qz (M) with V matrix will result in diagonal matrix Λ(M), then the estimated matrix of matrix B can be obtained which is:
则估计系统C为:Then the estimated system C is:
则：but:
有益效果：与现有技术相比，本发明的有益效果：1、与以往单通道心音采集相比较，利用多通道同步获取的心音信号具有明显优势，不仅包含有心音信号的生理信息，也可以包含心音产生的位置信息以及各通道信号之间的相互关系的信息；2、以心音发声特点为出发点，结合心音传播的模型，利用心音信号分时发生的特点，将第一心音S1分解成4个源成分进行表述，第二心音S2分解成2个源成分进行表述，成功获得成分较单一的心音信号源成分，有利于对心音信号进行深入分析、解释和分类，并最终应用到临床实际和进一步的科学研究。Beneficial effects: Compared with the prior art, the beneficial effects of the present invention: 1. Compared with the previous single-channel heart sound collection, the use of multi-channel synchronously acquired heart sound signals has obvious advantages, not only including the physiological information of the heart sound signals, but also Contains the position information of heart sound generation and the information of the relationship between the signals of each channel; 2. Taking the characteristics of heart sound as the starting point, combined with the model of heart sound propagation, and using the characteristics of time-sharing of heart sound signals, the first heart sound S1 is decomposed into 4 source components are used for expression, and the second heart sound S2 is decomposed into 2 source components for expression, and the heart sound signal source component with a relatively single component is successfully obtained, which is conducive to in-depth analysis, interpretation and classification of heart sound signals, and finally applied to clinical practice and further scientific research.
附图说明Description of drawings
图1为第一心音S1和第二心音S2的产生过程；Fig. 1 is the generation process of the first heart sound S1 and the second heart sound S2;
图2为心音信号的“分时产生”示意图；Fig. 2 is a schematic diagram of "time-sharing generation" of the heart sound signal;
图3为心音信号传播过程示意图。Fig. 3 is a schematic diagram of the heart sound signal propagation process.
具体实施方式Detailed ways
下面结合附图对本发明作进一步详细说明：Below in conjunction with accompanying drawing, the present invention is described in further detail:
心音是心脏瓣膜和相关血管系统机械振动时产生的一种声音信号。心音信号主要包含第一心音S1和第二心音S2，第一心音S1产生开始于心室的收缩期，主要因房室瓣的关闭而产生。A heart sound is an acoustic signal produced when the heart valves and associated vascular system vibrate mechanically. The heart sound signal mainly includes the first heart sound S1 and the second heart sound S2, and the first heart sound S1 starts from the systolic period of the ventricle, mainly due to the closure of the atrioventricular valve.
如图1所示，S1主要由四个部分组成，第一部分产生于心室的第一次收缩、血液加速流向心房的过程，其发生在房室瓣关闭之前；第二部分由血流扩张到房室瓣而引起的撞击以及血液反冲至心室时所产生；第三部分来源于大动脉(肺动脉)的底部和心室壁之间的血流而引起的振动；第四部分主要是由于血液通过主动脉射出时造成湍流而引起的振动。第二心音S2产生于心室收缩的末端至心房舒张的开始阶段，主要由主动脉瓣和肺动脉瓣的关闭产生，S2主要由两部分组成，一是由主动脉瓣关闭时产生的A部分，二是由肺动脉瓣关闭时产生的P部分组成。As shown in Figure 1, S1 is mainly composed of four parts. The first part is produced by the first contraction of the ventricle and the process of accelerating blood flow to the atrium, which occurs before the closure of the atrioventricular valve; the second part is caused by the expansion of blood flow to the atrium. The impact caused by the ventricular valve and the blood recoil to the ventricle; the third part comes from the vibration caused by the blood flow between the bottom of the aorta (pulmonary artery) and the wall of the ventricle; the fourth part is mainly due to the blood passing through the aorta Vibration caused by turbulent flow during injection. The second heart sound S2 is produced from the end of ventricular systole to the beginning of atrial diastole, and is mainly produced by the closure of the aortic valve and pulmonary valve. S2 is mainly composed of two parts, one is the A part produced when the aortic valve is closed, and the other is It is composed of the P component produced when the pulmonary valve closes.
根据心音的产生原理，我们可以发现，心音信号源成分的产生具有明显的“分时产生”特征，对于第一心音S1来说，S1的产生过程总是“1→2→3→4→1…”如图2所示。同理，第二心音S2的产生过程也是其源成分的循环产生的结果：“A→P→A→P→A…”，表现出了明显的“分时产生”特点。According to the principle of heart sound generation, we can find that the generation of heart sound signal source components has obvious "time-sharing generation" characteristics. For the first heart sound S1, the generation process of S1 is always "1→2→3→4→ 1..." as shown in Figure 2. Similarly, the production process of the second heart sound S2 is also the result of the cycle of its source components: "A→P→A→P→A...", showing the obvious "time-sharing production" characteristics.
根据心音信号在胸腔中的传播过程有混叠、反馈(回声)及分时的特点，建立如图3的数学模型：According to the characteristics of aliasing, feedback (echo) and time-sharing in the propagation process of the heart sound signal in the chest cavity, a mathematical model as shown in Figure 3 is established:
设心音为X(t)＝[x1(t),x2(t),…,xn(t)]T，xi(t)代表心音的源成分，体表检测到的心音信号为Y(t)＝[y1(t),y2(t),…,yn(t)]T，yi(t)代表一路心音信号。Suppose the heart sound is X(t)=[x1 (t), x2 (t),…,xn (t)]T , xi (t) represents the source component of the heart sound, and the heart sound signal detected on the body surface is Y(t)=[y1 (t), y2 (t),...,yn (t)]T , yi (t) represents a heart sound signal.
在n路心音信号已经去除背景噪声的情况下有：In the case where the background noise has been removed from the n-channel heart sound signal:
y1＝a11x1+a12x2+…+a1nxny1 =a11 x1 +a12 x2 +...+a1n xn
+w11y1+w12y2+…+w1nyn+w11 y1 +w12 y2 +…+w1n yn
y2＝a21x1+a22x2+…+a2nxn+y2 ＝a21 x1 +a22 x2 +...+a2n xn +
w21y1+w22y2+…+w2nynw21 y1 +w22 y2 +…+w2n yn
yn＝an1x1+an2x2+…+annxn+yn ＝an1 x1 +an2 x2 +…+ann xn +
wn1y1+wn2y2+…+wnnynwn1 y1 +wn2 y2 +…+wnn yn
即：which is:
写成矩阵形式为：Written in matrix form as:
Y＝AX+WYY=AX+WY
即：which is:
Y＝(I-W)-1AX＝BXY=(IW)-1 AX=BX
其中,B＝(I-W)-1。Among them, B=(IW)-1 .
Y为已知的采集信号，矩阵B和X皆未知，假定心音信号的源成分xi(t)的三阶、四阶累积量存在，xi(t)为准平稳随机过程，且相互统计独立。设为心音信号的原始成分矩阵，如果其各个分量相互独立，则即为心音源成分，因此，当且仅当存在一个矩阵C，其每一行和每一列有且仅有一个元素为非零元素时，对矩阵Y做如下变换：CY，则可以获取源成分，即：Y is a known acquisition signal, matrix B and X are both unknown, it is assumed that the third-order and fourth-order cumulants of the source component xi (t) of the heart sound signal exist, and xi (t) is a quasi-stationary random process, and mutual statistics independent. Assume is the original component matrix of the heart sound signal, if its components are independent of each other, then It is the heart sound source component. Therefore, if and only if there is a matrix C, each row and each column of which has and only one element is a non-zero element, the matrix Y is transformed as follows: CY, then the source component can be obtained. which is:
心音信号是一种典型的生物医学信号，具有非线性、非平稳、非高斯、非确定性等的固有特征，高阶统计量分析在信号处理某些应用中能提供特征信息量，具有一定的优势；再者，由本文前面所述心音产生具有“分时”特征，因此，心音信号源成分必定相互统计独立，对四通道心音信号有n＝4。因此，本文设计了基于四阶累积量的心音源成分获取算法，其算法如下：Heart sound signal is a typical biomedical signal, which has inherent characteristics such as nonlinearity, non-stationary, non-Gaussian, non-deterministic, etc. High-order statistical analysis can provide characteristic information in some applications of signal processing, and has a certain advantage; moreover, the heart sound produced by the above-mentioned text has "time-sharing" characteristics, therefore, the heart sound signal source component They must be statistically independent of each other, and n=4 for four-channel heart sound signals. Therefore, this paper designs a heart sound source component acquisition algorithm based on the fourth-order cumulant, and the algorithm is as follows:
(1)计算球化矩阵W，将观测信号Y进行球化处理(1) Calculate the spheroidization matrix W, and perform spherification processing on the observed signal Y
令C＝YYT＝UΛUT，称C为Y的协方差阵，有：Let C=YYT ＝UΛUT , call C the covariance matrix of Y, have:
其中球化矩阵通过球化处理，消除原始各通道数据间的二阶相关性，使得进一步分析可集中在高阶统计量上信号。where the spherical matrix Through spheroidization, the second-order correlation between the original data of each channel is eliminated, so that further analysis can focus on high-order statistics.
(2)计算四阶累积量(2) Calculate the fourth-order cumulant
设M为任意4×4矩阵，则Z的四维累计量矩阵QZ(M)的定义如下：Let M be any 4×4 matrix, then the four-dimensional cumulant matrix QZ (M) of Z is defined as follows:
(3)求“混合——球化”矩阵(3) Seek the "mixing-spherification" matrix
令V＝WB，则有：Let V=WB, then:
VVT＝VTV＝I4VVT = VT V = I4
其中V＝[v1,v2,v3,v4]，vm＝[vm1,vm2,vm3,vm4]T，M＝vmvmTwhere V=[v1 ,v2 ,v3 ,v4 ], vm =[vm1 ,vm2 ,vm3 ,vm4 ]T , M=vm vmT
则有：Then there are:
Qz(M)＝λMQz (M) = λM
即：which is:
[Qz(M)]ij＝λMij[Qz (M)]ij = λMij
式中λ＝k4(xm)是心音源成分的峰度，M称为Qz(M)的特征矩阵，由上面四维累计量矩阵Qz(M)的定义可知，Qz(M)是对角阵，即满足：In the formula, λ=k4 (xm ) is the kurtosis of the heart sound source components, and M is called the characteristic matrix of Qz (M). From the definition of the above four-dimensional cumulant matrix Qz (M), we can see that Qz (M) is a diagonal matrix, which satisfies:
Qij＝QjiQij =Qji
而and
Qz(m)＝k4(xm)MQz (m) = k4 (xm )M
(4)求解估计矩阵，获得心音信号的原始成分(4) Solve the estimated matrix to obtain the original components of the heart sound signal
由矩阵的特征分解理论，以M为权重构成的累计量阵Qz(M)必可分解成VΛ(M)VT的形式：According to the eigendecomposition theory of matrix, the cumulant matrix Qz (M) composed of M as weight must be decomposed into the form of VΛ(M)VT :
此式说明：用V阵对Qz(M)作二次型处理将得到对角阵Λ(M)，则可以求得矩阵B的估计矩阵即：This formula shows that the diagonal matrix Λ(M) will be obtained by quadratic processing of Qz (M) with the V matrix, then the estimated matrix of matrix B can be obtained which is:
则估计系统C为:Then the estimated system C is:
则：but:
从而可获得心音信号的源成分。Thereby the source component of the heart sound signal can be obtained.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810101338.4ACN108392220A (en) | 2018-02-01 | 2018-02-01 | A method of obtaining cardiechema signals derived components |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810101338.4ACN108392220A (en) | 2018-02-01 | 2018-02-01 | A method of obtaining cardiechema signals derived components |
| Publication Number | Publication Date |
|---|---|
| CN108392220Atrue CN108392220A (en) | 2018-08-14 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810101338.4APendingCN108392220A (en) | 2018-02-01 | 2018-02-01 | A method of obtaining cardiechema signals derived components |
| Country | Link |
|---|---|
| CN (1) | CN108392220A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109498054A (en)* | 2019-01-02 | 2019-03-22 | 京东方科技集团股份有限公司 | Heart sound monitoring device, the method and configuration method for obtaining cardiechema signals |
| CN109793533A (en)* | 2019-01-04 | 2019-05-24 | 东南大学 | A simple electronic stethoscope |
| CN110010145A (en)* | 2019-02-28 | 2019-07-12 | 广东工业大学 | A method of eliminating electronic auscultation device grating |
| CN112336369A (en)* | 2020-11-30 | 2021-02-09 | 山东大学 | Coronary heart disease risk index evaluation system of multichannel heart sound signals |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030088164A1 (en)* | 2001-11-02 | 2003-05-08 | Nellcor Puritan Bennett Inc. | Blind source separation of pulse oximetry signals |
| US20090264786A1 (en)* | 2008-04-21 | 2009-10-22 | Brainscope Company, Inc. | System and Method For Signal Denoising Using Independent Component Analysis and Fractal Dimension Estimation |
| CN104382614A (en)* | 2014-12-09 | 2015-03-04 | 重庆邮电大学 | Heart and lung sound signal separation method and device based on fast ICA (independent component analysis) |
| CN104757966A (en)* | 2015-04-13 | 2015-07-08 | 深圳市飞马与星月科技研究有限公司 | Fetal electrocardiosignal extraction method and device |
| CN104873218A (en)* | 2015-04-15 | 2015-09-02 | 南京邮电大学 | Four-passage heart sound synchronous positioning and collecting device |
| CN105653880A (en)* | 2016-03-03 | 2016-06-08 | 南京邮电大学 | Heart sound production field tracing method based on heart sounds |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030088164A1 (en)* | 2001-11-02 | 2003-05-08 | Nellcor Puritan Bennett Inc. | Blind source separation of pulse oximetry signals |
| US20090264786A1 (en)* | 2008-04-21 | 2009-10-22 | Brainscope Company, Inc. | System and Method For Signal Denoising Using Independent Component Analysis and Fractal Dimension Estimation |
| CN104382614A (en)* | 2014-12-09 | 2015-03-04 | 重庆邮电大学 | Heart and lung sound signal separation method and device based on fast ICA (independent component analysis) |
| CN104757966A (en)* | 2015-04-13 | 2015-07-08 | 深圳市飞马与星月科技研究有限公司 | Fetal electrocardiosignal extraction method and device |
| CN104873218A (en)* | 2015-04-15 | 2015-09-02 | 南京邮电大学 | Four-passage heart sound synchronous positioning and collecting device |
| CN105653880A (en)* | 2016-03-03 | 2016-06-08 | 南京邮电大学 | Heart sound production field tracing method based on heart sounds |
| Title |
|---|
| VIVEK NIGAM 等: "A procedure to extract the aortic and the pulmonary sounds from the phonocardiogram", 《ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY》* |
| 徐勤: "《西医学概论》", 30 September 2009* |
| 杨秀梅: "ICA在心音信号处理中的应用", 《生物医学工程学杂志》* |
| 梅铁民: "《盲源分离理论与算法》", 30 April 2013* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109498054A (en)* | 2019-01-02 | 2019-03-22 | 京东方科技集团股份有限公司 | Heart sound monitoring device, the method and configuration method for obtaining cardiechema signals |
| US11523795B2 (en) | 2019-01-02 | 2022-12-13 | Beijing Boe Display Technology Co., Ltd. | Heart sound monitoring device and method for acquiring heart sound signal |
| CN109793533A (en)* | 2019-01-04 | 2019-05-24 | 东南大学 | A simple electronic stethoscope |
| CN110010145A (en)* | 2019-02-28 | 2019-07-12 | 广东工业大学 | A method of eliminating electronic auscultation device grating |
| CN110010145B (en)* | 2019-02-28 | 2021-05-11 | 广东工业大学 | Method for eliminating friction sound of electronic stethoscope |
| CN112336369A (en)* | 2020-11-30 | 2021-02-09 | 山东大学 | Coronary heart disease risk index evaluation system of multichannel heart sound signals |
| Publication | Publication Date | Title |
|---|---|---|
| Abbas et al. | Phonocardiography signal processing | |
| Ari et al. | Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier | |
| US20190133481A1 (en) | System and method of extraction of the heart valve signals | |
| CN108392220A (en) | A method of obtaining cardiechema signals derived components | |
| KR101855369B1 (en) | Systems and methods for estimating physiological heart measurements from medical images and clinical data | |
| Wahlström et al. | A hidden markov model for seismocardiography | |
| Nigam et al. | Accessing heart dynamics to estimate durations of heart sounds | |
| Nogueira et al. | Classifying heart sounds using images of MFCC and temporal features | |
| Ahlström | Processing of the Phonocardiographic Signal− Methods for the Intelligent Stethoscope | |
| Lee et al. | Comparison between short time Fourier and wavelet transform for feature extraction of heart sound | |
| Imtiaz et al. | Correlation between seismocardiogram and systolic blood pressure | |
| Wang et al. | Fetal ECG signal extraction from long-term abdominal recordings based on adaptive QRS removal and joint blind source separation | |
| Gamage et al. | Clustering of scg events using unsupervised machine learning | |
| CN109711073B (en) | A method for blind source separation of heart-lung sound aliasing signals based on sparse representation | |
| Shukla | Estimation of blood pressure from non-invasive data | |
| Ari et al. | Classification of heart sounds using empirical mode decomposition based features | |
| Wajdan et al. | Automatic detection of aortic valve events using deep neural networks on cardiac signals from epicardially placed accelerometer | |
| Dhas et al. | Energy-dependent RLS architecture for the separation of fetal ECG using thoracic and abdominal lead ECG of mother | |
| Gamage et al. | Modeling Seismocardiographic signal using finite element Modeling and medical image processing | |
| Andreou et al. | Mapping the cardiac acousteome: An overview of technologies, tools and methods | |
| Ghaemmaghami et al. | Automatic segmentation and classification of cardiac cycles using deep learning and a wireless electronic stethoscope | |
| CN115062763B (en) | End-to-end heart sound segmentation method based on Residual Bi-LSTM network | |
| Abbas et al. | Introduction to phonocardiography signal processing | |
| Coskun et al. | Effect of filter selection on classification of extrasystole heart sounds via mobile devices | |
| Casanella et al. | Cardiac Mechanical Signals |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20180814 | |
| RJ01 | Rejection of invention patent application after publication |