改进的非线性自适应滤波器用于ECG信号去噪

提出了应用改进的非线性自适应多项式滤波器用于去除ECG信号噪声的方法.利用误差准则确定的Volterra序列展开能很好模拟生物信号成份,而基于Volterra序列的自适应滤波器能有效模拟ECG成份从而达到去除信号中噪声的目的.该方法在研究Volterra序列的特性并确定适应心电信号的多项式阶次、多项式结构等参数基础上,提出了改进的非线性多项式自适应滤波算法.针对MIT-BIH数据库数据的计算机模拟结果显示该方法能有效提高ECG的信噪比.     

基于金字塔卷积结构的深度残差网络心电信号分类方法研究

近年来,深度神经网络(DNNs)已广泛应用于心电图(ECG)信号分类领域,但是以往的模型从原始ECG数据中提取特征信息受限。因此,本文提出了一种基于金字塔型卷积层的深度残差网络(PC-DRN)算法,该算法中包含的金字塔型卷积(PC)层可以从原始ECG数据中同时提取多尺度特征,并采用深度残差网络训练ECG信号分类模型,可以实现对ECG信号的分类。本文使用2017心脏病学挑战赛(CinC2017)提供的公开数据集,验证本文提出方法对4类ECG数据的分类效果。本文选取精度和召回率之间的谐波均值F_1作为主要评价指标。实验结果表明,PC-DRN的平均序列级别F_1(SeqF_1)从0.857提升到了0.920,平均集合级别F_1(SetF_1)从0.876提升到了0.925。因此,本文提出的PC-DRN算法为ECG信号的特征提取和分类提供了一种新的思路,为心律失常的分类诊断提供了有效的手段。     

基于自适应陷波技术的心电图工频干扰抑制研究

我们研究了一种基于QR分解最小二乘（QRD-LS）算法自适应陷波技术的ECG工频干扰抑制法，其充分利用了自适应滤波器自动跟踪干扰的能力，自动消除工频干扰，提高信噪比。而且此方法采用直接针对输入数据矩阵进行递推的QRD-LS算法进行权值的训练和更新，有很好的数据稳定性，且可用并行Systolic处理结构高效地实现，因此ECG工频干扰抑制法有很强的实用性。仿真实验表明该方法具有传统基于LMS算法自适应陷波器所无法比拟的优点，工频干扰滤除效果更佳。     

基于BW算法的高采样率心电数据无损压缩

目前对心电数据压缩的研究主要集中在对低采样率心电数据的压缩,我们提出了一种基于BW(Burrows-Wheeler)算法对高采样率心电数据的无损压缩算法.首先对原始心电数据进行差分变换,将部分16位二进制差值表示为8位,然后对差分结果进行前移编码,使得相同字符集中于某一段区域,最后通过算术编码得到高压缩比.结果表明,该算法不仅适用于高采样率体表心电数据的压缩,而且也适用于心内心电数据的压缩, 平均压缩比分别达到3.547和3.608.同现有的心电无损压缩算法相比,它在压缩效果上获得了较大改进.另外针对高采样率心电数据,使用该算法进行无损压缩也可以得到较好的压缩效果.     

基于EMD的自适应ECG信号基线漂移消除方法研究

对比目前使用EMD或改进EMD方法进行的心电（ECG）信号基线漂移去除算法的实现。本文在详细考察EMD方法过程的基础上,提出一种与EMD物理意义高度契合的完全自适应的基线漂移算法,通过计算ECG平均心率周期,与EMD分解产生的IMF分量的“周期”进行对比,分离出不属于ECG信号的低频IMF分量,然后重构其余IMF分量得到去除基线漂移的ECG信号。使用美国麻省理工学院提供的MIT-BIH心率失常数据库中的原始ECG对本文提出的基线漂移去除方法进行定性分析。使用ECGSYN（实际ECG波形发生器）产生模拟干净的ECG信号,加入已知的低频信号作为基线漂移噪声,对本文提出的基线漂移去除方法进行定量分析。     

改进的三次样条插值心电基线漂移滤波法

基准点选择对三次样条插值法去噪的效果有重要影响。本文针对通常的三次样条插值滤波方法,提出一种改进的心电(ECG)信号滤波算法,能适应更宽范围的基线噪声频率分布。算法通过对原始ECG信号求一阶导数,得到每一个心拍周期内的最大和最小值点,其对应的位置作为基准点的位置。然后对原始ECG信号通过截止频率为1.5Hz的高通滤波器,将滤波前后基准点所对应信号幅值的差值作为基准点的幅度。对这些基准点进行三次样条插值曲线拟合,所得拟合曲线为基线漂移曲线。改进算法与原单点法相比,在模拟两种基线漂移情况下,改进样条差值的拟合基线漂移曲线对模拟基线漂移的相关系数分别提高了0.242和0.13;真实基线漂移的情况下,多个临床数据实验显示改进样条差值法平均相关系数达到0.972。     

基于小波神经网络的心电信号滤波研究

针对心电(ECG)信号检测中存在的主要噪声,本文研究了基于小波神经网络(WNN)的ECG信号滤波理论。提出一种通过WNN非线性逼近能力构建的针对ECG信号的非线性滤波器算法和滤波策略,实现对ECG信号中基线漂移、肌电干扰、工频干扰噪声的滤除;给出了网络训练算法和滤波实验,滤波后信号与期望信号误差范围在微伏级,验证了本文提出的基于WNN的心电非线性滤波器对心电主要噪声快速滤波的良好效果,最后讨论了影响WNN用于心电滤波的几个关键问题。     

基于焦点损失函数的嵌套长短时记忆网络心电信号分类研究EI北大核心CSCD

心电图(ECG)可直观地反映人体心脏生理电活动,在心律失常检测与分类领域中具有重要意义。针对ECG数据中类别不平衡对心律失常分类带来的消极作用,本文提出一种用于不平衡ECG信号分类的嵌套长短时记忆网络(NLSTM)模型。搭建NLSTM学习并记忆复杂信号中的时序特征,利用焦点损失函数(focal loss)降低易识别样本的权重;然后采用残差注意力机制(residual attention mechanism),根据各类别特征重要性修改已分配权值,解决样本不平衡问题;再采用合成过采样技术算法(SMOTE)对麻省理工学院与贝斯以色列医院心律失常(MIT-BIH-AR)数据库进行简单的人工过采样处理,进一步增加模型的分类准确率,最终应用MIT-BIHAR数据库对上述算法进行实验验证。实验结果表明,所提方法能有效地解决ECG信号中样本不平衡、特征不突出的问题,模型的总体准确率达到98.34%,较大地提升对少数类样本的识别和分类效果,为心律失常辅助诊断提供可行的新方法。     

心电信号处理中滤波器设计的研究

由体表电极(胸导联或肢导联)检测到的ECG心电信号常有不同的干扰,为了得到不失真的原始心电信号,在诊断分析前要进行必要的预处理--滤波.本文详细介绍了在处理动态心电图系统记录的ECG信号中各种滤波器的设计,包括去除各种噪声的低通、高通、带阻滤波器以及一次性滤波器.     

小鼠急性心肌缺血ECG的小波分析

结扎小鼠冠状动脉前降支造成心肌缺血10min，采集小鼠在正常和急性心肌缺血下的ECG信号。采样频率选为500Hz，连续采集20s的数据。用具有对数频率分辨率的小波变换技术来分析ECG信号。选Mexican Hat小波为母函数，尺度因子α在区间[0．00125，2．5]取值，则相应的带通滤波器中心频率为200～0．1Hz。计算出ECG信号在相应尺度下的小波分解系数，然后求出在频率f处带宽为△f内的信号能量，得出了小鼠急性心肌缺血前后ECG信号能量随频率f的变化规律。结果表明：小鼠急性心肌缺血时ECG信号平均能量在0．1～1．0Hz和1～10Hz段是增加的，在10～200Hz段减少。     

Elimination of electrocardiogram artifacts from electroencephalogram records by using the simultaneously recorded electrocardiograph data

We developed a simple method to eliminate electrocardiogram (ECG) artifacts from electroencephalogram (EEG) records by using simultaneously recorded ECG data. The raw EEG data, the real EEG data and the ECG data were regarded as multi-dimensional vectors Ea, Er and C, respectively. Also, the ECG data, with reduced amplitude whose coefficient was denoted as 'k', were assumed to be overlapped on the real EEG. These assumptions introduced the equations [Ea = Er + k.C], [Er.C = 0] and finally [k = Ea. C/C.C]. This calculation method was implemented by a Macintosh computer using data exported from digital EEG recordings (sampled at 200 Hz with 16-bit resolution). In several subjects, sampling intervals of 5 or 10 seconds for calculation succeeded in eliminating ECG artifacts. However, regardless of the sampling interval, this elimination condition was not always efficient in several other subjects, including a brain-dead patient. It was suggested that the ECG data used were insufficient for the calculation, because only one hand-to-hand reference was used for simultaneous recording, as usual. This one ECG reference was able to express only one ECG projection. Then two other hand-to-foot references of ECG were added to the recordings, and the elimination procedure was performed using all of the simultaneously recorded ECG data at the three references. Consequently, elimination was much improved in most subjects, including the brain-dead patient. Our method may be useful for eliminating ECG artifacts without changing reference electrodes.     

心电图波形基线漂移的数学形态滤波在线实时处理

研究数学形态学滤波器消除心电图波形的基线漂移。选择Maragos类型形态滤波器,得到平结构元为消除波形基线漂移最佳形态滤波形式,信号的衰减幅度由信号数字频率与结构元长度的比值唯一决定,由此归纳出平结构元长度大于或等于要滤波除去的分量的横向宽度的结论。借助Matlab软件进行算法模拟,并移植到DSP硬件平台上进行工程调试,实验表明,该方法运算简单,花费时间少于1 ms,能有效并实时地滤除基漂。     

Application of a wavelet adaptive filter to minimise distortion of the ST-segment

A wavelet adaptive filter (WAF) for the removal of baseline wandering in ECG signals is described. The WAF consists of two parts. The first part is a wavelet transform that decomposes the ECG signal into seven frequency bands using Vaidyanathan-Hoang wavelets. The second part is an adaptive filter that uses the signal of the seventh lowest-frequency band among the wavelet transformed signals as primary input and a constant as reference input. To evaluate the performance of the WAF, two baseline wandering elimination filters are used, a commercial standard filter with a cutoff frequency of 0.5 Hz and a general adaptive filter. The MIT/BIH database and the European ST-T database are used for the evaluation. The WAF performs better in the average power of eliminated noise than the standard filter and adaptive filter. Furthermore, it shows a lower ST-segment distortion than the standard filter and the adaptive filter.     

Single-lead fetal electrocardiogram estimation by means of combining R-peak detection,resampling and comb filter

Minimal detecting electrodes are preferred to miniaturise fetal electrocardiogram (fECG) monitoring devices for application in non-clinical environments. In this paper, a new method to estimate the fECG using a single-lead abdominal signal is introduced. In this method, for a preprocessed abdominal ECG recording, we follow a multi-step procedure to estimate the fECG signal. First, the locations of the maternal R-peaks are detected. Each R–R interval in the abdominal signal is resampled to have the same number of samples by changing its corresponding sampling frequency. A comb filter, which has teeth that coincide with the harmonics of the maternal electrocardiogram (mECG), is applied to the resampled signal. Each R–R interval in the filtered signal is resampled again to recover its original sampling frequency, and the mECG signal is obtained. This mECG signal is subtracted from the abdominal signal, and the residual signal is considered to be a primary estimate of the fECG signal. The same procedure can be applied to the residual signal to enhance the fECG signal. Compared to two other single-lead-based methods, singular value decomposition and nonlinear state-space projection, the proposed method has shown improved robustness and fidelity in restoration of the fECG during testing with synthetic ECG signals and a real fetal ECG database from MIT-BIH PhysioBank.     

Effects of noise and filtering on SVD-based morphological parameters of the T wave in the ECG

Singular value decomposition (SVD) based electrocardiogram (ECG) morphology analysis is a novel method in the assessment of subtle abnormalities in the T wave morphology of 12-lead ECG. As various types of noise contaminate the ECG signal and create a bias for the morphological analyses, this study was designed to estimate the effects of noise on the SVD method in an experimental setup. Ideal signals were generated by filtering real ECG signals several times with the Savitzky-Golay filter. Random and real noise samples were superimposed on the ideal signals. The noisy signals were filtered with a power line interference filter combined with the Savitzky-Golay or the wavelet filter. Results show that noise increased both the dipolar and non-dipolar components significantly unless filtering was applied. R-TWR (relative T wave residuum) and A-TWR (absolute T wave residuum) were four to eight times higher in noisy signals. The experiments with patient data demonstrated that certain types of noise may even lead to erroneous classification of patients. Filtering brings the median values closer to the correct ones and decreases significantly the variance of the values of parameters.     

Effects of noise and filtering on SVD-based morphological parameters of the T wave in the ECG

Singular value decomposition (SVD) based electrocardiogram (ECG) morphology analysis is a novel method in the assessment of subtle abnormalities in the T wave morphology of 12-lead ECG. As various types of noise contaminate the ECG signal and create a bias for the morphological analyses, this study was designed to estimate the effects of noise on the SVD method in an experimental setup. Ideal signals were generated by filtering real ECG signals several times with the Savitzky-Golay filter. Random and real noise samples were superimposed on the ideal signals. The noisy signals were filtered with a power line interference filter combined with the Savitzky-Golay or the wavelet filter. Results show that noise increased both the dipolar and non-dipolar components significantly unless filtering was applied. R-TWR (relative T wave residuum) and A-TWR (absolute T wave residuum) were four to eight times higher in noisy signals. The experiments with patient data demonstrated that certain types of noise may even lead to erroneous classification of patients. Filtering brings the median values closer to the correct ones and decreases significantly the variance of the values of parameters.     

自适应算法与小波变换在心电信号滤波中的应用

心电信号是一种基本的人体生理信号,具有重要的临床诊断价值。然而,体表检测人体心电信号中常带有工频干扰、基线漂移、肌电干扰等各种噪声,给临床对心血管疾病的诊断带来了障碍。为了消除心电信号检测过程中带有的上述三种噪声,采用LM S自适应算法及小波变换理论,有针对性的设计了自适应滤波器、小波变换滤波器和自适应信号分离器等三种数字滤波器来滤除相应干扰。结果表明,对心电信号中存在的这三种噪声具有很好的滤波效果。     

基于EMD与IMF分量统计特性的ECG去噪

经验模式分解（EMD）域内心电（ECG）信号的去噪,通常为基于QRS特征波经验性识别固有模态函数（IMF）分量并重建ECG信号。由于该方法引入个人误差,因此识别不准确。针对此问题,本文提出利用EMD与IMF分量统计特性对ECG信号进行去噪。本方法首先对含噪ECG信号进行EMD分解得到一系列IMF分量,然后利用IMF分量的统计特性识别IMF分量属性,并采用被识别为ECG信号的IMF分量重建ECG信号。该识别方法基于统计学方法,具有统计学和现实物理意义。将本方法应用于真实ECG信号去噪处理中,结果表明,本方法可有效去除ECG信号基线漂移噪声与肌电干扰噪声,去噪效果优于经验法。     

基于虚拟仪器的12导同步心电信号采集系统

本文介绍了一种基于虚拟仪器的12导同步心电信号采集系统的研制方法.硬件由笔记本电脑、同步心电放大器、12位数据采集卡组成,程序用虚拟仪器编程语言LabWindows/CVI编写,界面模拟实际的采样仪器,可以设置采样参数、登记病例信息、采集时实时显示心电波形并将数据存盘.应用此系统,采集正常30例、异常150例心电数据存入心电数据库,效果良好.