Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients

This paper describes feature extraction methods using higher order statistics (HOS) of wavelet packet decomposition (WPD) coefficients for the purpose of automatic heartbeat recognition. The method consists of three stages. First, the wavelet package coefficients (WPC) are calculated for each different type of ECG beat. Then, higher order statistics of WPC are derived. Finally, the obtained feature set is used as input to a classifier, which is based on k-NN algorithm. The MIT-BIH arrhythmia database is used to obtain the ECG records used in this study. All heartbeats in the arrhythmia database are grouped into five main heartbeat classes. The classification accuracy of the proposed system is measured by average sensitivity of 90%, average selectivity of 92% and average specificity of 98%. The results show that HOS of WPC as features are highly discriminative for the classification of different arrhythmic ECG beats.     

基于聚类分析的心电节拍分类算法

为提高计算机辅助心电节拍分类算法的准确率和普适性,提出一种基于聚类分析的心电节拍分类算法,该算法利用心电节拍个体内差异性较小的特性,采用两级聚类分析、抽样代表性心电节拍的方法,结合心电医师的辅助诊断,实现对心电节拍的准确分类。为了验证算法的准确性,采用国际公认的标准数据库--MIT-BIH心律失常数据库,AAMI/ANSI标准规定的心电节拍分类方法及准确率的计算方法进行仿真实验,最终总体分类准确率达到99.07%。与Kiranyaz等(KIRANYAZ S, INCE T,PULKKINEN J, et al. Personalized long-term ECG classification: A systematic approach［J］. Expert Systems with Applications, 2011, 38(4): 3220-3226.)的心电节拍分类算法相比,该算法无需进行设定的训练,且S类心电节拍分类灵敏度由40.15%提高到89.82%,显著提高了分类算法的普适性。     

Fiducial feature reduction analysis for electrocardiogram (ECG) based biometric recognition

Although the electrocardiogram (ECG) has been a reliable diagnostic tool for decades, its deployment in the context of biometrics is relatively recent. Its robustness to falsification, the evidence it carries about aliveness and its rich feature space has rendered the deployment of ECG based biometrics an interesting prospect. The rich feature space contains fiducial based information such as characteristic peaks which reflect the underlying physiological properties of the heart. The principal goal of this study is to quantitatively evaluate the information content of the fiducial based feature set in terms of their effect on subject and heart beat classification accuracy (ECG data acquired from the PhysioNet ECG repository). To this end, a comprehensive set of fiducial based features was extracted from a collection of ECG records. This feature set was subsequently reduced using a variety of feature extraction/selection methods such as principle component analysis (PCA), linear discriminant analysis (LDA), information-gain ratio (IGR), and rough sets (in conjunction with the PASH algorithm). The performance of the reduced feature set was examined and the results evaluated with respect to the full feature set in terms of the overall classification accuracy and false (acceptance/rejection) ratios (FAR/FRR). The results of this study indicate that the PASH algorithm, deployed within the context of rough sets, reduced the dimensionality of the feature space maximally, while maintaining maximal classification accuracy.     

Implementing wavelet transform/mixture of experts network for analysis of electrocardiogram beats

Abstract: Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of the ME network structure to guide model selection for classification of electrocardiogram (ECG) beats. The expectation maximization algorithm is used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. The ECG signals were decomposed into time–frequency representations using discrete wavelet transforms and statistical features were calculated to depict their distribution. The ME network structure was implemented for ECG beats classification using the statistical features as inputs. To improve classification accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. Five types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat, partial epilepsy beat) obtained from the Physiobank database were classified with an accuracy of 96.89% by the ME network structure. The ME network structure achieved accuracy rates which were higher than those of the stand-alone neural network models.     

Combining recurrent neural networks with eigenvector methods for classification of ECG beats

The purpose of this study is to evaluate the accuracy of the recurrent neural networks (RNNs) trained with Levenberg–Marquardt algorithm on the electrocardiogram (ECG) beats. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were analyzed. Decision making was performed in two stages: feature extraction by eigenvector methods and classification using the RNN trained on the extracted features. The RNNs were implemented for classification of the ECG beats using the statistical features as inputs. The ability of designed and trained Elman RNNs, combined with eigenvector methods, were explored to classify the ECG beats. The classification results demonstrated that the combined eigenvector methods/RNN approach can be useful in analyzing the ECG beats.     

Statistics over features of ECG signals

This paper presented the usage of statistics over the set of the features representing the electrocardiogram (ECG) signals. Since classification is more accurate when the pattern is simplified through representation by important features, feature extraction and selection play an important role in classifying systems such as neural networks. Multilayer perceptron neural network (MLPNN) architectures were formulated and used as basis for detection of variabilities of the ECG signals. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were classified. The selected Lyapunov exponents, wavelet coefficients and the power levels of power spectral density (PSD) values obtained by eigenvector methods of the ECG signals were used as inputs of the MLPNN trained with Levenberg–Marquardt algorithm. The classification results confirmed that the proposed MLPNN has potential in detecting the variabilities of the ECG signals.     

Feature saliency using signal-to-noise ratios in automated diagnostic systems developed for ECG beats

Artificial neural networks (ANNs) have been used in a great number of medical diagnostic decision support system applications and within feedforward ANNs framework there are a number of established measures such as saliency measures for identifying important input features. By identifying a set of salient features, the noise in a classification model can be reduced, resulting in more accurate classification. In this study, a signal-to-noise ratio (SNR) saliency measure was employed to determine saliency of input features of multilayer perceptron neural networks (MLPNNs) used in classification of electrocardiogram (ECG) beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database. The SNR saliency measure determines the saliency of a feature by comparing it to that of an injected noise feature and the SNR screening method utilizes the SNR saliency measure to select a parsimonious set of salient features. ECG signals were decomposed into time–frequency representations using discrete wavelet transform. Input feature vectors were extracted using statistics over the set of the wavelet coefficients. The MLPNNs used in the ECG beats-classification were trained for the SNR screening method. The application results of the SNR screening method to the ECG signals demonstrated that classification accuracies of the MLPNNs with salient input features are higher than that of the MLPNNs with salient and non-salient input features.     

基于小波变换和粗糙集的早搏信号识别算法

心电特征参数的选择和提取是心电图(ECG)分析的基础,提升检测算法的识别率和特征分类的精度是自动分析技术的关键。提出了基于小波变换和属性约简的心电早搏信号识别算法。该算法首先依据心血管专家的诊断标准选择了12个心电特征参数;然后运用基于小波变换的特征检测算法进行了特征提取,并利用基于粒计算的属性约简算法对特征参数进行了属性约简;最后,将约简后的数据用于模式分类并通过MIT-BIH数据库对结果进行验证。实验表明,约简后的分类精度大大高于约简前的数据,特征参数的合理选择(约简)是提高识别效率的重要因素。     

小波变换和支持向量机相融合的ECG身份识别

为了提高心电图（ECG）信号的身份识别正确率,提出一种小波变换和支持向量机相融合的ECG身份识别方法（IWT-ABC-SVM）。采用一种小波阈值函数对ECG进行去噪处理,提取ECG特征,将ECG特征输入到支持向量机中进行学习,采用人工蜂群算法优化支持向量机参数,建立ECG的身份识别模型,采用MIT-BIH心电图数据进行仿真测试。仿真结果表明,相对于其他识别方法,IWT-ABC-SVM提高了ECG身份识别的正确率和可靠性。     

基于改进K均值聚类生成匹配模板的心搏分类方法

为提高分析含大量数据的动态心电时的准确性和分析效率,提出了一种基于改进的K均值聚类生成心搏模板的匹配方法.使用K均值聚类和波形反混淆技术进行循环纠错,生成可变宽心搏模板、并建立心搏模板库.利用可变宽心搏模板和相关系数相结合的策略,对动态心电中心搏进行快速准确分类.实验方法经心率失常数据库MIT-BIT和ANMA/ANSI标准验证,分类结果总体准确率达98.06%,达到了心搏分类目标.     

类内类间距离在CNN识别心拍类中的应用研究

心脏疾病严重威胁人类身体健康，心电图（Electrocardiogram，ECG）心拍分类对心脏疾病的临床诊断和自动诊断具有重要意义。现有基于深度学习生成的ECG心拍特征虽然优于基于传统方法生成的心拍特征，但是因ECG中各类间存在着严重的数据不平衡问题，致使现有基于深度学习方法生成的心拍特征的性能仍不甚理想。针对这一问题，以卷积神经网络（Convolutional Neural Network，CNN）为基础，在各类心拍等量数据基础上构建能有效表达各类心拍共性信息的共性CNN模型，以共性CNN模型和最小化类内距离最大化类间距离模型为基础，分别在各类心拍数据上构建能有效反映相应心拍类别倾向性信息的类别CNN模型，综合各心拍类别CNN模型的输出进行识别与分类。在MIT-BIH数据库上的实验结果显示，该方法识别分类心拍的各项指标均达到100%，解决了MIT-BIH数据库中ECG四类心拍自动识别分类的问题。     

ECG beat classifier designed by combined neural network model

This paper illustrates the use of combined neural network model to guide model selection for classification of electrocardiogram (ECG) beats. The ECG signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The first level networks were implemented for ECG beats classification using the statistical features as inputs. To improve diagnostic accuracy, the second level networks were trained using the outputs of the first level networks as input data. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were classified with the accuracy of 96.94% by the combined neural network. The combined neural network model achieved accuracy rates which were higher than that of the stand-alone neural network model.     

ECG signal classification and arrhythmia detection using ELM-RNN

Arrhythmia is a unique type of heart disease which produces inefficient and irregular heartbeat. This is a cardiac disease which is diagnosed through electrocardiogram (ECG) procedure. Several studies have been focused on the speed and accuracy on the learning algorithm by applying pattern recognition, artificial intelligence in the classification algorithm. In this work a novel classification algorithm is planned based on ELM (Extreme Learning Machine) with Recurrent Neural Network (RNN) by using morphological filtering. The popular publicly available ECG arrhythmia database (MIT-BIH arrhythmia DB) is used to express the performance of the proposed algorithm where the level of accuracy is compared with the existing similar types of work. The comparative study shows that performance of our proposed model is much faster than the models working with RBFN (radial basis function network), BPBB(back propagation neural network) and Support Vector Machine. The experimental result with the MIT BIH database with hidden neurons of ELM with RNN, the accuracy is 96.41%, sensitivity 93.62% and specificity 92.66%. The classification methodology follows main four steps the heart beat detection, the ECG feature extraction, feature selection and the construction of the proposed classifier.

     

A modified mixture of experts network structure for ECG beats classification with diverse features

This paper illustrates the use of modified mixture of experts (MME) network structure to guide model selection for classification of electrocardiogram (ECG) beats with diverse features. The MME is a modular neural network architecture for supervised learning. Expectation-maximization (EM) algorithm was used for training the MME so that the learning process is decoupled in a manner that fits well with the modular structure. The wavelet coefficients and Lyapunov exponents of the ECG signals were computed and statistical features were calculated to depict their distribution. The statistical features, which were used for obtaining the diverse features of the ECG signals, were then input into the MME network structure for training and testing purposes. We explored the ability of designed and trained MME network structure, combined with wavelet preprocessing (computing wavelet coefficients) and nonlinear dynamics tools (computing Lyapunov exponents), to discriminate five types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat, partial epilepsy beat) obtained from the Physiobank database. The MME achieved accuracy rates which were higher than that of the mixture of experts (ME) and feedforward neural network models (multilayer perceptron neural network—MLPNN). The proposed MME approach can be useful in classifying long-term ECG signals for early detection of heart diseases/abnormalities.     

Detection of electrocardiogram signals using an efficient method

Automatic detection of electrocardiogram (ECG) signals is very important for clinical diagnosis of heart disease. This paper investigates the design of a three-step system for recognition of the five types of ECG beat. In the first step, stationary wavelet transform (SWT) is used for noise reduction of the electrocardiogram (ECG) signals. Feature extraction module extracts higher order statistics of ECG signals in combination with three timing interval features. Then hybrid Bees algorithm-radial basis function (RBF_BA) technique is used to classify the five types of electrocardiogram (ECG) beat. The suggested method can accurately classify and discriminate normal (Normal) and abnormal heartbeats. Abnormal heartbeats include left bundle branch block (LBBB), right bundle branch block (RBBB), atrial premature contractions (APC) and premature ventricular contractions (PVC). Finally, the classification capability of five different classes of ECG signals is attained over eight files from the MIT/BIH arrhythmia database. Simulation results show that classification accuracy of 95.79% for the first dataset (4000 beats) and an overall accuracy of detection of 95.18% are achieved over eight files from the MIT/BIH arrhythmia database.     

心电节拍自动分类算法的研究

世界卫生组织调查发现在全球范围内心血管、心脏疾病是导致死亡概率最高的疾病,心电图(ECG)是临床上广泛应用的预防、监护和诊断心血管及心脏疾病的重要工具之一。心电自动分析诊断技术可以大大减少心电医师的工作量,提高心电图的诊断效率,其中心电节拍(ECG Beat)分类是心电自动分析诊断技术的主要研究方向,是自动分析心律失常的一种重要分析手段,特别是在动态心电图或者长期心电记录领域发挥着重要的作用。本文提出一种心电节拍分类算法,该算法在聚类分析的基础上,结合线性分类器加权判断和心电医师对各聚类的抽样判断,获得心电节拍的最终分类。以MIT-BIH-AR[1]心律失常数据库作为原始数据,采用AAMI的ANSI/AAMI EC57:1998/(R)2003[2]标准规定的心电节拍分类种类及准确率的衡量方法,对该算法的检验,发现采用聚类分析和线性分类器加权判断的方法,分类的准确率达到86.60%;结合心电医师的抽样判断后,算法最终的准确率高达98.16%。     

Design of fuzzy classifier for diabetes disease using Modified Artificial Bee Colony algorithm

In this study, diagnosis of diabetes disease, which is one of the most important diseases, is conducted with artificial intelligence techniques. We have proposed a novel Artificial Bee Colony (ABC) algorithm in which a mutation operator is added to an Artificial Bee Colony for improving its performance. When the current best solution cannot be updated, a blended crossover operator (BLX-α) of genetic algorithm is applied, in order to enhance the diversity of ABC, without compromising with the solution quality. This modified version of ABC is used as a new tool to create and optimize automatically the membership functions and rules base directly from data. We take the diabetes dataset used in our work from the UCI machine learning repository. The performances of the proposed method are evaluated through classification rate, sensitivity and specificity values using 10-fold cross-validation method. The obtained classification rate of our method is 84.21% and it is very promising when compared with the previous research in the literature for the same problem.     

A switchable scheme for ECG beat classification based on independent component analysis

A switchable scheme is proposed to discriminate different types of electrocardiogram (ECG) beats based on independent component analysis (ICA). The RR-interval serves as an indicator for the scheme to select between the longer (1.0 s) and the shorter (0.556 s) data samples for the following processing. Six ECG beat types, including 13900 samples extracted from 25 records in the MIT-BIH database, are employed in this study. Three conventional statistical classifiers are employed to testify the discrimination power of this method. The result shows a promising accuracy of over 99%, with equally well recognition rates throughout all types of ECG beats. Only 27 ICA features are needed to attain this high accuracy, which is substantially smaller in quantity than that in the other methods. The results prove the capability of the proposed scheme in characterizing heart diseases based on ECG signals.     

Detecting variabilities of ECG signals by Lyapunov exponents

An approach based on the consideration that electrocardiogram (ECG) signals are chaotic signals was presented for automated diagnosis of electrocardiographic changes. This consideration was tested successfully using the nonlinear dynamics tools, like the computation of Lyapunov exponents. Multilayer perceptron neural network (MLPNN) architectures were formulated and used as basis for detection of variabilities of ECG signals. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were classified. The computed Lyapunov exponents of the ECG signals were used as inputs of the MLPNNs trained with backpropagation, delta-bar-delta, extended delta-bar-delta, quick propagation, and Levenberg–Marquardt algorithms. The performances of the MLPNN classifiers were evaluated in terms of classification accuracies. The results confirmed that the MLPNN trained with the Levenberg–Marquardt algorithm has potential in detecting the variabilities of the ECG signals (total classification accuracy was 95.00%).     

TSCNN:面向可穿戴心电信号监测与分析的卷积神经网络

目的 可穿戴设备能够长时间实时监测人体心脏状况,其在心电信号监测领域应用广泛。但目前仍没有公开的来自可穿戴设备的心电数据集,大部分心电信号分析算法都是针对医院设备所采集的心电数据。因此,本文使用IREALCARE 2.0柔性远程心电贴作为心电信号监测和采集设备制作了可穿戴设备的心电数据集。针对可穿戴心电数据干扰多、数据量大等特点,本文提出了一种针对可穿戴设备获得的心电信号进行自动分类的深层卷积神经网络,称之为时空卷积神经网络（time-spatial convolutional neural networks,TSCNN）。方法 将原始的长时间心电信号分割为单个的心搏并与滤波后不同频段的心搏数据组合成十通道的数据输入到TSCNN中。TSCNN对每个心搏使用时间卷积和空间滤波来提取丰富的特征。采用小卷积核级联卷积的方式提高分类性能,并降低网络的参数量和计算量。结果 在本文制作的心电数据集上进行了测试,并与其他4种心电分类算法：CNN（convolutional neural networks）、RNN（recurrent neural networks）、1-DCNN（1-dimensional convolution neural networks）和DCN（dense convolutional networks）进行了比较。实验结果显示,本文方法的分类准确率达到91.16%,优于其他4种方法。结论 本文方法面向可穿戴心电数据,获得了较好的分类性能,可以有效监控穿戴者是否出现了心电异常情况。