Deep Learning-Based ECG Classification for Arterial Fibrillation Detection

The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnosis increases the patient’s chances of recovery.However,issues like overfitting and inconsistent accuracy across datasets remain challenges.In a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib detection.The aim was to create a robust detection mechanism that consistently performs well.Metrics such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for evaluation.The findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated categories.It demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib detection.These insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG signals.The comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib detection.Moreover,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.

Efficient ECG classification based on Chi-square distance for arrhythmia detection

This study introduces a new classifier tailored to address the limitations inherent in conventional classifiers such as K-nearest neighbor(KNN),random forest(RF),decision tree(DT),and support vector machine(SVM)for arrhythmia detection.The proposed classifier leverages the Chi-square distance as a primary metric,providing a specialized and original approach for precise arrhythmia detection.To optimize feature selection and refine the classifier’s performance,particle swarm optimization(PSO)is integrated with the Chi-square distance as a fitness function.This synergistic integration enhances the classifier’s capabilities,resulting in a substantial improvement in accuracy for arrhythmia detection.Experimental results demonstrate the efficacy of the proposed method,achieving a noteworthy accuracy rate of 98% with PSO,higher than 89% achieved without any previous optimization.The classifier outperforms machine learning(ML)and deep learning(DL)techniques,underscoring its reliability and superiority in the realm of arrhythmia classification.The promising results render it an effective method to support both academic and medical communities,offering an advanced and precise solution for arrhythmia detection in electrocardiogram(ECG)data.

基于双阶段特征提取网络的ECG降噪分类算法

临床采集到的标准12导联心电图常含有噪声,影响了心电信号分类结果的准确度,为此提出了一种基于双阶段特征提取网络的心电图(ECG)降噪分类算法。首先,在空间特征提取阶段,由深度耦合软阈值化去噪方法的残差收缩网络从输入的12导联标准心电信号中提取空间特征;其次,在时间特征提取阶段,由长短期记忆网络与注意力机制结合继续从心电信号中提取时间特征;最后,通过全连接网络层融合提取到的空间特征与时间特征,输出9个类别的概率预测分布。在CPSC2018数据集上与其他同类型先进分类算法进行了对比实验,验证所提算法的效果,实验结果表明:提出的分类算法在对9类ECG信号进行分类时平均F1分数达到0.854,在各项指标上表现更优。此外,实验证明所提算法在含噪数据中的表现也优于其他主流网络,充分证明了所提算法对于含噪心电信号的降噪分类性能,该算法也可应用于其他类似含噪声生理信号的分析和处理。

Improved Bat Algorithm with Deep Learning-Based Biomedical ECG Signal Classification Model

With new developments experienced in Internet of Things(IoT),wearable,and sensing technology,the value of healthcare services has enhanced.This evolution has brought significant changes from conventional medicine-based healthcare to real-time observation-based healthcare.Biomedical Electrocardiogram(ECG)signals are generally utilized in examination and diagnosis of Cardiovascular Diseases(CVDs)since it is quick and non-invasive in nature.Due to increasing number of patients in recent years,the classifier efficiency gets reduced due to high variances observed in ECG signal patterns obtained from patients.In such scenario computer-assisted automated diagnostic tools are important for classification of ECG signals.The current study devises an Improved Bat Algorithm with Deep Learning Based Biomedical ECGSignal Classification(IBADL-BECGC)approach.To accomplish this,the proposed IBADL-BECGC model initially pre-processes the input signals.Besides,IBADL-BECGC model applies NasNet model to derive the features from test ECG signals.In addition,Improved Bat Algorithm(IBA)is employed to optimally fine-tune the hyperparameters related to NasNet approach.Finally,Extreme Learning Machine(ELM)classification algorithm is executed to perform ECG classification method.The presented IBADL-BECGC model was experimentally validated utilizing benchmark dataset.The comparison study outcomes established the improved performance of IBADL-BECGC model over other existing methodologies since the former achieved a maximum accuracy of 97.49%.

以BP神经网络为工具的短时ECG信号情感分类

针对目前生理信号情感识别领域采用的生理信号种类太多或使用的生信号长度较长的问题,本文使用BP神经网络对单一、短时ECG信号进行情感识别分类,并对识别时间进行了估计。通过诱发被试喜、怒、哀、惧和平静5种基本情感状态,采集到ECG生理信号,处理后利用神经网络建立模型。实验结果表明,本文方法得到的情感分类的平均识别率为89.14%,且生理信号进行特征提取和识别分类的时间总和小于0.15s,有效地降低了对生理信号种类和窗口长度的依赖。

An Attention Based Neural Architecture for Arrhythmia Detection and Classification from ECG Signals

Arrhythmia is ubiquitous worldwide and cardiologists tend to provide solutions from the recent advancements in medicine.Detecting arrhythmia from ECG signals is considered a standard approach and hence,automating this process would aid the diagnosis by providing fast,costefficient,and accurate solutions at scale.This is executed by extracting the definite properties from the individual patterns collected from Electrocardiography(ECG)signals causing arrhythmia.In this era of applied intelligence,automated detection and diagnostic solutions are widely used for their spontaneous and robust solutions.In this research,our contributions are two-fold.Firstly,the Dual-Tree Complex Wavelet Transform(DT-CWT)method is implied to overhaul shift-invariance and aids signal reconstruction to extract significant features.Next,A neural attention mechanism is implied to capture temporal patterns from the extracted features of the ECG signal to discriminate distinct classes of arrhythmia and is trained end-to-end with the finest parameters.To ensure that the model’s generalizability,a set of five traintest variants are implied.The proposed model attains the highest accuracy of 98.5%for classifying 8 variants of arrhythmia on the MIT-BIH dataset.To test the resilience of the model,the unseen(test)samples are increased by 5x and the deviation in accuracy score and MSE was 0.12%and 0.1%respectively.Further,to assess the diagnostic model performance,AUC-ROC curves are plotted.At every test level,the proposed model is capable of generalizing new samples and leverages the advantage to develop a real-world application.As a note,this research is the first attempt to provide neural attention in arrhythmia classification using MIT-BIH ECG signals data with state-of-the-art performance.

AUTOMATIC CLASSIFICATION OF ECG USING ARTIFICIAL NEURAL NETWORKS

ＡＵＴＯＭＡＴＩＣＣＬＡＳＳＩＦＩＣＡＴＩＯＮＯＦＥＣＧＵＳＩＮＧＡＲＴＩＦＩＣＩＡＬＮＥＵＲＡＬＮＥＴＷＯＲＫＳＡＵＴＯＭＡＴＩＣＣＬＡＳＳＩＦＩＣＡＴＩＯＮＯＦＥＣＧＵＳＩＮＧＡＲＴＩＦＩＣＩＡＬＮＥＵＲＡＬＮＥＴＷＯＲＫＳＣ．Ｌ．Ｐｅｎｇ，Ｚ．...

ECG Heartbeat Classification Under Dataset Shift

Electrocardiogram(ECG)is widely used to detect arrhythmia.Atrial fibrillation,atrioventricular block,premature beats,etc.can all be diagnosed by ECG.When the distribution of training data and test data is inconsistent,the accuracy of the model will be affected.This phenomenon is called dataset shift.In the real-world heartbeat classification system,the heartbeat of the training set and test set often comes from patients of different ages and genders,so there are differences in the distribution of data sets.The main challenge in applying machine learning algorithms to clinical AI systems is dataset shift.Test-time adaptation(TTA)aims to adapt a pre-trained model from the source domain(SD)to the target domain(TD)without using any SD data or TD labels,thereby reducing model performance degradation due to domain differences.We propose a method based on multimodal image fusion and continual test-time adaptation(FCTA)for accurate and efficient heartbeat classification.First,the original ECG data is converted into a three-channel color image through a multimodal image fusion framework.The impact of class imbalance on network performance is overcome using a batch weight loss function,and then the pretrained source model is adapted to the TD using a continual test-time adaptation(CTA)method.Although our method is very simple,compared with other domain adaptation methods,it can significantly improve model performance on the test set and reduce the impact caused by the difference in domain distribution.

Development of New Machine Learning Based Algorithm for the Diagnosis of Obstructive Sleep Apnea from ECG Data

In this study,a machine learning algorithm is proposed to be used in the detection of Obstructive Sleep Apnea(OSA)from the analysis of single-channel ECG recordings.Eighteen ECG recordings from the PhysioNet Apnea-ECG dataset were used in the study.In the feature extraction stage,dynamic time warping and median frequency features were obtained from the coefficients obtained from different frequency bands of the ECG data by using the wavelet transform-based algorithm.In the classification phase,OSA patients and normal ECG recordings were classified using Random Forest(RF)and Long Short-Term Memory(LSTM)classifier algorithms.The performance of the classifiers was evaluated as 90% training and 10%testing.According to this evaluation,the accuracy of the RF classifier was 82.43% and the accuracy of the LSTM classifier was 77.60%.Considering the results obtained,it is thought that it may be possible to use the proposed features and classifier algorithms in OSA classification and maybe a different alternative to existing machine learning methods.The proposed method and the feature set used are promising because they can be implemented effectively thanks to low computing overhead.

结合卷积神经网络与注意力机制的多域特征融合ECG心率失常分类

心率失常是心血管疾病诊断的重要手段,其自动分类具有重要的临床意义。为了提高心率失常分类的准确性,结合一维卷积神经网络(Convolutional Neural Networks,CNN)和注意力机制(Attention)提出了一种CNN+Attention的深度学习模型,使用CNN提取心电信号的一维时域特征。针对一维时序心电信号时域特征表征能力有限的问题,使用短时傅里叶变换(Short-Time Fourier transform,STFT)将心电信号变换到时频域,通过Attention提取心电信号的时频域全局相关依赖关系,将时域与时频域特征融合对5种类型心电信号进行分类。在MIT-BIH数据集上验证了模型的有效性,所提模型对5种类型心电信号的平均分类准确率、精准率、召回率、灵敏度以及F1_Score分别为99.72%、98.55%、99.46%、99.90%以及99.00%。与已有先进方法对比,验证了所提模型具有先进的性能表现。

手持式心电采集仪的使用技巧

手持式心电采集仪是一款简易的双极单导联心电图记录设备,只需双手拇指紧捏正、负两极,就能方便地记录出标准Ⅰ导联心电图,多用于监测心律失常。它属于家用医疗器械,颇受广大中老年朋友的欢迎。基于单极导联与双极导联的本质及其内在联系,本文衍生出标准导联与加压单极导联的记录方法;同时,在深入探究CR导联与Wilson导联内在联系的基础上,创造性地提出了手持式心电采集仪直采CR胸导联心电图的方法。理论和实践均表明,加压单极肢体导联的等效记录法与CR胸导联的双极记录法不仅能满足临床需要,而且还有其独到之处。该方法能充分发挥家用医疗器械的医用价值,值得推广普及。

基于自适应参数的心电压缩方法研究

为探究一种适应于临床诊断的高压缩比的心电(electrocardiograph, ECG)压缩方法,本研究提出了一个自适应压缩参数寻优器,基于压缩算法定位出压缩性能最佳的ECG信号参数组。针对算法的普适性,本研究推荐了一组适用于所有ECG信号的参数组,并利用4个指标在MIT-BIH数据库上对压缩性能进行估计。实验结果表明,平均压缩比(compression ratio, CR)达到了26.67,平均百分比均方根误差(percentage root-mean-square difference, PRD)达到了14.64%,压缩一条30 min ECG信号的平均时长为0.125 8 s。本研究改进后的压缩算法在压缩比上表现突出,对临床诊断有应用意义。

面向ECG的二分法稀疏度自适应匹配追踪重构算法

为了减少无线传感器网络(WSNs)心电信号的压缩感知重构时间,提出一种面向心电(ECG)信号的二分法稀疏度自适应匹配追踪重构算法。基于二分法快速接近真实稀疏度的值,并通过相邻迭代之间残差范数值差的绝对值确定下一轮迭代计算区间。实验结果表明:与传统稀疏自适应匹配追踪重构算法相比较,改进算法可显著降低重构时间并接近子空间追踪算法和正交匹配追踪算法;与子空间追踪算法和正交匹配追踪算法相比,峰值信噪比平均提升了6.29%和5.43%。

基于SVM的ECG传感器信号身份识别方法

通过心电图(ECG)传感器采集的信号在身份识别中得到了越来越广泛的应用。但小波滤噪结果往往通过主观判断,没有量化指标,滤波效果不理想;同时,对于ECG特征的提取没有考虑心率变化的影响,鲁棒性不佳。针对这2个问题,提出了一种通过信噪比和相关系数衡量预处理结果的办法,并且在特征的提取上只采用QRS波形,避开了易受心率影响的间期特征。最后使用了多种分类识别方法进行测试,得到了小样本下支持向量机(SVM)最适用于ECG识别的结论。

基于支持向量机算法的ECG分类策略

心电信号（ECG）对医生诊断心脏疾病极为重要。现存许多ECG分类技术存在实现困难，处理时间长和只能对2～3类的ECG进行分类的不足。我们提出了一类基于SVM的ECG分类的崭新的方法，阐明了SVM对ECG分类的基本思想。与传统的神经网络分类相比，在理论上该方法优于神经网络，因为支持向量机考虑的是测试样本的最小化而不是训练样本的最小化。

一种改进的ECG分类神经网络方法

本文引入信息熵作为惩罚函数，加入到神经网络的代价函数中．经过训练获得了更有组织的隐层神经元激励模式，每个输入样本仅使隐层少数神经元产生响应．经过本文提出的裁剪算法的裁剪后，减小了网络的规模，提高了神经网络的泛化能力和计算效率．文中的ＥＣＧ分类也证实了这一结果．

基于改进型蚁群神经网络的ECG心搏分类器

采用改进型蚁群算法优化神经网络模型,构造一个蚁群神经网络的ECG分类器,并对MIT/BIH心律失常数据库中的4类心搏进行分类.结果表明,本文的蚁群神经网络能改善网络性能,有效地避免局部极优,提高训练速度,获得了比BP算法更好的心搏分类性能.

基于Inception模块的CNN-BiLSTM房颤检测与心拍分类算法

心电(ECG)自动分类技术是心律不齐的一种重要辅助诊断手段。为提高动态心电异常心拍提取的准确率,提出一种基于Inception模块的CNN-BiLSTM房颤检测与心拍分类算法。首先将ECG信号分割成采样长度为1000个采样点的心拍片段,然后利用Inception模块提取3种不同尺度的心电特征,再通过4层一维卷积神经网络(CNN)和两层双向长短期记忆神经网络(BiLSTM)来进一步提取心电特征,最后使用一层全连接网络和softmax函数实现降维和心拍分类。为了进一步提高分类准确率,采用小波降噪技术对原始ECG进行降噪。实验采用PhysioNet/Computing in Cardiology Challenge 2017数据库提供的数据,预处理后选取60000个心拍样本进行分类,并以准确率(Acc)和F1分数(F1-score)作为评判标准来评价模型性能。实验结果表明,所建立的模型针对3类心拍(正常、房颤、其它)的分类Acc为91.38%,F1-score为91.27%,比仅使用CNN-BiLSTM组合模型(Acc为86.61%,F1-score为86.68%)分别提高了4.77%和4.59%。因此,所提出的基于Inception模块的CNN-BiLSTM房颤检测与心拍分类算法比CNN-BiLSTM的组合模型有更好的分类效果。

Arrhythmia Detection by Using Chaos Theory with Machine Learning Algorithms

Heart monitoring improves life quality.Electrocardiograms(ECGs or EKGs)detect heart irregularities.Machine learning algorithms can create a few ECG diagnosis processing methods.The first method uses raw ECG and time-series data.The second method classifies the ECG by patient experience.The third technique translates ECG impulses into Q waves,R waves and S waves(QRS)features using richer information.Because ECG signals vary naturally between humans and activities,we will combine the three feature selection methods to improve classification accuracy and diagnosis.Classifications using all three approaches have not been examined till now.Several researchers found that Machine Learning(ML)techniques can improve ECG classification.This study will compare popular machine learning techniques to evaluate ECG features.Four algorithms—Support Vector Machine(SVM),Decision Tree,Naive Bayes,and Neural Network—compare categorization results.SVM plus prior knowledge has the highest accuracy(99%)of the four ML methods.QRS characteristics failed to identify signals without chaos theory.With 99.8%classification accuracy,the Decision Tree technique outperformed all previous experiments.

基于CNN和ET的智能ECG识别方法

心电图(ECG)是检测心血管疾病的重要依据之一,通过对各类心电图的实时分析,可以达到检测被测者房颤及心脏健康情况的目的。采用基于卷积神经网络(CNN)和极端随机树(ET)混合模型的心电信号分类方法,通过连续小波变换对数据进行滤波处理,在此基础上通过CNN-ET混合模型,实现了心电信号的分类。方法结合了CNN对一维数据的强大表征能力,通过ET降低了异常值影响,预防了过拟合问题,具有较强的泛化能力。将所提出的方法在MIT-BIH数据集上进行了测试,在5类心电心拍次数不平衡问题检测中准确率达到99.95%,与现有方法相比,该改进方法进一步提高了ECG信号分类的精确度。