ECG Dataset Research Articles

Comparison of Electrocardiogram between Dilated Cardiomyopathy and Ischemic Cardiomyopathy Based on Empirical Mode Decomposition and Variational Mode Decomposition.

The clinical manifestations of ischemic cardiomyopathy (ICM) bear resemblance to dilated cardiomyopathy (DCM), yet their treatments and prognoses are quite different. Early differentiation between these conditions yields positive outcomes, but the gold standard (coronary angiography) is invasive. The potential use of ECG signals based on variational mode decomposition (VMD) as an alternative remains underexplored. An ECG dataset containing 87 subjects (44 DCM, 43 ICM) is pre-processed for denoising and heartbeat division. Firstly, the ECG signal is processed by empirical mode decomposition (EMD) and VMD. And then, five modes are determined by correlation analysis. Secondly, bispectral analysis is conducted on these modes, extracting corresponding bispectral and nonlinear features. Finally, the features are processed using five machine learning classification models, and a comparative assessment of their classification efficacy is facilitated. The results show that the technique proposed provides a better categorization for DCM and ICM using ECG signals compared to previous approaches, with a highest classification accuracy of 98.30%. Moreover, VMD consistently outperforms EMD under diverse conditions such as different modes, leads, and classifiers. The superiority of VMD on ECG analysis is verified.

Explainable AI-driven machine learning for heart disease detection using ECG signal

The majority of countries globally find that cardiovascular diseases have the greatest death rate. Early detection of heart disease is necessary to prevent deaths from it. Big data for medical diagnostics has made it easier to construct sophisticated machine learning (ML) and deep learning (DL)-based models for the early automatic identification of heart disease. Using three common ECG datasets, i.e., the Physionet Challenge 2016, the PASCAL Challenge Competition, and the MIT-BIH - random forest (RF) and extreme gradient boosting (XGBoost), two tree explainer classifiers are proposed for the detection of heart disease in this study. During pre-processing variety of techniques like bandpass filtering, denoising, butterworth filtering and zero-phase filtering of the signal are carried out. After the signals are restored to the time domain form using IDWT, DWT and EWT are utilized to extract features. SHapley Additive exPlanations (SHAP) is used for the feature importance which identifies important features that have more impact on the prediction output of the models. It is demonstrated from the simulation results that EWT with XGB performs well in the three datasets considered. RF explainer algorithm with EWT feature performs best and results in an AUC of 95.36 % for the PASCAL Challenge Competition dataset. However, with AUC values of 97.44 % and 98.25 % for the Physionet Challenge 2016 and MIT-BIH datasets, respectively, the XGB explainer algorithm with EWT features performs better than (DWT+XGB), (DWT+RF), and (EWT+RF). When all three datasets are compared to the current models, overall the suggested model performs better and has a higher AUC.

Power modulation spectrum – a promising approach for the indispensable quality control of electrocardiogram signals from monitoring units for the detection of autonomic dysfunction

ObjectiveElectrocardiogram (ECG) is essential for evaluating the autonomic nervous system. Ensuring the quality of real-world ECG datasets is critical, but manual control of large datasets is impractical. Thus, automated quality control is necessary. This paper introduces a new quality index, the peak-distance quality index (PDQI), based on the modulation spectrum approach. MethodsReal-life data from 1000 ECG recordings, each 600 s long, were collected at the stroke unit of the University Hospital Tulln. Each ECG was visually evaluated, including the duration of the signal, artefacts and noise, and the number of extrasystoles. The power-modulation spectrum, the percentage of ECG in each signal, and modulation spectrum-based quality index (MS-QI) and PDQI were calculated. The area under the curve (AUC) for the detection of high-quality ECGs was calculated for both quality indices, as well as the optimal threshold for each index. ResultsThe percentage of ECG signals in the recordings based on the modulation spectrum correlates with expert rating (r = 0.99, p < 0.001). The AUC for PDQI for the detection of extrasystoles is 0.96, and the AUC for MSQI for the detection of artefacts is 0.83. The optimal thresholds for PDQI and MSQI are 0.44 and 0.17, respectively ConclusionThe power modulation spectrum can be applied to large amounts of data to detect ECG signals within biosignals and calculate quality indices. MSQI can be used for artefact detection and PDQI for extrasystole detection in ECG signals. A combined approach using both quality indices can provide a picture of the underlying data quality.

M-XAF: Medical explainable diagnosis system of atrial fibrillation based on medical knowledge and semantic representation fusion

BackgroundElectrocardiogram (ECG) is a critical diagnostic tool used for screening atrial fibrillation (AF). In recent years, several deep learning-based ECG automatic diagnosis methods have been proposed and have yielded satisfactory results. However, the lack of interpretability in these systems limits their clinical usage. MethodsTo address this issue, we propose a medical explainable AF diagnosis system (M-XAF) that not only predicts AF diagnostic results but also generates an analysis report of the ECG medical features that influenced the classification model's decision. Using a novel ECG signal features occlusion analysis method, M-XAF establishes a connection between the medical knowledge space and the representation space from the convolutional neural network (CNN) by extracting understandable semantic sensitive channels (SSCs) via gradient-weighted channel sensitivity. Through the visualization and statistical modeling of SSCs, M-XAF provides multimodal explanations, including ECG feature descriptions, regions of interest (ROI), and class activation mapping (CAM), for AF diagnostic results. ConclusionThe experimental results demonstrate that the M-XAF has achieved satisfactory results in the AF identification task, with accuracy, specificity, PPV, F1, and MCC reaching over 0.9715, 0.9896, 0.9778, 0.9567, and 0.9365 on two public ECG datasets. In addition, M-XAF generates quantitative explainable reports and CAM for each predicted sample from the perspective of classification models. Furthermore, the explainable reports provided by M-XAF can address the high-confidence problem in classification models. Ultimately, the explainable framework in M-XAF can be widely applied in AI-ECG classification scenarios.

Frequency Domain Template Subtraction Approach to Attenuate Maternal Electrocardiogram in Fetal Electrocardiogram.

We develop a frequency domain template subtraction approach to attenuate the maternal ECG in the abdominal ECG measured from pregnant women. The proposed approach was tested on five public fetal ECG datasets simultaneously measured with ECG from the fetal scalp. The method's performance was compared with the template subtraction approach in the time domain using the accuracy and association metrics. The accuracy was calculated by counting the number of fetal complexes in the processed data that coincided with the fetal complexes in the scalp fetal ECG. The association is quantified as the coherence between the processed data and the gold standard. The maximum coherence values calculated for each approach were compared using the paired t-test. Our results showed no difference in the accuracy between the frequency and time domain approach (p = 0.733). However, the association was higher between the frequency domain data and the gold standard compared to the template subtraction data and the gold standard (p = 0.049), indicating that the frequency domain approach yielded a signal that resembled that of the scalp ECG compared to the time domain approach.

Usability of novel beat-by-beat ECG annotation software portal for generating large-scale machine learning training datasets

Abstract Introduction Despite the availability of numerous large publicly available ECG datasets, there is a distinct absence of specialized software to enable the beat-by-beat annotation and labeling, limiting the ability to generate high-quality machine learning training datasets. This study analyzed the usability of such a novel software interface. Through a survey of several cardiologists and clinic staff, several metrics were gauged, including user satisfaction, system and app simplicity, user interface, and effectiveness. The survey results gleaned insight into the users’ experiences, providing an understanding of the software’s user-friendliness and potential in developing a large-scale machine learning annotated ECG training dataset to advance cardiac health research. Methods 3 cardiology physicians, and 9 cardiac telemetry unit staff were surveyed following use of the SafeBeat Annotation Software Platform to annotate a large publicly available dataset ECGs (n=10,646) beat-by-beat. The validated Post-Study System Usability Questionnaire (PSSUQ) and mobile Health App Usability Questionnaire (MAUQ) were used to assess the overall usability of the software interface. Results are reported as mean ± standard deviation. Results Users completed 10,646 ECG beat-by-beat annotations in 62 days, and averaged 164.0 ECGs per day. Physicians rated the software interface highly, with an overall mean PSSUQ of 6.4 ± 0.8 and MAUQ of 6.4 ± 0.7. Staff also rated the software interface highly, with an overall mean PSSUQ of 6.7 ± 0.6 and MAUQ of 6.8 ± 0.5. Overall 92% of the users reported that they strongly agreed they would use the application again and 83% strongly agreed that it was easy to learn how to use the system. Conclusion The usability analysis of this novel beat-by-beat ECG annotation software revealed that it was a highly effective tool for both cardiologists and clinic staff. Both the system and app were reported to be simple to learn, comfortable to use, and easily navigable. With most users responding that they could become productive quickly using this system, there is clear potential for it to be used to develop a large-scale machine learning dataset.Figure 1

Clinical Turing tests with user certainty analysis to create and validate synthetic electrocardiogram images for artificial intelligence-enhanced algorithm development

Abstract Background Artificial intelligence-enhanced electrocardiogram (AI-ECG) algorithms have primarily been created using digitised signal data, owing to a relative absence of publicly available image-based datasets. ECGs are often scanned or photographed into electronic health records. For maximum clinical utility, AI-ECG algorithms should be applicable to these data. Synthetic data could expedite the creation of extensive, fully anonymised image-based ECG datasets to permit training image-based AI algorithms, but it is essential that such datasets contain the artefacts encountered in clinical practice. We investigated whether iterative clinical Turing tests with user certainty analysis could be used to develop and validate synthetic ECG data. Purpose To create synthetic ECG images containing the artefacts typically encountered in clinical practice, and to validate the images through iterative Turing testing and user certainty analysis. Methods Synthetic ECG images containing artefacts were created using the PTB-XL dataset (a publicly available signal-based dataset comprising 21799 ECGs) as source data. Iterative clinical Turing tests were conducted where healthcare professionals completed an online survey comprising 60 real and synthetic ECGs. Participants were asked to select whether they thought ECGs were real or synthetic. For user certainty analysis, participants were asked to rate their confidence in their answers using a five-point Likert scale (Figure 1). Likert scale responses were converted into a signed ordinal scale representing user certainty in the identification of real or synthetic data. This scale was used to perform Receiver Operating Characteristic (ROC) analysis. Following quantitative survey completion, qualitative feedback was sought and used to iteratively improve the realism of the synthetic images. Results A total of 26 healthcare professionals completed the clinical Turing tests over three rounds. Qualitative feedback was used to improve the fidelity of the synthetic ECG images between rounds (Table 1). During iterative testing, the proportion of synthetic ECGs correctly identified fell from 61.5% to 53.7%, and the proportion of real-world ECGs correctly identified fell from 66.3% to 53.0% (Figure 1). Following the final Turing test, ROC analysis revealed no discriminative ability for identifying synthetic data (C-statistic 0.480, 95% confidence interval 0.432-0.529). Conclusion Iterative Turing testing with user certainty analysis and qualitative user feedback may be used to create synthetic ECG images containing the artefacts typically encountered in clinical practice. Iterative Turing testing improved the images’ realism confirming their potential to augment image-based AI algorithm development. The presented methodology establishes a framework to develop high fidelity, synthetic patient datasets presenting a significant opportunity to enhance the uptake of AI within electrophysiology, cardiology, and medicine.

Emotion Detection Through Electrocardiogram Signal Classification in an IOT Environment with Deep Neural Networks

An ECG detects the health and rhythm of the heart by measuring the electric activity of the heart. It has also been demonstrated that a person's emotions may influence the electrical activity of the heart. As a result, studying the electrical behaviour of the heart may simply determine a person's cardiac state and emotional wellness. IoT is a new technology that is quickly gaining acceptance throughout the world. Anybody, at any time, from anywhere, may connect to any network or service because to the extraordinary power and capacity of IoT. IoT-enabled devices have revolutionized the medical business by providing new capabilities such as remote patient monitoring and self-monitoring. This research proposed an IoT-based ECG monitoring system that employs a heart rate sensor to generate data and an intelligent hybrid classification algorithm to categorize the data. ECG monitoring has become a widely used method for detecting cardiac problems. The following are the primary contributions of this paper: To begin, this paper describes WISE (Wearable IoT-cloud-based health monitoring system), a one-of-a-kind system for real-time personal health monitoring. WISE makes use of the BASN (body area sensor network) technology to provide real-time health monitoring. WISE rapidly transfers data from the BASN to the cloud, and a lightweight wearable LCD may be included to enable quick access to real-time data. This model can address the issue of class imbalance in the ECG dataset, assisting in the development of an IoT-based smart and accurate healthcare system. Pre-processing, feature extraction, and classification are the three steps in any classification technique, whether it is emotion classification or heart health classification. Sensors are used to collect an ECG signal from a person's outside body. The provided ECG signal is first pre-processed using the Butterworth Filtering Method, which effectively reduces noise from the signal. Following pre-processing, the Adaptive Discrete Wavelet Transform technique is used to anticipate the signal's attributes. Lastly, a decision making classification approach based on relational weights is used to determine if the ECG signal is normal or abnormal.

Multipoint ECG Signal Extraction on Palms and Figures for Human Identification System

The ECG signal contain vital information for cardiac disease which is one of main cause of catastrophic mortality. In conventional technique, the signals are extracted through different points located on the limbs and surface of the chest. The biological impedance of human body eliminates any practical means of making fake copies of the relevant physiological traits. Moreover, this method needs the complex data acquisition system and apparatus as well as inconvenience way of acquisition of signal at the chest. Hence, there is a demand to find out the promising alternative technique to extract the ECG signals in more convenient way with high accuracy. In this paper, the real-time ECG monitor has been developed to extract the signals from the multipoint on the hands and fingers. Placement of the electrodes are done based on the acupressure point on palms and fingers. A total of 120 volunteers were investigated to develop the ECG database as the development dataset. This work uses the template matching algorithm and distance classification method to analyze and to find the best similarities between the developed dataset of ECG biometric signals to improve the identification rate. In order to lessen the noise that was recorded with the ECG signals, signal averaging was used to create ECG databases and templates. The recognition rate rose to 98% accuracy on the development dataset when the prescreening procedure was introduced to create a combined system model. ECG biometric model was created by combining the two models and using the development dataset's results. The algorithm was applied on the entire developed ECG dataset and 96% of accuracy rate was achieved in identification.

Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets.

ECG classification or heartbeat classification is an extremely valuable tool in cardiology. Deep learning-based techniques for the analysis of ECG signals assist human experts in the timely diagnosis of cardiac diseases and help save precious lives. This research aims at digitizing a dataset of images of ECG records into time series signals and then applying deep learning (DL) techniques on the digitized dataset. State-of-the-art DL techniques are proposed for the classification of the ECG signals into different cardiac classes. Multiple DL models, including a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a self-supervised learning (SSL)-based model using autoencoders are explored and compared in this study. The models are trained on the dataset generated from ECG plots of patients from various healthcare institutes in Pakistan. First, the ECG images are digitized, segmenting the lead II heartbeats, and then the digitized signals are passed to the proposed deep learning models for classification. Among the different DL models used in this study, the proposed CNN model achieves the highest accuracy of ∼92%. The proposed model is highly accurate and provides fast inference for real-time and direct monitoring of ECG signals that are captured from the electrodes (sensors) placed on different parts of the body. Using the digitized form of ECG signals instead of images for the classification of cardiac arrhythmia allows cardiologists to utilize DL models directly on ECG signals from an ECG machine for the real-time and accurate monitoring of ECGs.

Automated identification of heart arrhythmias through HRV analysis and machine learning

Sudden cardiac death and arrhythmia are responsible for about 15-20% of cardiovascular disease incidences. Conventionally, the prediction and diagnosis of cardiovascular disorders (CVDs) have been mainly through the evaluation of ECG patterns by cardiologists. To improve the accuracy of and automate this process, and facilitate early detection, Heart Rate Variability (HRV) analysis has been promoted as a diagnostic and predictive tool for CVDs. In the present study, a machine learning model capable of detecting the presence of arrhythmia, using HRV indices obtained from ECG signals was built. Unlike similar works in the literature, this study deployed the developed model on Raspberry Pi with Streamlit software. Two ECG datasets from the Physionet database, one with arrhythmia patients (48 half-hour recordings) and another with healthy individuals (18 24-hour recordings), were employed. An ensemble of seven different machine learning models was used on the two sets of datasets to classify ECG recordings into Arrhythmia and Normal Sinus Rhythm (NSR). The best models were able to predict the presence of Arrhythmia in a 3-minute recording with an accuracy of 95.96%, and in a 10-minute recording with an accuracy of 96.20%. These performance measures were calculated using test dataset. The Random Forest models also had the highest precision, AUC, (Area under the Curve) recall, and F1 scores compared to the other models tested. The highest performing model (i.e., Random Forest Model) was then deployed onto a Raspberry Pi with Streamlit as the software interface for usability. This was done to facilitate a smooth user experience for faster and seamless diagnoses for cardiologists.

Cardiovascular Disease Detection using Deep Learning

Cardiovascular diseases have surged as the leading global cause of death, necessitating a focus on early detection and continuous monitoring. This study employs deep learning, specifically the MobileNet Architecture, on a public ECG dataset to predict four cardiac abnormalities: abnormal heartbeat, myocardial infarction, history of myocardial infarction, and normal cases. The developed model demonstrates a notable training accuracy of 97.34% and validation accuracy of 91.00%, showcasing its efficacy in disease classification. With the potential to save lives and reduce healthcare costs, this algorithmic approach offers a reliable, time-efficient alternative to manual diagnosis in detecting heart disorders, providing valuable support to medical professionals..

Wavelet Scattering Transform for ECG Cardiovascular Disease Classification

Classifying the ECG dataset is the main technique for diagnosing heart disease. However, the focus of this field is increasingly on prediction, with a growing dependence on machine learning techniques. This study aimed to enhance the accuracy of cardiovascular disease classification using data from the PhysioNet database by employing machine learning (ML). The study proposed several multi-class classification models that accurately identify patterns within three classes: heart failure rhythm (HFR), normal heart rhythm (NHR), and arrhythmia (ARR). This was accomplished by utilizing a database containing 162 ECG signals. The study employed a variety of techniques, including frequency-time domain analysis, spectral features, and wavelet scattering, to extract features and capture unique characteristics from the ECG dataset. The SVM model produced a training accuracy of 97.1% and a testing accuracy of 92%. This work provides a reliable, effective, and human error-free diagnostic tool for identifying heart disease. Furthermore, it could prove to be a valuable resource for future medical research projects aimed at improving the diagnosis and treatment of cardiovascular diseases.

Dense-BiGRU: Densely Connected Bi-directional Gated Recurrent Unit based Heart Failure Detection using ECG Signal

Heart failure, a state marked by the heart's inefficiency in pumping blood adequately., can lead to serious health complications and reduced quality of life. Detecting heart failure early is crucial as it allows for timely intervention and management strategies to prevent progression and improve patient outcomes. The effectiveness of integrating ECG and AI for heart failure detection stems from AI's capacity to meticulously analyze extensive ECG datasets, facilitating the early identification of nuanced cardiac irregularities and enhancing diagnostic precision. While the current research lacks sufficient accuracy and is burdened by complexity issues. To overcome this issue, we proposed a novel Densely Connected Bi-directional Gated Recurrent Unit (Dense-BiGRU) model for accurate heart failure detection. In this work, we enhanced collected ECG signal in terms of performing multiple data pre-treatment including as denoising, powerline interference and normalization utilizing Collaborative Empirical Mode Decomposition (CEMD) algorithm, Adaptive Least Mean Square (Adaptive LMS) and min-max normalization method, respectively. Here, we utilized the LiteStream_Net layer for extracting appropriate feature from pre-processed signal. Finally, based on extracted features heart failure detection is implemented through introducing Dense-BiGRU algorithm. The proposed research is implemented using MATLAB simulation tools, and its validation is conducted through various simulation metrics including accuracy, recall, precision, F1-score, and AUC. The results of the implementation demonstrate that the proposed research surpasses existing state-of-the-art methodologies.

Abstract 14208: New Artificial Intelligence Algorithms of Electrocardiogram Detection for Patients With Heart Failure

Introduction: Heart failure (HF) is a global pandemic with an increasing prevalence. The burden of HF-related hospitalizations and costs are increasing. Artificial intelligence(AI) algorithms applied to electrocardiograms have shown promise in diagnosing HF, but they require a large amount of training data, which is scarce and costly. Transfer learning addresses this challenge by utilizing knowledge from previous tasks, resulting in superior performance with limited data compared to conventional AI algorithms Hypothesis: AI algorithms using transfer learning can be accurately diagnose heart failure with reduced ejection fraction(HFrEF) using electrocardiograms compared to conventional AI algorithms. Methods: All patients aged 18 years older from the two hospitals with at least one ECG were included in the study. Electrocardiogram, transthoracic Echocardiogram (TTE), and demographic data were collected. The AI algorithm consisted of two phases: conventional AI algorithms, pre-training with a large-scale ECG dataset and transfer learning for HFrEF detection. Performance evaluation was conducted using various metrics, including AUROC, sensitivity, specificity, accuracy, F1 score. Results: The dataset consisted of 687,911 ECGs from 259,943 patients. Testing the conventional model on the HFrEF resulted in a sensitivity of 63.8%, specificity of 96.2%, accuracy of 93.6%, area under the receiver operating curve (AUC) of 0.93 (95% CI, 0.92 - 0.94), and F1 score of 61.6%. Testing the transfer learning model on the HFrEF increased the sensitivity of 75.1%, accuracy of 93.7%, area under the receiver operating curve (AUC) of 0.952 (95% CI, 0.93 - 0.96), and F1 score of 65.6%. but lowered the specificity of 95.3% Conclusions: A New AI-enabled ECG algorithm for identifying patients with HFrEF can be more accurately diagnosed than conventional AL algorithms.

ECG based apnea detection by multirate processing hybrid of wavelet-empirical decomposition Hjorth features extraction and neural networks.

Sleep Apnea (SA) can cause health complications including heart stroke and neurological disorders. The Polysomnography (PSG) test can detect the severity of sleep disturbance. However, it is expensive and requires a dedicated sleep laboratory and expertise to examine the patients. Therefore, it is not available to a large population in developing countries. This leads to the development of cost-effective and automated patient examination methods for the detection of sleep apnea. This study suggests an approach of using the ECG signals to categorize sleep apnea. In this work, we have devised an original technique of feature space designing by intelligently hybridizing the multirate processing, a mix of wavelet-empirical mode decomposition (W-EMD), modes-based Hjorth features extraction, and Adam-based optimized Multilayer perceptron neural network (MLPNN) for automated categorization of apnea. A publicly available ECG dataset is used for evaluating the performance of the suggested approach. Experiments are performed for four different sub-bands of the considered ECG signals. For each selected sub-band, five "Intrinsic Mode Functions" (IMFs) are extracted. Onward, three Hjorth features: complexity, activity, and mobility are mined from each IMF. In this way, four feature sets are formed based on wavelet-driven selected sub-bands. The performance of optimized MLPNN, for the apnea categorization, is compared for each feature set. Five different evaluation parameters are used to assess the performance. For the same dataset, a systematic comparison with current state-of-the-artwork has been done. Results have shown a classification accuracy of 98.12%.

A filter design method based on evolutionary learning for R-peak detection in portable ECG testing devices

Portable ECG testing devices can develop individuals’ understanding of abnormal heart conditions in a timely manner and are of great value in disease prevention. R-peak detection is the first step in achieving fast and accurate ECG diagnosis. Currently, most R-peak (and QRS complex) detection algorithms target medical-grade multilead ECG measurement devices and cannot be applied to portable single-lead ECG measurement bracelets in low computing power and strong noise environments. Therefore, a filter design method for ECG R-peak detection was proposed in this paper to improve ECG quality with limited hardware resources. Besides, evolutionary learning was adopted in the filter design of the R-peak detection algorithm to reveal the optimal filter through the good global search ability of the genetic algorithm and the morphological features of the ECG. Finally, the precision, recall, and F1 score on the self-built ECG dataset reached 97.03%, 98.49%, and 97.67%, respectively, and the superiority of the method in some performance metrics compared with other excellent filters was verified.

An intelligent deep neural network with Opposition based Laplacian Equilibrium Optimizer to improve feature extraction using ECG signals

ProblemThe leading cause of death in the world is cardiovascular disease (CVD). It is required to detect, prevent and manage cardiovascular diseases to reduce their effect and improve the outcome. Interpretation of ECG signals may vary from one expert to another. That’s why an automatic categorization of ECG recordings is needed. AimThe proposed study attempted to address the above issues by developing an automated method for predicting arrhythmias based on ECG signal categorization. This method would offer more precise and enhanced interpretation of ECGs while reducing small biases brought on by manual interpretation. MethodsIn this paper, a unique deep learning-based algorithm is used to efficiently and swiftly classify cardiac arrhythmias. We have used Discrete Wavelet Transformation (DWT) to appropriately classify ECG data into important arrhythmia categories during the pre-processing stage by removing intrinsic noise from ECG signals. To obtain optimal placement (equilibrium state) for better search space diversification, OB-L-EO uses Laplace distribution followed by opposition-based modelling to modify the intensity of search agents. A powerful type of machine learning technique called deep neural network (DNN) is used to accomplish signal categorization among sixteen categories using the MIT-BIH Arrhythmia ECG dataset. ResultsWith the help of analysing classification technique including optimized feature vector and the OBLEO method with DNN, the heart rate has been detected with a 98.779% accuracy, 98.67% sensitivity, 98.87% specificity and execution time with a value of 1.34 ms across the entire dataset. The application of 10-fold cross validation provides the better accuracy i.e 99.79%. ConclusionThe achieved performance parameters have demonstrated that the suggested ECG signal classification model is capable of categorizing arrhythmia classes appropriately using ECG signals.

A Deep Convolutional Model for Heart Disease Prediction based on ECG Data with Explainable AI

Heart disease (HD) prediction is crucial in realizing the notion of intelligent healthcare owing to the exploding number of heart diseases being reported on a daily basis. However, in a domain like healthcare, accountability is key for a medical practitioner to completely adopt the decisions of an intelligent model. Accordingly, the proposed model develops a convolutional model for heart disease prediction based on ECG data in a supervised manner. Moreover, the easily accessible and economical ECG data is utilized in the model in the form of image data. The incorporation of ECG data as images has provided amazing results in the recent researches compared to being considered as signals. The architecture follows a stacked Convolutional Neural Network for extracting features from ECG images followed by fully connected network for classification. The evaluation of the proposed model on customized public datasets demonstrates its ability to achieve impressive outcomes by leveraging the characteristics of convolutional neural networks (CNNs) and supervised learning. Similarly, Explainability in the form of interpretability has been incorporated into the framework thus ensuring accountability of the model which is crucial in medical domain. Detailed experiments for identification of ideal model architecture are conducted. Further, local and vision based Explainability has been explored in detail using LIME and Grad-CAM. The model could achieve a precision, recall and f1-score of 0.982, 0.982, and 0.981 respectively proving the superiority of the model. Moreover, Explainability visualization based on popular algorithms for true positive and false positive results have shown promising results on the PhysioNet ECG dataset.

TSMAE: A Novel Anomaly Detection Approach for Internet of Things Time Series Data Using Memory-Augmented Autoencoder

With the development of the Internet of Things, it has been widely studied and deployed in industrial manufacturing, intelligent transportation, and healthcare systems. The time-series feature of the IoT makes the data density and the data dimension higher, where anomaly detection is important to ensure hardware and software security. However, the traditional anomaly detection algorithm has difficulty meeting this demand, not only in complexity but also accuracy. Sometimes the anomaly can be well reconstructed, resulting in a low reconstruction error. In this paper, we propose a memory-augmented autoencoder approach for detecting anomalies in IoT data, which aims to use reconstruction errors to determine data anomalies. First, a memory mechanism is introduced to suppress the generalization ability of the model, and a memory-augmented autoencoder TSMAE is designed for time-series data anomaly detection. Second, by adding penalties and derivable rectifier functions to loss to make the addressing vector sparse, memory modules are encouraged to extract typical normal patterns, thus inhibiting model generalization ability. Finally, through experiments on ECG and Wafer datasets, the validity of TSMAE is verified, and the rationality of hyperparameter setting is discussed through visualizing the memory module addressing vector.