A Semi-Supervised TCN-LSTM Model for Single Lead ECG Heartbeat Classification

Electrocardiogram (ECG) heartbeat classification plays a vital role in early diagnosis and effective treatment, which provide opportunities for earlier prevention and intervention. In an effort to continuously monitor and detect abnormalities in patients’ ECG signals on portable devices, this paper present a lightweight ECG heartbeat classification method based on a spiking neural network (SNN), a relatively shallow SNN model integrated with a channel-wise attentional module. We further explore the best-optimized architecture, which benefits from leveraging the full advantages of the SNN potential with the attention mechanism to process the classification task at low power and capture prominent features concerning the time, morphology, and multi-channel representations of the ECG signal. Results show that our model achieves overall classification accuracy of 98.26%, sensitivity of 94.75%, and F1 score of 89.09% on the MIT-BIH database, with energy consumption of 346.33 μJ per beat and runtime of 1.37 ms. Moreover, we have conducted multiple experiments to compare against current state-of-the-art methods using their assessment strategies to evaluate our model implementation on FPGA. So far, our work achieves comparable overall performance with all the literature in terms of classification accuracy, energy consumption, and real-time capability.

Automated classification of cardiac rhythms from electrocardiogram (ECG) signals is significant for diagnosis of cardiovascular dysfunctioning. A biggest challenge in automated ECG classification is to address the task's specific characteristics, such as time dependencies between observations and a strong class imbalance. To address these issues, this work proposes machine learning ensemble techniques (Random Forest, Support Vector Machine, Xgboost, Adaboost and Stacked Ensemble Classifier) and an ensemble of convolutional neural network (CNN) and bi-directional long short-term memory (Bi-LSTM) architecture for classification of cardiac arrhythmias in ECG signals. The proposed model has been trained and tested on the MIT-BIH arrhythmias database which contains total 109443 ECG beats with 90589 normal beats (NB), 8039 supraventricular beats (SB), 7236 ventricular beats (VB), 2776 fusion beats (FB) and 803 unknown beats (QB) respectively. Here, in this study, we incorporate synthetic minority oversampling technique (SMOTE) for balancing dataset along with time-series feature extraction library (TSFEL) for extracting feature and an ensemble of CNN-LSTM to predict fast features of upcoming ECG signals to enhance the performance of heartbeat classification as compare to the state-of-the-art techniques. The achieved average accuracy (Acc), sensitivity (SE), precision (PE) and F1 score using stacked ensemble machine learning algorithm for detection arrhythmias heartbeat classes are 98.67%, 96%, 97.80% and 96.80% respectively. With ensemble CNN-BiLSTM method, the average accuracy of 99.88% has been achieved. The SE and PE values for SB and VB beats are 84.40%, 99.79%, 96.40% and 98.54% respectively. Experimental results demonstrate that an ensemble CNN-BiLSTM technique outperforms as compare to existing classification techniques in terms sensitivity, accuracy and precision.

A deep convolutional neural network model to classify heartbeats

Abstract. The present work proposes a prediction model of significant wave height (SWH) and average wave period (APD) based on variational mode decomposition (VMD), temporal convolutional networks (TCNs), and long short-term memory (LSTM) networks. The wave sequence features were obtained using VMD technology based on the wave data from the National Data Buoy Center. Then the SWH and APD prediction models were established using TCNs, LSTM, and Bayesian hyperparameter optimization. The VMD–TCN–LSTM model was compared with the VMD–LSTM (without TCN cells) and LSTM (without VMD and TCN cells) models. The VMD–TCN–LSTM model has significant superiority and shows robustness and generality in different buoy prediction experiments. In the 3 h wave forecasts, VMD primarily improved the model performance, while the TCN had less of an influence. In the 12, 24, and 48 h wave forecasts, both VMD and TCNs improved the model performance. The contribution of the TCN to the improvement of the prediction result determination coefficient gradually increased as the forecasting length increased. In the 48 h SWH forecasts, the VMD and TCN improved the determination coefficient by 132.5 % and 36.8 %, respectively. In the 48 h APD forecasts, the VMD and TCN improved the determination coefficient by 119.7 % and 40.9 %, respectively.

Electrocardiogram signal classification for automated delineation using bidirectional long short-term memory

A novel P-QRS-T wave localization method in ECG signals based on hybrid neural networks

Accurate and real-time prediction of network traffic can not only help system operators allocate resources rationally according to their actual business needs but also help them assess the performance of a network and analyze its health status. In recent years, neural networks have been proved suitable to predict time series data, represented by the model of a long short-term memory (LSTM) neural network and a temporal convolutional network (TCN). This article proposes a novel hybrid prediction method named SG and TCN-based LSTM (ST-LSTM) for such network traffic prediction, which synergistically combines the power of the Savitzky–Golay (SG) filter, the TCN, as well as the LSTM. ST-LSTM employs a three-phase end-to-end methodology serving time series prediction. It first eliminates noise in raw data using the SG filter, then extracts short-term features from sequences applying the TCN, and then captures the long-term dependence in the data exploiting the LSTM. Experimental results over real-world datasets demonstrate that the proposed ST-LSTM outperforms state-of-the-art algorithms in terms of prediction accuracy. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This work considers real-time and high-accuracy prediction of network traffic. It is highly important to well predict network traffic by capturing long-term dependence and effectively extracting high- and low-frequency information from time series data. Yet, it is a big challenge to achieve it because there are unstable characteristics and strong nonlinear features in the network traffic due to continuous expansion of network scale and fast emergence of new services. Current prediction methods usually have oversimplified theoretical assumptions, need significant time and memory, or suffer problems of gradient disappearance or early convergence. Thus, they fail to effectively capture the nonlinear characteristics of large-scale network sequences. This work proposes a hybrid prediction method named SG and TCN-based LSTM (ST-LSTM), which integrates the merits of the Savitzky–Golay filter, the temporal convolutional network (TCN), and the long short-term memory (LSTM), serving as smoothing time series, capturing short-term local features, and capturing long-term dependence, respectively. Experimental results based on the real-life dataset demonstrate that it achieves better prediction accuracy than its state-of-the-art peers, including the TCN and the LSTM. It can be readily implemented and deployed in many real-life industrial areas including smart city, edge computing, cloud computing, and data centers.

Effective and powerful methods for denoising real electrocardiogram (ECG) signals are important for wearable sensors and devices. Deep Learning (DL) models have been used extensively in image processing and other domains with great success but only very recently have been used in processing ECG signals. This paper presents several DL models namely Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Restricted Boltzmann Machine (RBM) together with the more conventional filtering methods (low pass filtering, high pass filtering, Notch filtering) and the standard wavelet-based technique for denoising EEG signals. These methods are trained, tested and evaluated on different synthetic and real ECG datasets taken from the MIT PhysioNet database and for different simulation conditions (i.e. various lengths of the ECG signals, single or multiple records). The results show the CNN model is a performant model that can be used for off-line denoising ECG applications where it is satisfactory to train on a clean part of an ECG signal from an ECG record, and then to test on the same ECG signal, which would have some high level of noise added to it. However, for real-time applications or near-real time applications, this task becomes more cumbersome, as the clean part of an ECG signal is very probable to be very limited in size. Therefore the solution put forth in this work is to train a CNN model on 1 second ECG noisy artificial multiple heartbeat data (i.e. ECG at effort), which was generated in a first instance based on few sequences of real signal heartbeat ECG data (i.e. ECG at rest). Afterwards it would be possible to use the trained CNN model in real life situations to denoise the ECG signal.

An explainable attention-based TCN heartbeats classification model for arrhythmia detection

In this paper, we proposed a classification method based on a nature-inspired algorithm, i.e., modified artificial bee colony (MABC). This method was applied to electrocardiogram (ECG) heartbeat classification. ECG data was obtained from MITBIH database. Eight different types of heartbeats (N, j, V, F, f, A, a, and R) were analyzed. For a better classification result, both time domain and frequency domain features were used. Feature selection was done by divergence analysis. MABC classification accuracy and heartbeat sensitivity values were compared with the results of other methods. Among other classifiers, k-nearest neighbor (KNN), Kohonen's self-organizing map (SOM), and ant colony optimization (ACO) were the best performing ones, and therefore their results are presented. The MABC classifier achieved 97.18 % accuracy on the analyzed dataset, as well as high sensitivity values for heartbeat types.

Accurate detection of cardiac pathological events is an important part of electrocardiogram (ECG) evaluation and subsequent correct treatment of the patient. For this purpose, several adaptive filter structures were proposed during the past decades for noise cancellation and arrhythmia detection. Currently there are a lot of devices on the market that analyze ECGs, such as patient monitors, stress test systems, and Holter analysis systems, that are able to detect beats and classify arrhythmia. This paper proposes a system for ECG analysis and heartbeat classification. The proposed solution relies on a combination of machine learning algorithm and a wavelet transformation in order to maximize its performance with the minimum possible training phase. Experimental results with public available data for arrhythmia indicate the efficiency in classifying heartbeats, whereas its low-computational and memory requirements makes it suitable for being implemented as part of an embedded (IoT) system.

Cardiovascular diseases (CVDs) are the number one cause of death today. Therefore, the early detection of arrhythmia is very important for cardiac patients. This paper proposes the heartbeat classification algorithm using the electrocardiogram(ECG) signals. An ECG is a 1D signal that is the result of recording the electrical activity of the heart using an electrode. In this paper, a single-layer Tensorflow LSTM model has been proposed to classify a biological time-series consisting of normal and abnormal heartbeats. The method was evaluated using the publicly available Physio net's MIT-BIH Arrhythmia dataset. The dataset has been divided into training and testing data. As a result, the classifier achieved a 95% average accuracy. Compared with the other CNN and RNN models used for the heartbeat classification, the simulation result shows the proposed algorithm has higher accuracy.

Traditional machine learning models are common to classify Electrocardiogram (ECG) signals. In comparison, ECG prediction with such models is rare. The proposed work aims to predict the RR Interval (RRI) for a 10 sec. Normal Sinus Rhythm (NSR) ECG signals by designing and developing a Long Short Term Memory (LSTM)-Recurrent Neural Network (RNN) based model. The ECG signals from the Chapman University and Shaoxing People's hospital have 10 sec. of sample data of each patient used in this study. Signal processing techniques to detect the R-peaks and RRI were calculated further and provided as the model's input. LSTM-RNN model based on univariate time series predicted the RRI for the subsequent 20 ECG cycles. The model underwent 500 epochs of training before the accurate ECG prediction. The model's error value started at 0.8 and ended at 0.000001, which provided a good fit for the predicted data. The LSTM-RNN model predicted the RRI from the 10th to the 30th ECG cycle based on 9 RRI. The model's error rate decreased exponentially as the epoch's number increased, stating the model's accuracy, helping to determine the intra-individual Heart Rate Variability (HRV).

The intrinsic and liveness detection behavior of electrocardiogram (ECG) signals has made it an emerging biometric modality for the researcher with several applications including forensic, surveillance and security. The main challenge is the low recognition performance with datasets of large populations, including healthy and heart-disease patients, with a short interval of an ECG signal. This research proposes a novel method with the feature-level fusion of the discrete wavelet transform and a one-dimensional convolutional recurrent neural network (1D-CRNN). ECG signals were preprocessed by removing high-frequency powerline interference, followed by a low-pass filter with a cutoff frequency of 1.5 Hz for physiological noises and by baseline drift removal. The preprocessed signal is segmented with PQRST peaks, while the segmented signals are passed through Coiflets' 5 Discrete Wavelet Transform for conventional feature extraction. The 1D-CRNN with two long short-term memory (LSTM) layers followed by three 1D convolutional layers was applied for deep learning-based feature extraction. These combinations of features result in biometric recognition accuracies of 80.64%, 98.81% and 99.62% for the ECG-ID, MIT-BIH and NSR-DB datasets, respectively. At the same time, 98.24% is achieved when combining all of these datasets. This research also compares conventional feature extraction, deep learning-based feature extraction and a combination of these for performance enhancement, compared to transfer learning approaches such as VGG-19, ResNet-152 and Inception-v3 with a small segment of ECG data.

The distortion of the electrocardiogram by capacitance