An Automated ECG Beat Classification System Using Convolutional Neural Networks

Zubair, Muhammad; Kim, Jinsul; Yoon, Changwoo

doi:10.1109/icitcs.2016.7740310

Cited by 173 publications

(110 citation statements)

References 20 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…The algorithms provide a very in-depth analysis for an artificial real-time cardiac imaging with better spatial and temporal resolution. It potentially improves the quality of health caring and reducing costs [15][16][17][18][19]. Such algorithms can be trained using an unsupervised learning approach with unlimited memory [9,20,21] and, it is also suitable for noisy data [5,15,16].…”

Section: Introductionmentioning

confidence: 99%

An Automated ECG Beat Classification System Using Deep Neural Networks with an Unsupervised Feature Extraction Technique

et al. 2019

View full text Add to dashboard Cite

An automated classification system based on a Deep Learning (DL) technique for Cardiac Disease (CD) monitoring and detection is proposed in this paper. The proposed DL architecture is divided into Deep Auto-Encoders (DAEs) as an unsupervised form of feature learning and Deep Neural Networks (DNNs) as a classifier. The objective of this study is to improve on the previous machine learning technique that consists of several data processing steps such as feature extraction and feature selection or feature reduction. It is also noticed that the previously used machine learning technique required human interference and expertise in determining robust features, yet was time-consuming in the labeling and data processing steps. In contrast, DL enables an embedded feature extraction and feature selection in DAEs pre-training and DNNs fine-tuning process directly from raw data. Hence, DAEs is able to extract high-level of features not only from the training data but also from unseen data. The proposed model uses 10 classes of imbalanced data from ECG signals. Since it is related to the cardiac region, abnormality is usually considered for an early diagnosis of CD. In order to validate the result, the proposed model is compared with the shallow models and DL approaches. Results found that the proposed method achieved a promising performance with 99.73% accuracy, 91.20% sensitivity, 93.60% precision, 99.80% specificity, and a 91.80% F1-Score. Moreover, both the Receiver Operating Characteristic (ROC) curve and the Precision-Recall (PR) curve from the confusion matrix showed that the developed model is a good classifier. The developed model based on unsupervised feature extraction and deep neural network is ready to be used on a large population before its installation for clinical usage.

show abstract

Section: Introductionmentioning

confidence: 99%

An Automated ECG Beat Classification System Using Deep Neural Networks with an Unsupervised Feature Extraction Technique

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Convolution neural networks are of two parts. The irst part is feature extraction which automatically extracts the features from raw input signal while the second part is a fully connected multi-layer perceptron (MLP) which performs classi ication based on the learned features from the irst part (Zubair et al, 2016). The developed system consists of seven layers, including an input layer.…”

Section: (Iii) Convolution Neural Networkmentioning

confidence: 99%

“…Classi ication of ECG becomes dif icult due to the difference in morphological characteristics of basic ECG patterns of various patients (Zubair et al, 2016). The ECG waveforms are also similar for multiple patients having different heart beats and should show a difference, especially between things that should be the same for the identical patient at different time.…”

Section: Introductionmentioning

confidence: 99%

Convolution Neural Network Based Ecg Classifier

Sharanya¹,

Pa²,

Poornakala³

et al. 2019

ijrps

View full text Add to dashboard Cite

Classi ication of Electrocardiogram (ECG) signals plays a signi icant role in the identi ication of the functioning of the heart. This work pertains with the ECG signals, where the classi ier is developed for identi ication of normal or abnormal conditions of the heart. The raw ECG signals are collected from an online database (www.physioNet.org) for classi ication. The raw ECG signal is pre-processed for noise removal, and the frequency spectrum is analysed to compare raw and denoised ECG signal. Attributes (P, Q, R, S, T time intervals) from denoised ECG signal is analysed and classi ied using Convolution Neural Network (CNN). The paper reports a classi ication technique to differentiate ECG signals from the MIT-BIH database (arrhythmia database, arrhythmia pwave annotations, atrial ibrillation). The CNN analyses the deviation between nominal ranges of attributes (amplitude and time interval) and classi ies between the abnormality and normal ECG wave. This work provides a simple method for interpreting ECG related condition for the clinician and helps medical practitioners to make diagnostic decisions.

show abstract

“…The author shows accuracies ranging from 86.39% to 99.77% while using the publicly available ECG database. Zubair et al [30] propose a ECG classification method using convolution neural networks. The model extracts hidden features from raw ECG signals.…”

Section: Heartbeat Classification With Automatic Feature Extraction Umentioning

confidence: 99%

Power-Accuracy Trade-Offs for Heartbeat Classification on Neural Networks Hardware

Balaji¹,

Corradi²,

Das³

et al. 2018

Journal of Low Power Electronics

View full text Add to dashboard Cite

Heartbeat classification using electrocardiogram (ECG) data is an essential feature of modern day wearable devices. State-of-the-art machine learning-based heartbeat classifiers are designed using convolutional neural networks (CNN). Despite their high classification accuracy, CNNs require significant computational resources and power. This makes the mapping of CNNs on resource-and power-constrained wearable devices challenging. In this paper, we propose heartbeat classification using spiking neural networks (SNN), an alternative approach based on a biologically inspired, event-driven neural networks. SNNs compute and transfer information using discrete spikes that require fewer operations and less complex hardware resources, making them energy-efficient compared to CNNs. However, due to complex error-backpropagation involving spikes, supervised learning of deep SNNs remains challenging. We propose an alternative approach to SNN-based heartbeat classification. We start with an optimized CNN implementation of the heartbeat classification task and then convert the CNN operations, such as multiply-accumulate, pooling and softmax, into spiking equivalent with a minimal loss of accuracy. We evaluate the SNN-based heartbeat classification using publicly available ECG database of the Massachusetts Institute of Technology and Beth Israel Hospital (MIT/BIH), and demonstrate a minimal loss in accuracy when compared to 85.92% accuracy of a CNN-based hearbeat classification. We demonstrate that, for every operation, the activation of SNN neurons in each layer is sparse when compared to CNN neurons, in the same layer. We also show that this sparsity increases with an increase in the number of layers of the neural network. In addition, we detail the power-accuracy trade-off of the SNN and show a 87.76% and 96.82% reduction in SNN neuron and synapse activity,respectively, for accuracy loss ranging between 0.6% and 1.00%, when compared to a CNN-only implementation.

show abstract

An Automated ECG Beat Classification System Using Convolutional Neural Networks

Cited by 173 publications

References 20 publications

An Automated ECG Beat Classification System Using Deep Neural Networks with an Unsupervised Feature Extraction Technique

An Automated ECG Beat Classification System Using Deep Neural Networks with an Unsupervised Feature Extraction Technique

Convolution Neural Network Based Ecg Classifier

Power-Accuracy Trade-Offs for Heartbeat Classification on Neural Networks Hardware

Contact Info

Product

Resources

About