Deep Learning-Based Stacked Denoising and Autoencoder for ECG Heartbeat Classification

Abstract

The electrocardiogram (ECG) is a widely used, noninvasive test for analyzing arrhythmia. However, the ECG signal is prone to contamination by different kinds of noise. Such noise may cause deformation on the ECG heartbeat waveform, leading to cardiologists’ mislabeling or misinterpreting heartbeats due to varying types of artifacts and interference. To address this problem, some previous studies propose a computerized technique based on machine learning (ML) to distinguish between normal and abnormal heartbeats. Unfortunately, ML works on a handcrafted, feature-based approach and lacks feature representation. To overcome such drawbacks, deep learning (DL) is proposed in the pre-training and fine-tuning phases to produce an automated feature representation for multi-class classification of arrhythmia conditions. In the pre-training phase, stacked denoising autoencoders (DAEs) and autoencoders (AEs) are used for feature learning; in the fine-tuning phase, deep neural networks (DNNs) are implemented as a classifier. To the best of our knowledge, this research is the first to implement stacked autoencoders by using DAEs and AEs for feature learning in DL. Physionet’s well-known MIT-BIH Arrhythmia Database, as well as the MIT-BIH Noise Stress Test Database (NSTDB). Only four records are used from the NSTDB dataset: 118 24 dB, 118 −6 dB, 119 24 dB, and 119 −6 dB, with two levels of signal-to-noise ratio (SNRs) at 24 dB and −6 dB. In the validation process, six models are compared to select the best DL model. For all fine-tuned hyperparameters, the best model of ECG heartbeat classification achieves an accuracy, sensitivity, specificity, precision, and F1-score of 99.34%, 93.83%, 99.57%, 89.81%, and 91.44%, respectively. As the results demonstrate, the proposed DL model can extract high-level features not only from the training data but also from unseen data. Such a model has good application prospects in clinical practice.

Stages-Based ECG Signal Analysis From Traditional Signal Processing to Machine Learning Approaches: A Survey

“…Deep learning has great potential of applications in cardiology such as ECG arrhythmia detection with Deep-CNN [71], [72], [74], [76], [77], [79], [80], Robust Deep Dictionary Language (RDDL) [73], Deep Brief Network with Restricted Boltzmann Machine (DBN+RBM) [75] and Deep Neural Network (DNN) [78]. MI detection is performed with Deep-CNN [81] and Deep Neural Network (DNN) [82] while detecting heartbeats is performed by DNN in [83]. There is a variety of neural networks; LeCun et al [6] presented a detailed introduction to deep learning.…”

Recommendation System Using Autoencoders

“…An autoencoder is an unsupervised deep learning method that learns how to effectively compress and encode data, and then reconstructs data from a reduced encoded representation to a representation that is identical to the original input. In another words, an autoencoder is a neural network that applies back-propagation, setting the target values (outputs) to be equal to the inputs [30,44].…”

“…where S f is an activation function, n is the number of neurons in the input layer, and m is the number of neurons in the hidden layer. The encoder is parameterized by a m × n weight matrix W and a bias vector b ∈ R m [27,44]. Then, the decoder maps the hidden representation h back to a reconstruction x = {x 1 , x 2 , ..., x n } by a function g:…”

“…where S g represents the decoder's activation function. The decoder's parameters are comprised of a bias vector b ∈ R n and a n × m weight matrix W [27,44]. The purpose of an autoencoder is to obtain d dimensional representation of data such that an error measure between x and u(x) = decode(encode(x)) is minimized [45].…”

Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model

“…The employment of computer-aided diagnosis systems optimized the performance of the breast cancer diagnosis [9]. Recently, Deep Learning (DL) has played the main role in several medical tasks [10][11][12][13], and the classification and detection of breast cancer [14,15]. The breast cancer classification task is challenging due the complexity of the breast cancer images.…”