Deep learning-based multidimensional feature fusion for classification of ECG arrhythmia

Cui, Jianfeng; Wang, Lixin; He, Xu; Albuquerque, Victor Hugo C. de; AlQahtani, Salman A.; Hassan, Mohammad Mehedi

doi:10.1007/s00521-021-06487-5

Cited by 24 publications

(13 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two most often used neural network models are CNN and LSTM. Cui et al [ 33 ] proposed a feature extraction method that combines traditional classification methods and CNN to improve the accuracy of arrhythmia classification by finding the best feature set. Acharya et al [ 34 ] created a 9-layer CNN model that uses an ECG segment as an input to automatically categorize arrhythmias into five types.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification and Classification Algorithms

Cui

Xiao

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Automated ECG-based arrhythmia detection is critical for early cardiac disease prevention and diagnosis. Recently, deep learning algorithms have been widely applied for arrhythmia detection with great success. However, the lack of labeled ECG data and low classification accuracy can have a significant impact on the overall effectiveness of a classification algorithm. In order to better apply deep learning methods to arrhythmia classification, in this study, feature extraction and classification strategy based on generative adversarial network data augmentation and model fusion are proposed to address these problems. First, the arrhythmia sparse data is augmented by generative adversarial networks. Then, aiming at the identification of different types of arrhythmias in long-term ECG, a spatial information fusion model based on ResNet and a temporal information fusion model based on BiLSTM are proposed. The model effectively fuses the location information of the nearest neighbors through the local feature extraction part of the generated ECG feature map and obtains the correlation of the global features by autonomous learning in multiple spaces through the BiLSTM network in the part of the global feature extraction. In addition, an attention mechanism is introduced to enhance the features of arrhythmia-type signal segments, and this mechanism can effectively focus on the extraction of key information to form a feature vector for final classification. Finally, it is validated by the enhanced MIT-BIH arrhythmia database. The experimental results demonstrate that the proposed classification technique enhances arrhythmia diagnostic accuracy by 99.4%, and the algorithm has high recognition performance and clinical value.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification and Classification Algorithms

Cui

Xiao

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…The model proposed by Cui et al [10] achieves an average accuracy of 98.35% and per-class precision and recall scores of more than 98%. The authors claim that the proposed model can be used for real-time ECG monitoring but do not provide supportive evidence.…”

Section: B Model Optimization and Testing At The Edgementioning

confidence: 99%

“…The most commonly used methods are support vector machines (SVMs) and deep neural networks (DNNs). SVMs models with various feature types have been extensively used for ECG classification [10,6,3,5] yet such models suffer from the computational complexity of the SVM algorithm. On the other hand, many recent works proposed various topologies of 1D and 2D CNNs in conjunction with different feature spaces for ECG classification [11,12,13,11,3,5].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Many recent works other than the STFT-based CNNs have been also proposed for ECG classification and arrhythmia detection. Cui et al [10] proposed an ECG feature extraction method based on DWT and Conv1D with Principle Component Analysis (PCA) to reduce the number of features. An SVM classifier is trained on an upsampled subset of the MIT-BIH dataset to address dataset imbalance.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A Self-Contained STFT CNN for ECG Classification and Arrhythmia Detection at the Edge

Farag

2022

IEEE Access

View full text Add to dashboard Cite

Automated classification of Electrocardiogram (ECG) for arrhythmia monitoring is the core of cardiovascular disease diagnosis. Machine Learning (ML) is widely used for arrhythmia detection using various feature engineering and classification models. Cloud-based inference is the prevailing deployment model of modern ML algorithms which does not always meet the availability and privacy requirements of ECG monitoring. Edge inference is an emerging alternative which addresses the concerns of latency, privacy, connectivity, and availability. However, edge deployment of AI models is challenging due to the demanding requirements of modern ML algorithms and the computation constraints of edge devices. In this work, we propose a lightweight self-contained short-time Fourier Transform (STFT) Convolutional Neural Network (CNN) model for ECG classification and arrhythmia detection in real-time at the edge. We provide a clear interpretation of the convolutional layer as a Finite Impulse Response (FIR) filter and exploit this interpretation to develop an STFT-based 1D convolutional (Conv1D) layer to extract the spectrogram of the input ECG signal. The Conv1D output feature maps are reshaped into a 2D heatmap and fed to a 2D convolutional (Conv2D) neural network (CNN) for classification. The real-time performance of the proposed model is planned in advance to fit the resource constraints of edge inference. Four model variants are trained, optimized, and tested on a raspberry-pi edge device. Weight quantization and pruning techniques are applied to the developed models to optimize them for edge computing. The MIT-BIH arrhythmia database is used for model training and testing. The proposed classifiers can achieve up to 99.1% classification accuracy and 95% F1-score at the edge with a maximum model size of 90 KB, an average inference time of 9 ms, and a maximum memory usage of 12 MB. The achieved results of the proposed classifier enable its deployment on a wide range of edge devices for arrhythmia detection.

show abstract

“…Therefore, more deep learning methods are used for the classification of ECG signals. Cui et al [22] used convolutional neural network (CNN) and support vector machine (SVM) to classify ECG signals, thereby to diagnosis the status of heart. Zeng et al [23] performed variational pattern decomposition (VMD) of the ECG signal and fed it into an artificial neural network (ANN) to achieve the identification of five heartbeat types.…”

Section: Introductionmentioning

confidence: 99%

Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network

Wang

Chen

Liu

et al. 2023

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

Electrocardiogram (ECG) signals are often used to diagnose cardiac status. However, most of the existing ECG diagnostic methods only use the time-domain information, resulting in some obviously lesion information in frequency-domain of ECG signals are not being fully utilized. Therefore, we propose a method to fuse the time and frequency domain information in ECG signals by convolutional neural network (CNN). First, we adapt multi-scale wavelet decomposition to filter the ECG signal; Then, R-wave localization is used to segment each individual heartbeat cycle; And then, the frequency domain information of this heartbeat cycle is extracted via fast Fourier transform. Finally, the temporal information is spliced with the frequency domain information and input to the neural network for classification. The experimental results show that the proposed method has the highest recognition accuracy (99.43%) of ECG singles compared with state-of-the-art methods.

show abstract

Deep learning-based multidimensional feature fusion for classification of ECG arrhythmia

Cited by 24 publications

References 53 publications

Deep Learning-Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification and Classification Algorithms

Deep Learning-Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification and Classification Algorithms

A Self-Contained STFT CNN for ECG Classification and Arrhythmia Detection at the Edge

Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network

Contact Info

Product

Resources

About