Improved Neural Network Arrhythmia Classification Through Integrated Data Augmentation

Cayce, Garrett I.; Depoian, Arthur C.; Bailey, Colleen P.; Guturu, Parthasarathy

doi:10.1109/metrocon56047.2022.9971141

Cited by 5 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of MHATT is compared against a four layer convolutional neural network (4LCNN), 10 a 4LCNN with multi-head attention (MH), and a 4LCNN with MH and data augmentation (DA). 9 The results of the highest performing models from sets of 100 isolated models of each type are contained in Table 1. Multiple instances of MHATT achieved higher results for accuracy than any of the comparable architectures, demonstrating that the proposed network is a robust improvement.…”

Section: Resultsmentioning

confidence: 99%

Augmented multi-head classification network: MHATT

Cayce

Depoian

Bailey

et al. 2023

Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII

View full text Add to dashboard Cite

Classification of one-dimensional (1D) data is important for a variety of complex problems. From the finance industry to audio processing to the medical field, there are many industries that utilize 1D data. Machine learning techniques have excelled at solving these classification problems, but there is still room for improvement because the techniques have not been perfected. This paper proposes a novel architecture called Multi-Head Augmented Temporal Transformer (MHATT) for 1D classification of time-series data. Highly modified vision transformers were used to improve performance while keeping the network exceptionally efficient. To showcase its efficacy, the network is applied to heartbeat classification using the MIT-BIH OSCAR dataset. This dataset was ethically-split to ensure a fair and intensive test for networks. The novel architecture is 94.6% more efficient and had a peak accuracy of 91.79%, which was a 13.6% reduction in error over a recent state-of-the-art network. The impressive performance and efficiency of the MHATT architecture can be exploited by edge devices for unmatched performance and flexibility of deployment.

show abstract

Section: Resultsmentioning

confidence: 99%

Augmented multi-head classification network: MHATT

Cayce

Depoian

Bailey

et al. 2023

Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII

View full text Add to dashboard Cite

show abstract

“…Basic data augmentation techniques encompass flipping, snipping, and introducing noise. In addition to these techniques, some other basic data augmentation techniques such as spatial inversion [11], time-spatial inversion [6], baseline wandering [20] are also applied to ECG signals. However, when it comes to the management of complex data such as medical imaging, these basic techniques are inadequate.…”

Section: Literature Reviewmentioning

confidence: 99%

A Generative Model for Deep Fake Augmentation of Phonocardiogram and Electrocardiogram Signals Using Lsgan and Cycle Gan

Rayavarapu,

Prasanthi,

Kumar

et al. 2023

IAPGOS

View full text Add to dashboard Cite

In order to diagnose a range of cardiac conditions, it is important to conduct an accurate evaluation of either phonocardiogram (PCG) and electrocardiogram (ECG) data. Artificial intelligence and machine learning-based computer-assisted diagnostics are becoming increasingly commonplace in modern medicine, assisting clinicians in making life-or-death decisions. The requirement for an enormous amount of information for training to establish the framework for a deep learning-based technique is an empirical challenge in the field of medicine. This increases the risk of personal information being misused. As a direct result of this issue, there has been an explosion in the study of methods for creating synthetic patient data. Researchers have attempted to generate synthetic ECG or PCG readings. To balance the dataset, ECG data were first created on the MIT-BIH arrhythmia database using LS GAN and Cycle GAN. Next, using VGGNet, studies were conducted to classify arrhythmias for the synthesized ECG signals. The synthesized signals performed well and resembled the original signal and the obtained precision of 91.20%, recall of 89.52% and an F1 score of 90.35%.

show abstract

“…Therefore, it is necessary to collect ECG data from various electrode placements. However, this process requires multiple attempts and consumes a considerable amount of labor and time [15][16][17][18][19]. Despite the effort required, persisting with these endeavors helps address the differences in ECG signals [20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Domain Adaptation for Individual Identification from Electrocardiogram Signals

Byeon,

Kwak

2023

Applied Sciences

View full text Add to dashboard Cite

When acquiring electrocardiogram (ECG) signals, the placement of electrode patches is crucial for acquiring electrocardiographic signals. Constant displacement positions are essential for ensuring the consistency of the ECG signal when used for individual identification. However, achieving constant placement of ECG electrode patches in every trial for data acquisition is challenging. This is because different individuals may attach patches, and even when the same person attaches them, it may be difficult to specify the exact position. Therefore, gathering ECG data from various locations is necessary. However, this process requires a substantial amount of labor and time, owing to the requirement for multiple attempts. Nonetheless, persisting with these efforts enables the endurance of some ECG differences. To reduce labor and time, we propose a semi-supervised domain adaptation for individual identification using ECG signals. The method operates with a full set of original ECG signals and a small set of ECG signals from different placements to account for the differences between the signals in the generative adversarial network (CycleGAN). Specifically, to train the CycleGAN, the ECG signals were transformed into time–frequency representations, and the trained generator was used to generate ECG signals to expand the small set of ECG signals from different placements. Subsequently, both the original and generated signals were used to train the classifier for individual identification. This scenario can also be applied to the classification of ECG signals from different sensors. The PTB-ECG dataset was used for this experiment. We found that the proposed method showed higher accuracy than when only the original ECG signals were used for the training classifier.

show abstract

Improved Neural Network Arrhythmia Classification Through Integrated Data Augmentation

Cited by 5 publications

References 5 publications

Augmented multi-head classification network: MHATT

Augmented multi-head classification network: MHATT

A Generative Model for Deep Fake Augmentation of Phonocardiogram and Electrocardiogram Signals Using Lsgan and Cycle Gan

Semi-Supervised Domain Adaptation for Individual Identification from Electrocardiogram Signals

Contact Info

Product

Resources

About