Implementation of One-Dimensional Convolutional Neural Network for Individual Identification Based on ECG Signal

Yuniarti, Ana Rahma; Rizal, Syamsul

doi:10.1007/978-981-19-1804-9_26

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the explanation above, research related to ECG with an artificial neural network approach can be presented in Table 5. [68] ANN (Levenberg-Marquardt) PhysioNet 2021 [2] ANN 2021 [69] Multilayered Perceptron Accuracy: 98,89 % PhysioNet 2022 [3] ANN Accuracy: 92,47 % UCI 2022 [70] Backpropagation Accuracy: 87 % 2022 [71] Multi-Layer Perceptron PhysioNet 2022 [39] CNN Accuracy: 92 % PhysioNet 2022 [72] Convolution Neural Networks Cardiovascular Department of Azienda Sanitaria Universitaria Giuliano Isontina (ASUGI) in Trieste, Italy…”

Section: Identification and Performancementioning

confidence: 99%

Application of Artificial Neural Networks in the Identification of Heart Abnormalities Based on Ecg: Literature Review

2023

ETJ

View full text Add to dashboard Cite

In recent years, a lot of research on Biomedicine is mainly related to heart defects. The recognition and detection of heart defects using an electrocardiogram (ECG) is numerous. This article aims to explain ECG research trends using the artificial neural networks (ANN) approach in the last twelve years. We reviewed journals with the keyword title "ANN ECG" and published from 2011 to 2022. Articles classified by the most frequently discussed topics include: data sets, case studies, pre-processing, feature extraction, and classification/identification methods. Data collection from articles obtained some of them use data banks such as PhysioNet, European Society of Cardiology (ESC), UCI Repository, as well as data collection directly from patients. The pre-processing stage of the total number of journals used 23% uses this stage, while in characteristic extraction almost 25% of papers are used. This research is very interesting because only a few researchers focus on researching about it. This article will provide further explanation of the most widely used algorithms for ECG research with the ANN approach. At the end of this article, critical aspects of ECG research can be carried out in the future, and the use of deep learning becomes a huge opportunity for researchers.

show abstract

Section: Identification and Performancementioning

confidence: 99%

Application of Artificial Neural Networks in the Identification of Heart Abnormalities Based on Ecg: Literature Review

2023

ETJ

View full text Add to dashboard Cite

show abstract

“…Other key strengths of ECG utilization for biometric authentication are as follows. First, ECGs have been proven to be unique among individuals due to variations in both physiological and geometrical characteristics of the heart among different individuals (inter-individual variability) ( AlDuwaile and Islam, 2021 ; Yuniarti and Rizal, 2022 ). The pattern of the ECG waveform on each individual is reliant on morphological aspects, such as the thickness of the cardiac muscle, shape, and size of the heart ( El Boujnouni et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Single heartbeat ECG authentication: a 1D-CNN framework for robust and efficient human identification

Yuniarti,

Rizal,

Lim

2024

Front. Bioeng. Biotechnol.

Self Cite

View full text Add to dashboard Cite

This study proposes a small one-dimensional convolutional neural network (1D-CNN) framework for individual authentication, considering the hypothesis that a single heartbeat as input is sufficient to create a robust system. A short segment between R to R of electrocardiogram (ECG) signals was chosen to generate single heartbeat samples by enforcing a rigid length thresholding procedure combined with an interpolation technique. Additionally, we explored the benefits of the synthetic minority oversampling technique (SMOTE) to tackle the imbalance in sample distribution among individuals. The proposed framework was evaluated individually and in a mixture of four public databases: MIT-BIH Normal Sinus Rhythm (NSRDB), MIT-BIH Arrhythmia (MIT-ARR), ECG-ID, and MIMIC-III which are available in the Physionet repository. The proposed framework demonstrated excellent performance, achieving a perfect score (100%) across all metrics (i.e., accuracy, precision, sensitivity, and F1-score) on individual NSRDB and MIT-ARR databases. Meanwhile, the performance remained high, reaching more than 99.6% on mixed datasets that contain larger populations and more diverse conditions. The impressive performance demonstrated in both small and large subject groups emphasizes the model’s scalability and potential for widespread implementation, particularly in security contexts where timely authentication is crucial. For future research, we need to examine the incorporation of multimodal biometric systems and extend the applicability of the framework to real-time environments and larger populations.

show abstract

Implementation of One-Dimensional Convolutional Neural Network for Individual Identification Based on ECG Signal

Cited by 2 publications

References 20 publications

Application of Artificial Neural Networks in the Identification of Heart Abnormalities Based on Ecg: Literature Review

Application of Artificial Neural Networks in the Identification of Heart Abnormalities Based on Ecg: Literature Review

Single heartbeat ECG authentication: a 1D-CNN framework for robust and efficient human identification

Contact Info

Product

Resources

About