Research on Multi‐Scale Parallel Joint Optimization CNN for Arrhythmia Diagnosis DOI
Wenping Chen, Huibin Wang, Zhe Chen

и другие.

Concurrency and Computation Practice and Experience, Год журнала: 2025, Номер 37(4-5)

Опубликована: Фев. 10, 2025

ABSTRACT The morphological characteristics of electrocardiograms (ECGs) serve as a fundamental basis for diagnosing arrhythmias. Convolutional neural networks (CNNs), leveraging their local receptive field properties, effectively capture the features ECG signals and have been extensively employed in automatic diagnosis However, variability duration renders single‐scale convolutional kernels inadequate fully extracting these features. To address this limitation, study proposes multi‐scale parallel joint optimization network (MPJO_CNN). proposed method utilizes varying scales to extract features, further refining via computation implementing strategy enhance classification performance. Experimental results demonstrate that on MIT‐BIH arrhythmia database, not only achieved state‐of‐the‐art performance, with an accuracy 99.41% F1 score 98.09%, but also showed high sensitivity classes fewer samples.

Язык: Английский

SUPER-COUGH: A Super Learner-based ensemble machine learning method for detecting disease on cough acoustic signals DOI
E. Topuz, Yasin Kaya

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 93, С. 106165 - 106165

Опубликована: Фев. 28, 2024

Язык: Английский

Процитировано

4
Detecting Electrocardiogram Arrhythmia Empowered With Weighted Federated Learning DOI Creative Commons

Rizwana Naz Asif,

Allah Ditta, Hani Alquhayz

и другие.

IEEE Access, Год журнала: 2023, Номер 12, С. 1909 - 1926

Опубликована: Дек. 26, 2023

In this study, a weighted federated learning approach is proposed for electrocardiogram (ECG) arrhythmia classification. The considers the heterogeneity of data distribution among multiple clients in settings. weight each client dynamically adjusted according to its contribution global model improvement. Experiments on public ECG datasets show that outperforms traditional and centralized methods terms accuracy robustness. On side, suggested (FL) had an 0.93, sensitivity 0.98, specificity 0.82, miss classification rate 0.07, precision 0.06, FPR 0.01, FNR 0.01. FL has 0.98 accuracy, 0.99 sensitivity, 0.91 specificity, 0.02 rate, 0.10 precision, FPR, 0.01 server. server-side client-side rates, precision. results indicate promising solution distributed environment. short, applied detection aims address privacy concerns improve while still maintaining framework advanced algorithmic approach.

Язык: Английский

Процитировано

9
Binary Hybrid Artificial Hummingbird with Flower Pollination Algorithm for Feature Selection in Parkinson’s Disease Diagnosis DOI
Liuyan Feng, Yongquan Zhou, Qifang Luo

и другие.

Journal of Bionic Engineering, Год журнала: 2024, Номер 21(2), С. 1003 - 1021

Опубликована: Фев. 28, 2024

Язык: Английский

Процитировано

3
Multi-source deep feature fusion for medical image analysis DOI
Ercan Gürsoy, Yasin Kaya

Multidimensional Systems and Signal Processing, Год журнала: 2024, Номер 36(1)

Опубликована: Дек. 10, 2024

Язык: Английский

Процитировано

3
Research on Multi‐Scale Parallel Joint Optimization CNN for Arrhythmia Diagnosis DOI
Wenping Chen, Huibin Wang, Zhe Chen

и другие.

Concurrency and Computation Practice and Experience, Год журнала: 2025, Номер 37(4-5)

Опубликована: Фев. 10, 2025

ABSTRACT The morphological characteristics of electrocardiograms (ECGs) serve as a fundamental basis for diagnosing arrhythmias. Convolutional neural networks (CNNs), leveraging their local receptive field properties, effectively capture the features ECG signals and have been extensively employed in automatic diagnosis However, variability duration renders single‐scale convolutional kernels inadequate fully extracting these features. To address this limitation, study proposes multi‐scale parallel joint optimization network (MPJO_CNN). proposed method utilizes varying scales to extract features, further refining via computation implementing strategy enhance classification performance. Experimental results demonstrate that on MIT‐BIH arrhythmia database, not only achieved state‐of‐the‐art performance, with an accuracy 99.41% F1 score 98.09%, but also showed high sensitivity classes fewer samples.

Язык: Английский

Процитировано

0