{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T11:10:17Z","timestamp":1788952217032,"version":"build-2803163510"},"reference-count":20,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Automatic cardiac arrhythmia detection using electrocardiogram (ECG) signals is essential for early diagnosis of cardiovascular conditions. Most of the previously existing systems for arrhythmia detection depend on fully supervised learning approaches. In addition to that, since the ECG patient data is centrally stored, it can raise concerns like privacy and security in healthcare environments. To address these issues, this work explores a semi-supervised federated learning framework that detects arrhythmia using ECG signals. The MIT-BIH Arrhythmia dataset is used from which the heartbeat segments are extracted and relevant features are obtained. The framework incorporates the use of multi-level feature extraction, adaptive feature fusion and pseudo-labeling to utilize both labeled and unlabeled data efficiently. In order to improve the performance of the model, a weighted federated aggregation approach is used where the contribution of each of the clients is considered during the global model updates. Implementation and evaluation of multiple machine learning and deep learning models including Random Forest, Support Vector Machine, K-Nearest Neighbor, AdaBoost, Gradient Boosting and Multi-Layer Perceptron are performed within the proposed framework. This proposed approach achieves an accuracy of 96.81% in semi-supervised federated settings and has an AUC value of 0.9957 that shows high classification reliability. The system helps improve the model learning with limited number of labeled data at the same time ensuring privacy preserving distributed training. The model maintains a competitive performance under federated settings as compared to the centralized training. Among the evaluated models, ensemble and neural network based approaches show superior performance. The framework demonstrates a stable performance across federated training rounds. Overall, the results obtained show the effectiveness of the proposed framework for arrhythmia detection in a simulated federated setting.<\/jats:p>","DOI":"10.3389\/frai.2026.1913613","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:16:49Z","timestamp":1788949009000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive feature fusion based semi-supervised federated learning system for ECG arrhythmia detection"],"prefix":"10.3389","volume":"9","author":[{"given":"Silla Ann","family":"Regi","sequence":"first","affiliation":[{"name":"Department of Computer Applications, School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jagadeesan","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Department of Software and Systems Engineering, School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thanapal","family":"Pandi","sequence":"additional","affiliation":[{"name":"Department of Software and Systems Engineering, School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"110593","DOI":"10.1016\/j.compbiomed.2025.110593","article-title":"Spindle autoencoder\u2013CNN hybrid model for cardiac arrhythmia classification","volume":"195","author":"Akku\u015f","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"105884","DOI":"10.1016\/j.bspc.2023.105884","article-title":"A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection","volume":"90","author":"Alamatsaz","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"100249","DOI":"10.1016\/j.jnlest.2024.100249","article-title":"Efficient ECG classification based on chi-square distance for arrhythmia detection","volume":"22","author":"Al-Shammary","year":"2024","journal-title":"J. Electron. Sci. Technol."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"110594","DOI":"10.1016\/j.compbiomed.2025.110594","article-title":"A comprehensive review of AI-based detection of arrhythmia using electrocardiogram (ECG)","volume":"196","author":"Ayyub","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"100322","DOI":"10.1016\/j.jnlest.2025.100322","article-title":"XABH-CNN-GRU: explainable attention-based hybrid CNN-GRU model for accurate identification of common arrhythmias","volume":"23","author":"Ba Mahel","year":"2025","journal-title":"J. Electron. Sci. Technol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"104816","DOI":"10.1016\/j.bspc.2023.104816","article-title":"ECG-based heartbeat classification using exponential-political optimizer trained deep learning for arrhythmia detection","volume":"84","author":"Choudhury","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"102195","DOI":"10.1016\/j.mex.2023.102195","article-title":"Analysis of ECG-based arrhythmia detection system using machine learning","volume":"10","author":"Dhyani","year":"2023","journal-title":"MethodsX"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"102818","DOI":"10.1016\/j.artmed.2024.102818","article-title":"ECG-based cardiac arrhythmias detection through ensemble learning and fusion of deep spatial\u2013temporal and long-range dependency features","volume":"150","author":"Din","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"114889","DOI":"10.1016\/j.knosys.2025.114889","article-title":"Arrhythmia detection in multi-channel ECG images: vision transformer and explainable approaches","volume":"331","author":"Duranay","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"ref15","first-page":"1","article-title":"Development of deep learning model for cardiac arrhythmia detection from ECG","volume-title":"in 2024 International Conference on Recent Advances in Information and Communication Systems (RAICS)","author":"Fahad","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"105325","DOI":"10.1016\/j.compbiomed.2022.105325","article-title":"A transformer-based deep neural network for arrhythmia detection using continuous ECG signals","volume":"144","author":"Hu","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e02687","DOI":"10.1016\/j.sciaf.2025.e02687","article-title":"GAF-GradCAM: guided dynamic weighted fusion of temporal and frequency GAF 2D matrices for ECG-based arrhythmia detection using deep learning","volume":"28","author":"Khatar","year":"2025","journal-title":"Sci. Afr."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"108751","DOI":"10.1016\/j.bspc.2025.108751","article-title":"DWTFrTV-DEAL: denoising and deep ensemble learning for arrhythmia classification using ECG signals","volume":"112","author":"Lamba","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"104418","DOI":"10.1016\/j.medengphy.2025.104418","article-title":"Graph-enhanced deep learning for ECG arrhythmia detection: an integration of CNN-GNN-BiLSTM approach","volume":"145","author":"Mahajan","year":"2025","journal-title":"Med. Eng. Phys."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"108063","DOI":"10.1016\/j.bspc.2025.108063","article-title":"HLS-compiled PYNQ-based cardiac arrhythmia detection system leveraging quantized ECG beat images","volume":"109","author":"Mangaraj","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"108031","DOI":"10.1016\/j.bspc.2025.108031","article-title":"Analysis and classification of beat-level ECG arrhythmia using WST-inspired CNN framework","volume":"109","author":"Nahak","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"2266","DOI":"10.1109\/GLOBECOM48099.2022.10001697","article-title":"Fetal arrhythmia detection based on deep learning using fetal ecg signals","volume-title":"in GLOBECOM 2022-2022 IEEE Global Communications Conference","author":"Nakatani","year":"2022"},{"key":"ref18","first-page":"1","article-title":"Comparison analysis for life-threatening arrhythmia classification from ECG data using machine learning and deep learning methods","volume-title":"in 2024 8th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE)","author":"Nugraha","year":"2024"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/INCOFT60753.2023.10425439","article-title":"Design and implementation of cardiac arrhythmia detection using machine learning algorithm for healthcare application","volume-title":"in 2023 2nd International Conference on Futuristic Technologies (INCOFT)","author":"Tabhane","year":"2023"},{"key":"ref20","first-page":"1174","article-title":"Research on arrhythmia classification and detection based on multiple machine learning algorithms","volume-title":"in 2023 5th International Conference on Frontiers Technology of Information and Computer (ICFTIC)","author":"Yu","year":"2023"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1913613\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:16:50Z","timestamp":1788949010000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1913613\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":20,"alternative-id":["10.3389\/frai.2026.1913613"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1913613","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]},"article-number":"1913613"}}