{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:53:34Z","timestamp":1792086814189,"version":"4.4.0"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangdong Provincial Educational Research Project","award":["2025GXJK0569"],"award-info":[{"award-number":["2025GXJK0569"]}]},{"name":"The Third Division Tumxuk City Science and Technology Innovation Talent Program","award":["KY2025RC03"],"award-info":[{"award-number":["KY2025RC03"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M761177"],"award-info":[{"award-number":["2024M761177"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>To address the heavy reliance of deep learning models on manually labeled data in ECG classification, we need to tackle two major limitations. First, sample sizes are often limited in clinical settings, making data annotation costly and impractical. Second, existing few-shot learning methods still fall short in two key areas: 1) Existing strategies pay insufficient attention to rare arrhythmia types. This makes it difficult to effectively identify rare clinical cases. 2) Single feature representation fails to fully integrate the global frequency, local time-frequency, and semantic information of ECG signals. This results in incomplete feature representation. To overcome these challenges, we propose a novel few-shot learning method for ECG classification. In terms of feature extraction, a spectral-temporal convolution feature extractor is designed to precisely focus on the key information of ECG by efficiently integrating the global frequency, local time-frequency features and semantic information of the signal. Furthermore, with regard to classification, an improved prototypical network based on cross-class bias diminishing is developed to enhance the recognition performance for rare arrhythmia type samples. The experimental results show that the proposed method achieves significant classification performance across multiple public datasets, especially on Chapman, it attains an average accuracy exceeding 90% in the 2-way 1-shot and 2-way 5-shot tasks.<\/jats:p>","DOI":"10.1371\/journal.pone.0357954","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:40:16Z","timestamp":1792086016000},"page":"e0357954","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["STCP-Net: A few-shot learning approach based on spectral-temporal convolution and an improved prototypical network for ECG classification"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4286-5953","authenticated-orcid":true,"given":"Jia","family":"Li","sequence":"first","affiliation":[{"name":"Wuyi University","place":["Jiangmen, China"],"department":["School of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dainan","family":"Gan","sequence":"additional","affiliation":[{"name":"Wuyi University","place":["Jiangmen, China"],"department":["School of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolin","family":"Zhan","sequence":"additional","affiliation":[{"name":"Wuyi University","place":["Jiangmen, China"],"department":["School of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yao","sequence":"additional","affiliation":[{"name":"Wuyi University","place":["Jiangmen, China"],"department":["School of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zou","sequence":"additional","affiliation":[{"name":"Wuyi University","place":["Jiangmen, China"],"department":["School of Mathematics and Computational Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Jiangmen Central Hospital","place":["Jiangmen, China"],"department":["Department of Cardiovascular Disease and Clinical Experimental Center"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Li","sequence":"additional","affiliation":[{"name":"Jiangmen Central Hospital","place":["Jiangmen, China"],"department":["Department of Intensive Care Unit"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0755-0996","authenticated-orcid":true,"given":"Dan","family":"Li","sequence":"additional","affiliation":[{"name":"Jiangmen Central Hospital","place":["Jiangmen, China"],"department":["Department of Electrocardiogram"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1367-4071","authenticated-orcid":true,"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Shengjing Hospital of China Medical University","place":["Shenyang, China"],"department":["Department of Rehabilitation"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"issue":"25","key":"pone.0357954.ref001","first-page":"2982","article-title":"Global burden of cardiovascular diseases and risk factors, 1990-2019: Update from the GBD 2019 study","volume":"76","author":"GA Roth","year":"2020","journal-title":"J Am Coll Cardiol"},{"issue":"1","key":"pone.0357954.ref002","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"AY Hannun","year":"2019","journal-title":"Nat Med"},{"key":"pone.0357954.ref003","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1016\/j.measurement.2016.07.043","article-title":"Feature selection for ECG signal processing using improved genetic algorithm and empirical mode decomposition","volume":"94","author":"L Lu","year":"2016","journal-title":"Measurement"},{"key":"pone.0357954.ref004","doi-asserted-by":"crossref","unstructured":"Kropf M, Hayn D, Schreier G. ECG classification based on time and frequency domain features using random forests. 2017 Computing in Cardiology (CinC). IEEE; 2017. p. 1\u20134.","DOI":"10.22489\/CinC.2017.168-168"},{"key":"pone.0357954.ref005","doi-asserted-by":"crossref","first-page":"1380348","DOI":"10.1155\/2018\/1380348","article-title":"Arrhythmia classification of ECG signals using hybrid features","volume":"2018","author":"SM Anwar","year":"2018","journal-title":"Comput Math Methods Med"},{"issue":"11","key":"pone.0357954.ref006","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/10.959322","article-title":"ECG beat recognition using fuzzy hybrid neural network","volume":"48","author":"S Osowski","year":"2001","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0357954.ref007","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.bspc.2017.12.004","article-title":"Classification of imbalanced ECG beats using re-sampling techniques and AdaBoost ensemble classifier","volume":"41","author":"KNVPS Rajesh","year":"2018","journal-title":"Biomed Signal Process Control"},{"key":"pone.0357954.ref008","doi-asserted-by":"crossref","unstructured":"Chourasia M, Thakur A, Gupta S, Singh A. ECG heartbeat classification using CNN. 2020 IEEE 7th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON). IEEE; 2020. p. 1\u20136.","DOI":"10.1109\/UPCON50219.2020.9376451"},{"key":"pone.0357954.ref009","doi-asserted-by":"crossref","unstructured":"Tippannavar SS, Harshith R, Shashidhar R, Sweekar S, Jain S. ECG based heart disease classification and validation using 2D CNN. 2022 5th International Conference on Contemporary Computing and Informatics (IC3I). IEEE; 2022. p. 1182\u20136.","DOI":"10.1109\/IC3I56241.2022.10073094"},{"key":"pone.0357954.ref010","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.1109\/LSP.2020.3036314","article-title":"Attentive RNN-based network to fuse 12-lead ECG and clinical features for improved myocardial infarction diagnosis","volume":"27","author":"E Prabhakararao","year":"2020","journal-title":"IEEE Signal Process Lett"},{"key":"pone.0357954.ref011","doi-asserted-by":"crossref","unstructured":"Mahmud MS, Nayan MMR, Hasan S, Taj MNA. A deep ensemble model with an efficient feature for multi-class arrhythmia classification utilizing 12-lead ECG signal. 2022 12th International Conference on Electrical and Computer Engineering (ICECE). IEEE; 2022. p. 48\u201351.","DOI":"10.1109\/ICECE57408.2022.10088465"},{"key":"pone.0357954.ref012","doi-asserted-by":"crossref","unstructured":"Patra GR, Naik MK, Mohanty MN. ECG signal classification using a CNN-LSTM hybrid network. 2023 2nd International Conference on Ambient Intelligence in Health Care (ICAIHC). IEEE; 2023. p. 1\u20136.","DOI":"10.1109\/ICAIHC59020.2023.10431449"},{"key":"pone.0357954.ref013","doi-asserted-by":"crossref","unstructured":"Reddy L, Talwar V, Alle S, Bapi RS, Priyakumar UD. Imle-net: An interpretable multi-level multi-channel model for ecg classification. 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE; 2021. p. 1068\u201374.","DOI":"10.1109\/SMC52423.2021.9658706"},{"key":"pone.0357954.ref014","doi-asserted-by":"crossref","first-page":"109480","DOI":"10.1016\/j.patcog.2023.109480","article-title":"A survey on machine learning from few samples","volume":"139","author":"J Lu","year":"2023","journal-title":"Pattern Recognit"},{"key":"pone.0357954.ref015","doi-asserted-by":"crossref","first-page":"104038","DOI":"10.1016\/j.compbiomed.2020.104038","article-title":"Generating wall shear stress for coronary artery in real-time using neural networks: Feasibility and initial results based on idealized models","volume":"126","author":"B Su","year":"2020","journal-title":"Comput Biol Med"},{"key":"pone.0357954.ref016","doi-asserted-by":"crossref","first-page":"1518732","DOI":"10.3389\/fphys.2025.1518732","article-title":"Prediction of time averaged wall shear stress distribution in coronary arteries\u2019 bifurcation varying in morphological features via deep learning","volume":"16","author":"MH Sarkhosh","year":"2025","journal-title":"Front Physiol"},{"key":"pone.0357954.ref017","doi-asserted-by":"crossref","unstructured":"Bhaskarpandit S. How much data is enough? Benchmarking transfer learning for few shot ECG image classification. Proceedings of the 1st Workshop on Scarce Data in Artificial Intelligence Healthcare-SDAIH; 2023. p. 35\u201340.","DOI":"10.5220\/0011531700003523"},{"key":"pone.0357954.ref018","doi-asserted-by":"crossref","first-page":"103094","DOI":"10.1016\/j.dsp.2021.103094","article-title":"Few-shot learning for cardiac arrhythmia detection based on electrocardiogram data from wearable devices","volume":"116","author":"T Liu","year":"2021","journal-title":"Digit Signal Process"},{"key":"pone.0357954.ref019","doi-asserted-by":"crossref","unstructured":"Gupta P, Bhaskarpandit S, Gupta M. Similarity learning based few shot learning for ECG time series classification. 2021 Digital Image Computing: Techniques and Applications (DICTA). IEEE; 2021. p. 1\u20138.","DOI":"10.1109\/DICTA52665.2021.9647357"},{"key":"pone.0357954.ref020","doi-asserted-by":"crossref","unstructured":"Cao Z, Guo F, An Y, Wang J. Residual spatio-temporal attention based prototypical network for rare arrhythmia classification. International Symposium on Bioinformatics Research and Applications. Springer; 2024. p. 89\u2013101.","DOI":"10.1007\/978-981-97-5087-0_8"},{"key":"pone.0357954.ref021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2022.3181276","article-title":"Automatic cardiac arrhythmia classification using residual network combined with long short-term memory","volume":"71","author":"YK Kim","year":"2022","journal-title":"IEEE Trans Instrum Meas"},{"issue":"1","key":"pone.0357954.ref022","doi-asserted-by":"crossref","first-page":"119","DOI":"10.3390\/e23010119","article-title":"Automatic ECG classification using continuous wavelet transform and convolutional neural network","volume":"23","author":"T Wang","year":"2021","journal-title":"Entropy (Basel)"},{"key":"pone.0357954.ref023","doi-asserted-by":"crossref","unstructured":"Zhang H, Zhao W, Liu S. SE-ECGNet: A multi-scale deep residual network with squeeze-and-excitation module for ECG signal classification. 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE; 2020. p. 2685\u201391.","DOI":"10.1109\/BIBM49941.2020.9313548"},{"key":"pone.0357954.ref024","doi-asserted-by":"crossref","first-page":"59842","DOI":"10.1109\/ACCESS.2024.3392965","article-title":"ECG classification exercise health analysis algorithm based on GRU and convolutional neural network","volume":"12","author":"W Ji","year":"2024","journal-title":"IEEE Access"},{"issue":"4","key":"pone.0357954.ref025","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1007\/s00607-023-01243-0","article-title":"Automatic ECG classification using discrete wavelet transform and one-dimensional convolutional neural network","volume":"106","author":"A Shoughi","year":"2023","journal-title":"Computing"},{"issue":"1","key":"pone.0357954.ref026","doi-asserted-by":"crossref","first-page":"679","DOI":"10.3934\/mbe.2024029","article-title":"Few-shot learning based on deep learning: A survey","volume":"21","author":"W Zeng","year":"2024","journal-title":"Math Biosci Eng"},{"key":"pone.0357954.ref027","doi-asserted-by":"crossref","unstructured":"Li Z, Wang H, Liu X. A one-dimensional Siamese few-shot learning approach for ECG classification under limited data. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE; 2021. p. 455\u20138.","DOI":"10.1109\/EMBC46164.2021.9630622"},{"key":"pone.0357954.ref028","doi-asserted-by":"crossref","first-page":"106465","DOI":"10.1016\/j.compbiomed.2022.106465","article-title":"Diagnosis of arrhythmias with few abnormal ECG samples using metric-based meta learning","volume":"153","author":"Z Liu","year":"2023","journal-title":"Comput Biol Med"},{"key":"pone.0357954.ref029","doi-asserted-by":"crossref","unstructured":"Li Z, Zhang H. Parallel multi-scale convolution based prototypical network for few-shot ECG beats classification. 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI). IEEE; 2022. p. 1\u20134.","DOI":"10.1109\/BHI56158.2022.9926948"},{"key":"pone.0357954.ref030","unstructured":"Yang L, Hong S, Zhang L. Spectral propagation graph network for few-shot time series classification. arXiv:220204769 [Preprint]. 2022."},{"key":"pone.0357954.ref031","doi-asserted-by":"crossref","unstructured":"Liu P, Wu B, Li N, Dai T, Lei F, Bao J, et al. Wftnet: Exploiting global and local periodicity in long-term time series forecasting. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2024. p. 5960\u20134.","DOI":"10.1109\/ICASSP48485.2024.10446883"},{"issue":"8","key":"pone.0357954.ref032","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"pone.0357954.ref033","doi-asserted-by":"crossref","unstructured":"Lai J, Yang S, Liu W, Zeng Y, Huang Z, Wu W, et al. tsf: Transformer-based semantic filter for few-shot learning. European Conference on Computer Vision. Springer; 2022. p. 1\u201319.","DOI":"10.1007\/978-3-031-20044-1_1"},{"key":"pone.0357954.ref034","doi-asserted-by":"crossref","unstructured":"Liu J, Song L, Qin Y. Prototype rectification for few-shot learning. European Conference on Computer Vision. Springer; 2020. p. 741\u201356.","DOI":"10.1007\/978-3-030-58452-8_43"},{"key":"pone.0357954.ref035","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"J Snell","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"pone.0357954.ref036","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41597-020-0386-x","article-title":"A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients","volume":"7","author":"J Zheng","year":"2020","journal-title":"Sci Data"},{"issue":"6","key":"pone.0357954.ref037","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1109\/JAS.2019.1911747","article-title":"The UCR time series archive","volume":"6","author":"HA Dau","year":"2019","journal-title":"IEEE\/CAA J Autom Sin"},{"key":"pone.0357954.ref038","article-title":"Matching networks for one shot learning","volume":"29","author":"O Vinyals","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"pone.0357954.ref039","doi-asserted-by":"crossref","first-page":"100886","DOI":"10.1016\/j.isci.2020.100886","article-title":"Detection and classification of cardiac arrhythmias by a challenge-best deep learning neural network model","volume":"23","author":"T-M Chen","year":"2020","journal-title":"iScience"},{"issue":"6","key":"pone.0357954.ref040","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"InceptionTime: Finding AlexNet for time series classification","volume":"34","author":"H Ismail Fawaz","year":"2020","journal-title":"Data Min Knowl Disc"},{"key":"pone.0357954.ref041","doi-asserted-by":"crossref","unstructured":"He T, Zhang Z, Zhang H, Zhang Z, Xie J, Li M. Bag of tricks for image classification with convolutional neural networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2019. p. 558\u201367.","DOI":"10.1109\/CVPR.2019.00065"},{"key":"pone.0357954.ref042","doi-asserted-by":"crossref","unstructured":"Guan Y, An Y, Guo F, Wang J. MPFNet: ECG arrhythmias classification based on multi-perspective feature fusion. International Symposium on Bioinformatics Research and Applications. Springer; 2023. p. 85\u201396.","DOI":"10.1007\/978-981-99-7074-2_7"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:40:27Z","timestamp":1792086027000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357954"}},"subtitle":[],"editor":[{"given":"Agnese","family":"Sbrollini","sequence":"first","affiliation":[{"name":"Polytechnic University of Marche: Universita Politecnica delle Marche","place":["ITALY"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,15]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0357954","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,15]]}}}