{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T09:48:43Z","timestamp":1792144123363,"version":"4.4.0"},"reference-count":48,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T00:00:00Z","timestamp":1792108800000},"content-version":"vor","delay-in-days":15,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T00:00:00Z","timestamp":1792108800000},"content-version":"tdm","delay-in-days":15,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"RIIM LPDP Kompetisi","award":["RIIM 2024-02 G6"],"award-info":[{"award-number":["RIIM 2024-02 G6"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    This study investigates how Kolmogorov\u2013Arnold Networks (KANs) behave when combined with semi-supervised learning for single-lead ECG analysis. Three architectures are compared: a standard CNN-BiLSTM-Attention model (accurate but uninterpretable), a minimal KAN with a simple CNN front-end (ablation), and the proposed SE-MSC-KAN-CNN. The proposed model uses multi-scale depthwise convolutions, Squeeze-and-Excitation attention, BiLSTM, and a B-spline KAN head. Interpretability is evaluated in three ways: visualising learned B-spline functions, applying Grad-CAM to highlight important signal regions, and measuring how the splines change when fewer labels are used (spline drift). On the PhysioNet\u20092017 dataset (8528 recordings, four classes), the proposed model reaches 85.2% supervised accuracy (\n                    <jats:italic>F<\/jats:italic>\n                    1 = 0.851), outperforming the CNN baseline (83.1%) and matching much larger black-box models. With only 90% of the labels, it still achieves 85.1%. After training, we applied post-training TFLite INT8 conversion. Only the CNN-front-end KAN converted (measured size 422\u2009KB). The proposed SE-MSC-KAN-CNN did not convert, because Bidirectional LSTM and custom attention lack TFLite kernels; its float32 footprint is about 9.8\u2009MB (theoretical INT8 size about 806\u2009KB). Classification metrics in this paper are float32; INT8 test accuracy was not measured. The spline drift metric summarises how KAN coefficients change under semi-supervised training; use as an on-device out-of-distribution detector is proposed but not validated here. These results show that competitive accuracy and inspectable KAN maps can be obtained in one hybrid architecture. Wearable deployment of the proposed SE-MSC-KAN-CNN is not yet achieved: TFLite INT8 conversion failed, and the present graph still requires float32 inference.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/aeb0af","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T22:48:11Z","timestamp":1791326891000},"page":"055056","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["B-spline Kolmogorov\u2013Arnold networks for interpretable semi-supervised ECG classification"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7876-2206","authenticated-orcid":true,"given":"M R","family":"Baidillah","sequence":"first","affiliation":[{"name":"Research Center for Electronics, KST Samaun Samadikun, BRIN"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"M","family":"Rahmawati","sequence":"additional","affiliation":[{"name":"FMIPA, Andalas University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5925-1096","authenticated-orcid":false,"given":"S","family":"Oktamuliani","sequence":"additional","affiliation":[{"name":"FMIPA, Andalas University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6368-6938","authenticated-orcid":false,"given":"R","family":"Febryarto","sequence":"additional","affiliation":[{"name":"Research Center for Electronics, KST Samaun Samadikun, BRIN"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0431-6988","authenticated-orcid":false,"given":"P","family":"Busono","sequence":"additional","affiliation":[{"name":"Research Center for Smart Mechatronics, KST Samaun Samadikun, BRIN"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"project-administration","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8621-4293","authenticated-orcid":false,"given":"I M","family":"Astawa","sequence":"additional","affiliation":[{"name":"Research Center for Electronics, KST Samaun Samadikun, BRIN"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2002-655X","authenticated-orcid":true,"given":"S","family":"Karim","sequence":"additional","affiliation":[{"name":"Research Center for Electronics, KST Samaun Samadikun, BRIN"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7917-3390","authenticated-orcid":true,"given":"R","family":"Riyanto","sequence":"additional","affiliation":[{"name":"Research Center for Electronics, KST Samaun Samadikun, BRIN"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"software","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6542-0941","authenticated-orcid":false,"given":"C","family":"Achmad","sequence":"additional","affiliation":[{"name":"Padjadjaran University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]}],"member":"266","published-online":{"date-parts":[[2026,10,16]]},"reference":[{"key":"bpexaeb0afbib1","article-title":"Cardiovascular diseases (CVDs). World Health Organization News Room","author":"WHO","year":"2021","type":"other"},{"key":"bpexaeb0afbib2","doi-asserted-by":"publisher","first-page":"515","DOI":"10.2188\/jea.JE20150178","type":"journal-article","article-title":"The burden of cardiovascular disease attributable to major modifiable risk factors in Indonesia","volume":"26","author":"Hussain","year":"2016","journal-title":"J. Epidemiol."},{"key":"bpexaeb0afbib3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswax.2020.100033","type":"journal-article","article-title":"A review on deep learning methods for ECG arrhythmia classification","volume":"7","author":"Ebrahimi","year":"2020","journal-title":"Expert Syst. Appl. X"},{"key":"bpexaeb0afbib4","doi-asserted-by":"publisher","first-page":"16","DOI":"10.4313\/TEEM.2015.16.1.16","type":"journal-article","article-title":"Real time ECG monitoring through a wearable smart t-shirt","volume":"16","author":"Mathias","year":"2015","journal-title":"Trans. Electr. Electron. Mater."},{"key":"bpexaeb0afbib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103801","type":"journal-article","article-title":"Opportunities and challenges of deep learning methods for electrocardiogram data: a systematic review","volume":"122","author":"Hong","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"bpexaeb0afbib6","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1109\/tbme.2006.889201","type":"journal-article","article-title":"Capacitive sensing of electrocardiographic potential through cloth","volume":"54","author":"Ueno","year":"2007","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexaeb0afbib7","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1016\/j.medj.2021.06.005","type":"journal-article","article-title":"Smartwatch biomarkers and the path to clinical use","volume":"2","author":"Picard","year":"2021","journal-title":"MED"},{"key":"bpexaeb0afbib8","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.12928\/telkomnika.v16i3.9387","type":"journal-article","article-title":"Energy consumption saving in embedded microprocessors using hardware accelerators","volume":"16","author":"Cardarilli","year":"2018","journal-title":"Telkomnika"},{"key":"bpexaeb0afbib9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2017.065-469","type":"journal-article","article-title":"AF classification from a short single lead ECG recording: the PhysioNet\/Computing in cardiology challenge 2017","volume":"44","author":"Clifford","year":"2017","journal-title":"Comput. Cardiol."},{"key":"bpexaeb0afbib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2017.178-245","type":"journal-article","article-title":"ENCASE: an ENsemble ClASsifiEr for ECG classification using expert features and deep neural networks","volume":"44","author":"Hong","year":"2017","journal-title":"Comput. Cardiol."},{"key":"bpexaeb0afbib11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2017.166-054","type":"journal-article","article-title":"Arrhythmia classification from the abductive interpretation of short single-lead ECG records","volume":"44","author":"Teijeiro","year":"2018","journal-title":"Comput. Cardiol."},{"key":"bpexaeb0afbib12","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","type":"journal-article","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat. Med."},{"key":"bpexaeb0afbib13","doi-asserted-by":"publisher","first-page":"5888","DOI":"10.24963\/ijcai.2019\/816","type":"journal-article","article-title":"MINA: Multilevel knowledge-guided attention for modeling electrocardiography signals","author":"Hong","year":"2019","journal-title":"Proc. IJCAI"},{"key":"bpexaeb0afbib14","article-title":"EfficientECG: Cross-attention with feature fusion for efficient electrocardiogram classification","author":"Wang","year":"2025","type":"preprint"},{"key":"bpexaeb0afbib15","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241234624","type":"journal-article","article-title":"Attention-assisted hybrid CNN-BiLSTM-BiGRU model with SMOTE\u2013Tomek","volume":"10","author":"Chopannejad","year":"2024","journal-title":"Digit Health"},{"key":"bpexaeb0afbib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-025-92582-9","type":"journal-article","article-title":"A novel hybrid CNN-transformer model for arrhythmia detection","volume":"15","author":"Kim","year":"2025","journal-title":"Sci. Rep."},{"key":"bpexaeb0afbib17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-07781-1","type":"journal-article","article-title":"DeepECG-net: a hybrid transformer-based deep learning model for real-time ECG anomaly detection","volume":"15","author":"Alghieth","year":"2025","journal-title":"Sci. Rep."},{"key":"bpexaeb0afbib18","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","type":"journal-article","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018","journal-title":"Proc. IEEE CVPR"},{"key":"bpexaeb0afbib19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0326079","type":"journal-article","article-title":"Arrhythmia classification based on multi-input convolutional neural network with attention mechanism.","volume":"20","author":"Zheng","year":"2025","journal-title":"PLoS One"},{"key":"bpexaeb0afbib20","article-title":"Kan: Kolmogorov-arnold networks","author":"Liu","year":"2024","type":"preprint"},{"key":"bpexaeb0afbib21","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-7063327\/v1","type":"preprint","article-title":"Kolmogorov-arnold networks: a critical assessment of claims, performance, and practical viability","author":"Hou","year":"2025"},{"key":"bpexaeb0afbib22","doi-asserted-by":"publisher","DOI":"10.1103\/4t7t-v19l","type":"journal-article","article-title":"Kolmogorov-Arnold networks meet science","volume":"15","author":"Liu","year":"2025","journal-title":"Phys. Rev. X"},{"key":"bpexaeb0afbib23","article-title":"Kolmogorov-Arnold networks: a critical assessment of claims, performance, and practical viability","author":"Hou","year":"2024","type":"preprint"},{"key":"bpexaeb0afbib24","doi-asserted-by":"publisher","first-page":"7207","DOI":"10.3390\/s24227207","type":"journal-article","article-title":"A multi-class ECG signal classifier using a binarized depthwise separable CNN","volume":"24","author":"Zhang","year":"2024","journal-title":"Sensors"},{"key":"bpexaeb0afbib25","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-02474-1","type":"journal-article","article-title":"A lightweight intrusion detection approach using DSC-KAN","volume":"15","author":"Zhao","year":"2025","journal-title":"Sci. Rep."},{"key":"bpexaeb0afbib26","doi-asserted-by":"publisher","DOI":"10.2196\/25415","type":"journal-article","article-title":"Assessing ECG and respiratory signal quality of a wearable device","volume":"9","author":"Xu","year":"2021","journal-title":"JMIR MHealth UHealth"},{"key":"bpexaeb0afbib27","article-title":"CE-SSL: computation-efficient semi-supervised learning for ECG-based cardiovascular diseases detection","author":"Zhou","year":"2024","type":"preprint"},{"key":"bpexaeb0afbib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.101568","type":"journal-article","article-title":"FedECG: a federated semi-supervised learning framework for ECG abnormalities prediction","volume":"35","author":"Ying","year":"2023","journal-title":"J. King Saud. Univ."},{"key":"bpexaeb0afbib29","doi-asserted-by":"publisher","first-page":"4261","DOI":"10.1109\/JBHI.2023.3281977","type":"journal-article","article-title":"An efficient and private ECG classification system using split and semi-supervised learning","volume":"27","author":"Ayad","year":"2023","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"bpexaeb0afbib30","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105331","type":"journal-article","article-title":"An accurate and efficient method to train classifiers for atrial fibrillation detection","volume":"143","author":"Wesselius","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"bpexaeb0afbib31","doi-asserted-by":"publisher","first-page":"90","DOI":"10.3390\/a18020090","type":"journal-article","article-title":"ECG signal classification using interpretable KAN","volume":"18","author":"Zaid","year":"2025","journal-title":"Algorithms"},{"key":"bpexaeb0afbib32","doi-asserted-by":"publisher","DOI":"10.2196\/38454","type":"journal-article","article-title":"State-of-the-art deep learning methods on ECG data: systematic review","volume":"10","author":"Petmezas","year":"2022","journal-title":"JMIR Med. Inf."},{"key":"bpexaeb0afbib33","doi-asserted-by":"publisher","DOI":"10.1145\/3743128","type":"journal-article","article-title":"A comprehensive survey on Kolmogorov-Arnold network","author":"ACM","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"bpexaeb0afbib34","doi-asserted-by":"publisher","first-page":"3928","DOI":"10.3390\/s25133928","type":"journal-article","article-title":"MAK-Net: A multi-scale attentive KAN with BiGRU for imbalanced ECG arrhythmia","volume":"25","author":"Zhao","year":"2025","journal-title":"Sensors"},{"key":"bpexaeb0afbib35","article-title":"Semi-KAN: KAN provides an effective representation for semi-supervised medical image segmentation","author":"Ye","year":"2025","type":"preprint"},{"key":"bpexaeb0afbib36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1101\/2024.06.04.24308428","type":"journal-article","article-title":"Abnormality detection in time-series bio-signals using KAN for resource-constrained devices","author":"Huang","year":"2024","journal-title":"MedRxiv"},{"key":"bpexaeb0afbib37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108447","type":"journal-article","article-title":"Interpretable deep learning framework for multi-label ECG classification: Enhancing cardiac diagnostics through feature attention and explainability","volume":"112","author":"Zheng","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexaeb0afbib38","article-title":"Softly symbolifying Kolmogorov-Arnold networks","author":"Bagrow","year":"2025","type":"preprint"},{"key":"bpexaeb0afbib39","article-title":"Free-Knots KAN: on the analysis of spline knots and advancing stability","author":"Zheng","year":"2025","type":"other"},{"key":"bpexaeb0afbib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111226","type":"journal-article","article-title":"SmartMatch: a semi-supervised framework for obstructive sleep apnea classification","volume":"157","author":"Gayen","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"bpexaeb0afbib41","doi-asserted-by":"publisher","first-page":"248","DOI":"10.15575\/join.v10i2.1557","type":"journal-article","article-title":"Performance evaluation of NAS parallel and high-performance conjugate gradient benchmarks in Mahameru","volume":"10","author":"Wirahman","year":"2025","journal-title":"Jurnal Online Informatika"},{"key":"bpexaeb0afbib42","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2020.610956","type":"journal-article","article-title":"Impact of data transformation: an ECG heartbeat classification approach","volume":"2","author":"Liang","year":"2020","journal-title":"J. Online Inf."},{"key":"bpexaeb0afbib43","doi-asserted-by":"publisher","first-page":"2496","DOI":"10.3390\/s25082496","type":"journal-article","article-title":"Reliable ECG anomaly detection on edge devices for IoMT applications","volume":"25","author":"Hizem","year":"2025","journal-title":"Sensors"},{"key":"bpexaeb0afbib44","doi-asserted-by":"publisher","first-page":"321","DOI":"10.5555\/1622407.1622416","type":"journal-article","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"bpexaeb0afbib45","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1186\/s12911-021-01736-y","type":"journal-article","article-title":"ECG signal classification based on deep CNN and BiLSTM","volume":"21","author":"Li","year":"2021","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"bpexaeb0afbib46","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.12928\/telkomnika.v23i5.26735","type":"journal-article","article-title":"Hybrid Kolmogorov-Arnold and convolutional neural network model for single-lead ECG classification","volume":"23","author":"Baidillah","year":"2025","journal-title":"Telkomnika"},{"key":"bpexaeb0afbib47","doi-asserted-by":"publisher","first-page":"3599","DOI":"10.1007\/s00034-024-02986-7","type":"journal-article","article-title":"Automated ECG analysis with dual-channel SqueezeNet using Hilbert Huang transform, fuzzy entropy and Hurst exponent","volume":"44","author":"Tiedeu","year":"2025","journal-title":"Circuits Syst. Signal Process."},{"key":"bpexaeb0afbib48","doi-asserted-by":"publisher","first-page":"4805","DOI":"10.3390\/s23104805","type":"journal-article","article-title":"Electrocardiogram monitoring wearable devices and AI-enabled diagnostic capabilities: a review","volume":"23","author":"Neri","year":"2023","journal-title":"Sensors"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T09:23:58Z","timestamp":1792142638000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb0af"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,10,16]]},"published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/aeb0af","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"assertion":[{"value":"B-spline Kolmogorov\u2013Arnold networks for interpretable semi-supervised ECG classification","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-05-26","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-16","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}