{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:43:18Z","timestamp":1786038198984,"version":"3.56.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T00:00:00Z","timestamp":1738108800000},"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. Neuroinform."],"abstract":"<jats:p>Anomaly detection is a typical binary classification problem under the condition of unbalanced samples, which has been widely used in various fields of data mining. For example, it can help detect heart murmurs when the heart is structurally abnormal, to tell if a newborn has congenital heart disease. Due to the low time and high efficiency, most work focuses on the semi- supervised anomaly detection method. However, the anomaly detection effect of this method is not high because of massive data with uneven samples and different noise. To improve the accuracy of anomaly detection under unbalanced sample conditions, we propose a new semi-supervised anomaly detection method (WCOS) based on semi-supervised clustering, which combines wavelet reconstruction, convolutional autoencoder, and one classification support vector machine. In this way, we can not only distinguish a small proportion of abnormal heart sounds in the huge data scale but also filter the noise through the noise reduction network, thus significantly improving the detection accuracy. In addition, we evaluated our method using real datasets. When the noise of sigma = 0.5, the AUC standard deviation of the WR-CAE-OCSVM is 19.2, 54.1, and 29.8% lower than that of WR-OCSVM, CAE-OCSVM and OCSVM, respectively. The results confirmed the higher accuracy of anomaly detection in WCOS compared to other state-of-the-art methods.<\/jats:p>","DOI":"10.3389\/fninf.2025.1530047","type":"journal-article","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T06:50:27Z","timestamp":1738133427000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhanced heart sound anomaly detection via WCOS: a semi-supervised framework integrating wavelet, autoencoder and SVM"],"prefix":"10.3389","volume":"19","author":[{"given":"Peipei","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuimiao","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"6508","DOI":"10.3390\/s24206508","article-title":"Diagnosis of schizophrenia using EEG sensor data: a novel approach with automated log energy-based empirical wavelet reconstruction and cepstral features","volume":"24","author":"Aziz","year":"2024","journal-title":"Sensors"},{"key":"ref2","first-page":"104813","article-title":"A multi-scale dual-decoder autoencoder model for domain-shift machine sound anomaly detection","author":"Chen","year":"2024","journal-title":"Digit. Signal Process."},{"key":"ref3","first-page":"1","article-title":"A survey on deep learning-based anomaly detection","volume":"54","author":"Chong","year":"2021","journal-title":"ACM Comput. Surveys"},{"key":"ref4","article-title":"Deep Learning for Anomaly Detection","volume-title":"Report, Cloudera.","author":"Cloudera","year":"2020"},{"key":"ref5","first-page":"11483","article-title":"One-class variational autoencoder for anomaly detection in text data","volume":"9","author":"Fan","year":"2021","journal-title":"IEEE Access"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1016\/j.isprsjprs.2024.09.028","article-title":"Variational autoencoder with Gaussian random field prior: application to unsupervised animal detection in aerial images","volume":"218","author":"Gangloff","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref7","first-page":"3257","article-title":"Anomaly detection in multivariate time series with conditional generative flow","volume":"32","author":"Gao","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"108124","DOI":"10.1016\/j.cie.2022.108124","article-title":"An intuitionistic fuzzy bireduct model and its application to cancer treatment","volume":"168","author":"Jain","year":"2022","journal-title":"Comput. Ind. Eng."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2773","DOI":"10.1007\/s00521-022-07754-9","article-title":"Fuzzy rough assisted missing value imputation and feature selection","volume":"35","author":"Jain","year":"2023","journal-title":"Neural Comput. & Applic."},{"key":"ref10","first-page":"748","article-title":"A dynamic network anomaly detection algorithm based on graph neural networks","volume":"31","author":"Jia-Yan","year":"2020","journal-title":"J. Softw."},{"key":"ref11","first-page":"1395","article-title":"Classification of normal\/abnormal heart sound recording through convolution neural network through the integration of baseline and adaboost classifier","author":"Jyothi","year":"2021","journal-title":"In Proceedings of the 2nd International Conference on Computational and Bio Engineering: CBE 2020."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1007\/s41478-023-00687-z","article-title":"Adaptive control of unknown fuzzy disturbance-based uncertain nonlinear systems: application to hypersonic flight dynamics","volume":"32","author":"Kumar","year":"2024","journal-title":"J. Analysis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/en17163904","article-title":"Electricity behavior modeling and anomaly detection services based on a deep variational autoencoder network","volume":"17","author":"Li","year":"2024","journal-title":"Energies"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1638","DOI":"10.1109\/TIFS.2023.3245413","article-title":"A high accuracy and adaptive anomaly detection model with dual-domain graph convolutional network for insider threat detection","volume":"18","author":"Li","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"109443","DOI":"10.1016\/j.engappai.2024.109443","article-title":"Convolutional variational autoencoder and multi-scale attention convolutional neural network based diagnostics on filament current sensors for mass spectrometers","volume":"138","author":"Li","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref16","first-page":"2317","article-title":"Unsupervised deep anomaly detection model based on sample association perception","volume":"44","author":"Liang","year":"2021","journal-title":"J. Comput."},{"key":"ref17","first-page":"519","article-title":"AUC: a statistically consistent and more discriminating measure than accuracy","volume":"3","author":"Ling","year":"2003","journal-title":"In:Ijcai"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1109\/ICCChina.2019.8855955","article-title":"SCOD: a novel semi-supervised outlier detection framework","volume-title":"2019 IEEE\/CIC international conference on Communications in China (ICCC)","author":"Liu","year":"2019"},{"key":"ref19","article-title":"Graph anomaly detection with graph convolutional networks","volume":"14","author":"Mir","year":"2023","journal-title":"Int. J. Advan. Comput. Sci. Applic."},{"key":"ref20","first-page":"200","article-title":"Adaptive anomaly detection in dynamic graph networks","volume-title":"Adaptive Anomaly Detection in Dynamic Graph Networks","author":"Mir","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3125987","article-title":"An adaptive pyramid graph and variation residual-based anomaly detection network for rail surface defects","volume":"70","author":"Niu","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"11250","DOI":"10.1002\/int.23041","article-title":"Graph convolutional network-based deep feature learning for cardiovascular disease recognition from heart sound signals","volume":"37","author":"Rezaee","year":"2022","journal-title":"Int. J. Intell. Syst."},{"key":"ref23","first-page":"2298","article-title":"Deep one-class classification","volume":"43","author":"Ruff","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref24","first-page":"1141","article-title":"Non-Markov policies to reduce sequential failures in robot bin picking","author":"Sanders","year":"2020"},{"key":"ref25","first-page":"1","article-title":"Noise suppression for vector magnetic anomaly detection by noise spatial characteristics investigation","volume-title":"IEEE geoscience and remote sensing letters","author":"Shen","year":"2021"},{"key":"ref26","first-page":"167","article-title":"Element defective sample augmentation method based on improved DCGAN","author":"Shi","year":"2023"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/02331934.2023.2270683","article-title":"A novel (alpha, beta)-indiscernibility-assisted intuitionistic fuzzy-rough set model and its application to dimensionality reduction","author":"Shreevastava","year":"2023","journal-title":"Optimization"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.32604\/chd.2024.048314","article-title":"Machine learning-based intelligent auscultation techniques in congenital heart disease: application and development","volume":"19","author":"Wang","year":"2024","journal-title":"Congenital Heart Disease."},{"key":"ref28","first-page":"311","article-title":"Reconstruction of ECG signals based on improved empirical modal decomposition domain inner physical feature recognition mode components","volume":"70","author":"Xiao-dong","year":"2020","journal-title":"J. Phys."},{"key":"ref29","volume-title":"Research on anomaly detection method based on deep generative model","author":"Xing","year":"2020"},{"key":"ref30","first-page":"4","article-title":"Research progress on the development mechanism of malnutrition in children with congenital heart disease","volume":"6","author":"Xue","year":"2022","journal-title":"Electr. J. Modern Med. Health Res."},{"key":"ref31","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/DDCLS61622.2024.10606793","article-title":"A hybrid MTS anomaly detection method based on reconstruction and adaptive spatial-temporal graph network","volume-title":"2024 IEEE 13th data driven control and learning systems conference (DDCLS)","author":"Yuan","year":"2024"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"106128","DOI":"10.1016\/j.tust.2024.106128","article-title":"A confident learning-based support vector machine for robust ground classification in noisy label environments","volume":"155","author":"Zhang","year":"2025","journal-title":"Tunnel. Underground Space Technol. Incorporat. Trenchless Technol. Res."}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2025.1530047\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T06:50:36Z","timestamp":1738133436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2025.1530047\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,29]]},"references-count":33,"alternative-id":["10.3389\/fninf.2025.1530047"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2025.1530047","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,29]]},"article-number":"1530047"}}