{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:35:24Z","timestamp":1775633724509,"version":"3.50.1"},"reference-count":21,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T00:00:00Z","timestamp":1663718400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Label noise is omnipresent in the annotations process and has an impact on supervised learning algorithms. This work focuses on the impact of label noise on the performance of learning models by examining the effect of random and class-dependent label noise on a binary classification task: quality assessment for photoplethysmography (PPG). PPG signal is used to detect physiological changes and its quality can have a significant impact on the subsequent tasks, which makes PPG quality assessment a particularly good target for examining the impact of label noise in the field of biomedicine. Random and class-dependent label noise was introduced separately into the training set to emulate the errors associated with fatigue and bias in labeling data samples. We also tested different representations of the PPG, including features defined by domain experts, 1D raw signal and 2D image. Three different classifiers are tested on the noisy training data, including support vector machine (SVM), XGBoost, 1D Resnet and 2D Resnet, which handle three representations, respectively. The results showed that the two deep learning models were more robust than the two traditional machine learning models for both the random and class-dependent label noise. From the representation perspective, the 2D image shows better robustness compared to the 1D raw signal. The logits from three classifiers are also analyzed, the predicted probabilities intend to be more dispersed when more label noise is introduced. From this work, we investigated various factors related to label noise, including representations, label noise type, and data imbalance, which can be a good guidebook for designing more robust methods for label noise in future work.<\/jats:p>","DOI":"10.3390\/s22197166","type":"journal-article","created":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T23:07:55Z","timestamp":1663888075000},"page":"7166","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Impact of Label Noise on the Learning Based Models for a Binary Classification of Physiological Signal"],"prefix":"10.3390","volume":"22","author":[{"given":"Cheng","family":"Ding","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, GA 30332, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1681-2436","authenticated-orcid":false,"given":"Tania","family":"Pereira","sequence":"additional","affiliation":[{"name":"INESC TEC-Institute for Systems and Computer Engineering, Technology and Science, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3689-1680","authenticated-orcid":false,"given":"Ran","family":"Xiao","sequence":"additional","affiliation":[{"name":"Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, GA 30332, USA"}]},{"given":"Randall J.","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Medicine, University of California San Francisco, San Francisco, CA 94143, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9478-5571","authenticated-orcid":false,"given":"Xiao","family":"Hu","sequence":"additional","affiliation":[{"name":"Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, GA 30332, USA"},{"name":"Department of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA 30332, USA"},{"name":"Department of Computer Science, College of Arts and Sciences, Emory University, Atlanta, GA 30332, USA"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,21]]},"reference":[{"key":"ref_1","first-page":"3762","article-title":"Few-shot pulse wave contour classification based on multi-scale feature extraction","volume":"11","author":"Lu","year":"2021","journal-title":"Sci. Reports"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Fang, M., and Wang, N. (2019). Channel-spatial attention network for fewshot classification. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0225426"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Che, J., Wang, L., Bai, X., Liu, C., and Zhou, F. (2022). Spatial-Temporal Hybrid Feature Extraction Network for Few-shot Automatic Modulation Classification. IEEE Trans. Veh. Technol., 1\u20136.","DOI":"10.1109\/TVT.2022.3196103"},{"key":"ref_4","first-page":"1789","article-title":"Learning with Bounded Instance-and Label-dependent Label Noise","volume":"119","author":"Cheng","year":"2020","journal-title":"PMLR"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fedjajevs, A., Groenendaal, W., Agell, C., and Hermeling, E. (2020). Platform for Analysis and Labeling of Medical Time Series. Sensors, 20.","DOI":"10.3390\/s20247302"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","article-title":"Classification in the Presence of Label Noise: A Survey","volume":"25","author":"Frenay","year":"2013","journal-title":"IEEE Trans. NEURAL NETWORKS Learn. Syst."},{"key":"ref_7","unstructured":"Khetan, A., Anandkumar, A., and Lipton, Z.C. (2017). Learning from Noisy Singly-Labeled Data. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Pelletier, C., Valero, S., Inglada, J., Champion, N., Sicre, C.M., and Dedieu, G. (2017). Effect of training class label noise on classification performances for land cover mapping with satellite image time series. Remote Sens., 9.","DOI":"10.3390\/rs9020173"},{"key":"ref_9","unstructured":"Rolnick, D., Veit, A., Belongie, S., and Shavit, N. (2017). Deep Learning is Robust to Massive Label Noise. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ding, Y., Wang, L., Fan, D., and Gong, B. (2018, January 12\u201315). A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00138"},{"key":"ref_11","first-page":"1126","article-title":"Noninvasive intracranial hypertension detection utilizing semisupervised learning","volume":"60","author":"Kim","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1088\/0967-3334\/34\/4\/465","article-title":"Semi-supervised detection of intracranial pressure alarms using waveform dynamics","volume":"34","author":"Scalzo","year":"2013","journal-title":"Physiol. Meas."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1613\/jair.606","article-title":"Friedl, Identifying Mislabeled Training Data","volume":"11","author":"Brodley","year":"1999","journal-title":"J. Artif. Intell. Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.bspc.2014.10.013","article-title":"Genetic algorithm-based method for mitigating label noise issue in ECG signal classification","volume":"19","author":"Pasolli","year":"2015","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.bspc.2018.08.026","article-title":"Identifying the mislabeled training samples of ECG signals using machine learning","volume":"47","author":"Li","year":"2018","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1038\/s41746-019-0207-9","article-title":"Photoplethysmography based atrial fibrillation detection: A review","volume":"3","author":"Pereira","year":"2020","journal-title":"npj Digit. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1109\/JBHI.2019.2909065","article-title":"A Supervised Approach to Robust Photoplethysmography Quality Assessment","volume":"24","author":"Pereira","year":"2019","journal-title":"IEEE J. Biomed. Heal. Inform."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"125002","DOI":"10.1088\/1361-6579\/ab5b84","article-title":"Deep learning approaches for plethysmography signal quality assessment in the presence of atrial fibrillation","volume":"40","author":"Pereira","year":"2019","journal-title":"Physiol. Meas."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Beigman, E., and Klebanov, B.B. (2009, January 2\u20137). Learning with annotation noise. Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Suntec, Singapore.","DOI":"10.3115\/1687878.1687919"},{"key":"ref_21","unstructured":"Chan, J. (2015). On Boosting and Noisy Labels, Massachusetts Institute of Technology."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7166\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:36:48Z","timestamp":1760143008000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,21]]},"references-count":21,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22197166"],"URL":"https:\/\/doi.org\/10.3390\/s22197166","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,21]]}}}