{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T18:11:31Z","timestamp":1777918291089,"version":"3.51.4"},"reference-count":49,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2020,12,19]],"date-time":"2020-12-19T00:00:00Z","timestamp":1608336000000},"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>Assessing the health condition has a wide range of applications in healthcare, military, aerospace, and industrial fields. Nevertheless, traditional feature-engineered techniques involve manual feature extraction, which are too cumbersome to adapt to the changes caused by the development of sensor network technology. Recently, deep-learning-based methods have achieved initial success in health-condition assessment research, but insufficient considerations for problems such as class skewness, noisy segments, and result interpretability make it difficult to apply them to real-world applications. In this paper, we propose a K-margin-based Interpretable Learning approach for health-condition assessment. In detail, a skewness-aware RCR-Net model is employed to handle problems of class skewness. Furthermore, we present a diagnosis model based on K-margin to automatically handle noisy segments by naturally exploiting expected consistency among the segments associated with each record. Additionally, a knowledge-directed interpretation method is presented to learn domain knowledge-level features automatically without the help of human experts which can be used as an interpretable decision-making basis. Finally, through experimental validation in the field of both medical and aerospace, the proposed method has a better generality and high efficiency with 0.7974 and 0.8005 F1 scores, which outperform all state-of-the-art deep learning methods for health-condition assessment task by 3.30% and 2.99%, respectively.<\/jats:p>","DOI":"10.3390\/s20247307","type":"journal-article","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T01:01:08Z","timestamp":1608512468000},"page":"7307","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Addressing Noise and Skewness in Interpretable Health-Condition Assessment by Learning Model Confidence"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6875-726X","authenticated-orcid":false,"given":"Yuxi","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China"},{"name":"Key Laboratory of Machine Perception, Ministry of Education, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenda","family":"Hong","sequence":"additional","affiliation":[{"name":"National Institute of Health Data Science at Peking University, Beijing 100191, China"},{"name":"Institute of Medical Technology, Health Science Center of Peking University, Beijing 100191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyuan","family":"Shang","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China"},{"name":"Key Laboratory of Machine Perception, Ministry of Education, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China"},{"name":"Key Laboratory of Machine Perception, Ministry of Education, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China"},{"name":"Key Laboratory of Machine Perception, Ministry of Education, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China"},{"name":"Key Laboratory of Machine Perception, Ministry of Education, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junqing","family":"Xie","sequence":"additional","affiliation":[{"name":"Centre for Statistics in Medicine (CSM), Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences (NDROMS), University of Oxford, Oxford OX3 7LD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1007\/BF02345439","article-title":"Automatic detection of atrial fibrillation using the coefficient of variation and density histograms of RR and \u0394RR intervals","volume":"39","author":"Tateno","year":"2001","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1142\/S0129065710002334","article-title":"Automatic identification of epileptic and background EEG signals using frequency domain parameters","volume":"20","author":"Faust","year":"2010","journal-title":"Int. J. Neural Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.bspc.2011.06.002","article-title":"Linear and nonlinear analysis of cardiac health in diabetic subjects","volume":"7","author":"Faust","year":"2012","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1007\/s13239-016-0256-z","article-title":"Accurate, automated detection of atrial fibrillation in ambulatory recordings","volume":"7","author":"Linker","year":"2016","journal-title":"Cardiovasc. Eng. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"054009","DOI":"10.1088\/1361-6579\/ab15a2","article-title":"Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings","volume":"40","author":"Hong","year":"2019","journal-title":"Physiol. Meas."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/s41019-020-00129-x","article-title":"Unsupervised Qualitative Scoring for Binary Item Features","volume":"5","author":"Ichikawa","year":"2020","journal-title":"Data Sci. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1007\/s41019-019-00106-z","article-title":"Identification of k-Most Promising Features to Set Blue Ocean Strategy in Decision Making","volume":"4","author":"Kumar","year":"2019","journal-title":"Data Sci. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ieracitano, C., Mammone, N., Hussain, A., and Morabito, F.C. (2020, January 18\u201322). A Convolutional Neural Network based self-learning approach for classifying neurodegenerative states from EEG signals in dementia. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN)), Shenzheng, China.","DOI":"10.1109\/IJCNN48605.2020.9207167"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"021004","DOI":"10.1115\/1.3025827","article-title":"Structural health monitoring with autoregressive support vector machines","volume":"131","author":"Bornn","year":"2009","journal-title":"J. Vib. Acoust."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1873","DOI":"10.1088\/0967-3334\/36\/9\/1873","article-title":"Heart rate dynamics distinguish among atrial fibrillation, normal sinus rhythm and sinus rhythm with frequent ectopy","volume":"36","author":"Carrara","year":"2015","journal-title":"Physiol. Meas."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"110520","DOI":"10.1016\/j.engstruct.2020.110520","article-title":"A Bayesian approach for condition assessment and damage alarm of bridge expansion joints using long-term structural health monitoring data","volume":"212","author":"Ni","year":"2020","journal-title":"Eng. Struct."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TBME.2015.2468589","article-title":"Real-time patient-specific ECG classification by 1D convolutional neural networks","volume":"63","author":"Kiranyaz","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"035006","DOI":"10.1088\/1361-6579\/aaaa9d","article-title":"A robust deep convolutional neural network for the classification of abnormal cardiac rhythm using single lead electrocardiograms of variable length","volume":"39","author":"Kamaleswaran","year":"2018","journal-title":"Physiol. Meas."},{"key":"ref_14","unstructured":"Hu, B., Hu, Z., Ran, L., Mawby, P., Jia, C., Ng, C., and McKeever, P. (October, January 29). Deep Learning Neural Networks for Heat-Flux Health Condition Monitoring Method of Multi-Device Power Electronics System. Proceedings of the IEEE Energy Conversion Congress and Exposition (ECCE), Baltimore, MD, USA."},{"key":"ref_15","unstructured":"San, K.T., and Sohn, S.Y. (2020). Multitask learning for health condition identification and remaining useful life prediction: Deep convolutional neural network approach. J. Intell. Manuf., 1\u201311."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hong, S., Xu, Y., Khare, A., Priambada, S., Maher, K.O., Aljiffry, A., Sun, J., and Tumanov, A. (2020, January 23\u201327). HOLMES: Health Online Model Ensemble Serving for Deep Learning Models in Intensive Care Units. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual Event, Los Angeles, CA, USA.","DOI":"10.1145\/3394486.3403212"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Schwab, P., Scebba, G.C., Zhang, J., Delai, M., and Karlen, W. (2017, January 24\u201327). Beat by beat: Classifying cardiac arrhythmias with recurrent neural networks. Proceedings of the IEEE Computing in Cardiology (CinC), Nice, France.","DOI":"10.22489\/CinC.2017.363-223"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.compbiomed.2018.07.001","article-title":"Automated detection of atrial fibrillation using long short-term memory network with RR interval signals","volume":"102","author":"Faust","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"114002","DOI":"10.1088\/1361-6579\/aad386","article-title":"Ensembling convolutional and long short-term memory networks for electrocardiogram arrhythmia detection","volume":"39","author":"Warrick","year":"2018","journal-title":"Physiol. Meas."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.patrec.2020.02.005","article-title":"Validating the robustness of an internet of things based atrial fibrillation detection system","volume":"133","author":"Faust","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4501952","DOI":"10.1155\/2018\/4501952","article-title":"Convolutional recurrent neural network for fault diagnosis of high-speed train bogie","volume":"2018","author":"Liang","year":"2018","journal-title":"Complexity"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1109\/JBHI.2019.2910082","article-title":"MFB-CBRNN: A hybrid network for MI detection using 12-lead ECGs","volume":"24","author":"Liu","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hong, S., Wang, C., and Fu, Z. (2020). Gated Temporal Convolutional Neural Network and Expert Features for Diagnosing and Explaining Physiological Time Series: A Case Study on Heart Rates. Comput. Methods Programs Biomed., 105847.","DOI":"10.1016\/j.cmpb.2020.105847"},{"key":"ref_24","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":"Hannun","year":"2019","journal-title":"Nat. Med."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Shen, Y., Voisin, M., Aliamiri, A., Avati, A., Hannun, A., and Ng, A. (2019, January 4\u20138). Ambulatory atrial fibrillation monitoring using wearable photoplethysmography with deep learning. Proceedings of the 25th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330657"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.neunet.2019.12.006","article-title":"A novel multi-modal machine learning based approach for automatic classification of EEG recordings in dementia","volume":"123","author":"Ieracitano","year":"2020","journal-title":"Neural Netw."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1111\/mice.12476","article-title":"Convolutional neural network-based wind-induced response estimation model for tall buildings","volume":"34","author":"Oh","year":"2019","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101789","DOI":"10.1016\/j.artmed.2019.101789","article-title":"Comprehensive electrocardiographic diagnosis based on deep learning","volume":"103","author":"Lih","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Hong, S., Shang, J., Wu, M., Wang, Q., Li, H., and Xie, J. (2019, January 10\u201316). K-margin-based residual-convolution-recurrent neural network for atrial fibrillation detection. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), Macao, China.","DOI":"10.24963\/ijcai.2019\/839"},{"key":"ref_30","unstructured":"Sun, C., Hong, S., Song, M., and Li, H. (2020). A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"103801","DOI":"10.1016\/j.compbiomed.2020.103801","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":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2907070","article-title":"A survey of predictive modeling on imbalanced domains","volume":"49","author":"Branco","year":"2016","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lu, Y., Cheung, Y., and Tang, Y.Y. (2017, January 19\u201325). Dynamic Weighted Majority for Incremental Learning of Imbalanced Data Streams with Concept Drift. Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia.","DOI":"10.24963\/ijcai.2017\/333"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Liu, S.-H., Hsieh, C.-H., Chen, W., and Tan, T.-H. (2019). ECG noise cancellation based on grey spectral noise estimation. Sensors, 19.","DOI":"10.3390\/s19040798"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1007\/s11265-020-01531-4","article-title":"Kalman-based Spectro-Temporal ECG Analysis using Deep Convolutional Networks for Atrial Fibrillation Detection","volume":"92","author":"Zhao","year":"2020","journal-title":"J. Signal Process. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Reljin, N., Lazaro, J., Hossain, M.B., Noh, Y.S., Cho, C.H., and Chon, K.H. (2020). Using the Redundant Convolutional Encoder-Decoder to Denoise QRS Complexes in ECG Signals Recorded with an Armband Wearable Device. Sensors, 20.","DOI":"10.3390\/s20164611"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Xu, Y., Biswal, S., Deshpande, S.R., Maher, K.O., and Sun, J. (2018, January 19\u201323). Raim: Recurrent attentive and intensive model of multimodal patient monitoring data. Proceedings of the 24th ACM International Conference on Knowledge Discovery & Data Mining (SIGKDD), London, UK.","DOI":"10.1145\/3219819.3220051"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Hong, S., Xiao, C., Ma, T., Li, H., and Sun, J. (2019, January 10\u201316). Mina: Multilevel knowledge-guided attention for modeling electrocardiography signals. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), Macao, China.","DOI":"10.24963\/ijcai.2019\/816"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy should i trust you?\u201d Explaining the predictions of any classifier. Proceedings of the 22nd ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_40","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Clifford, G.D., Liu, C., Moody, B., Lehman, L.H., Silva, I., Li, Q., Johnson, A.E., and Mark, R.G. (2017, January 24\u201327). AF Classification from a short single lead ECG recording: The PhysioNet\/Computing in Cardiology Challenge 2017. Proceedings of the IEEE Computing in Cardiology (CinC), Nice, France.","DOI":"10.22489\/CinC.2017.065-469"},{"key":"ref_42","first-page":"278","article-title":"Integrated Method of Multiple Machine-Learning Models for Damage Recognition","volume":"35","author":"Yang","year":"2020","journal-title":"J. Data Acquis. Process."},{"key":"ref_43","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Saeedan, F., Weber, N., Goesele, M., and Roth, S. (2018, January 18\u201322). Detail-preserving pooling in deep networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00949"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Betz1, D.C., Staszewski1, W.J., Thursby, G., and Culshaw, B. (2006). Structural damage identification using multifunctional Bragg grating sensors: II. Damage detection results and analysis. Smart Mater. Struct., 15, 1313.","DOI":"10.1088\/0964-1726\/15\/5\/021"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Michaels, J.E., and Michaels, T.E. (2007, January 18\u201322). An integrated strategy for detection and imaging of damage using a spatially distributed array of piezoelectric sensors. Proceedings of the Health Monitoring of Structural and Biological Systems, San Diego, CA, USA.","DOI":"10.1117\/12.715438"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Gao, H., Shi, Y., and Ros, J.L. (2005, January 18\u201322). Guided wave tomography on an aircraft wing with leave in place sensors. Proceedings of the AIP Conference, Paris, France.","DOI":"10.1063\/1.1916887"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"104005","DOI":"10.1088\/1361-6579\/aae304","article-title":"A convolutional neural network for ECG annotation as the basis for classification of cardiac rhythms","volume":"39","author":"Sodmann","year":"2018","journal-title":"Physiol. Meas."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/24\/7307\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:47:20Z","timestamp":1760179640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/24\/7307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,19]]},"references-count":49,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["s20247307"],"URL":"https:\/\/doi.org\/10.3390\/s20247307","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,19]]}}}