{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T06:53:06Z","timestamp":1771051986797,"version":"3.50.1"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:00:00Z","timestamp":1743638400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1016\/j.engappai.2025.110674","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T08:05:44Z","timestamp":1744358744000},"page":"110674","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Explainable time series features for hard disk drive failure prediction"],"prefix":"10.1016","volume":"152","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0131-4955","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3843-1440","authenticated-orcid":false,"given":"Haozhou","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1560-3619","authenticated-orcid":false,"given":"Srinivasan","family":"Radhakrishnan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5845-7714","authenticated-orcid":false,"given":"Sagar","family":"Kamarthi","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2025.110674_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107339","article-title":"Cost aware LSTM model for predicting hard disk drive failures based on extremely imbalanced SMART sensors data","volume":"127","author":"Ahmed","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2025.110674_b2","article-title":"Interpretable predictive maintenance for hard drives","volume":"5","author":"Amram","year":"2021","journal-title":"Mach. Learn. Appl."},{"key":"10.1016\/j.engappai.2025.110674_b3","series-title":"2018 IEEE International Congress on Big Data (BigData Congress)","first-page":"251","article-title":"Large scale predictive analytics for hard disk remaining useful life estimation","author":"Anantharaman","year":"2018"},{"key":"10.1016\/j.engappai.2025.110674_b4","series-title":"The backblaze storage pod - our secret to the least expensive cloud storage in the world!","author":"Backblaze","year":"2024"},{"key":"10.1016\/j.engappai.2025.110674_b5","series-title":"Hard drive data and stats","author":"Backblaze","year":"2024"},{"key":"10.1016\/j.engappai.2025.110674_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109648","article-title":"Designing on-board explainable passenger flow prediction","volume":"139","author":"Barbareschi","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2025.110674_b7","series-title":"Metrology, Inspection, and Process Control XXXVII","first-page":"352","article-title":"Addressing misclassification costs in machine learning through asymmetric loss functions","volume":"12496","author":"Barnes","year":"2023"},{"key":"10.1016\/j.engappai.2025.110674_b8","series-title":"Hard drive SMART stats","author":"Beach","year":"2014"},{"key":"10.1016\/j.engappai.2025.110674_b9","series-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"39","article-title":"Predicting disk replacement towards reliable data centers","author":"Botezatu","year":"2016"},{"key":"10.1016\/j.engappai.2025.110674_b10","series-title":"Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining","first-page":"785","article-title":"Xgboost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"10.1016\/j.engappai.2025.110674_b11","series-title":"Data centers around the world: A quick look","author":"Daigle","year":"2021"},{"key":"10.1016\/j.engappai.2025.110674_b12","series-title":"Data recovery prices","author":"Data Recovery Professionals","year":"2024"},{"key":"10.1016\/j.engappai.2025.110674_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.107968","article-title":"Global wavelet-integrated residual frequency attention regularized network for hypersonic flight vehicle fault diagnosis with imbalanced data","volume":"132","author":"Dong","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2025.110674_b14","series-title":"2008 IEEE International Symposium on Modeling, Analysis and Simulation of Computers and Telecommunication Systems","first-page":"1","article-title":"Failure prediction models for proactive fault tolerance within storage systems","author":"Eckart","year":"2008"},{"key":"10.1016\/j.engappai.2025.110674_b15","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","author":"Fabian","year":"2011","journal-title":"J. Mach. Learn. Res. 12"},{"issue":"7","key":"10.1016\/j.engappai.2025.110674_b16","doi-asserted-by":"crossref","first-page":"7279","DOI":"10.1007\/s10462-022-10354-7","article-title":"Evaluating eXplainable artificial intelligence tools for hard disk drive predictive maintenance","volume":"56","author":"Ferraro","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.engappai.2025.110674_b17","series-title":"2016 IEEE Second International Conference on Big Data Computing Service and Applications (Bigdataservice)","first-page":"105","article-title":"A practical approach to hard disk failure prediction in cloud platforms: Big data model for failure management in datacenters","author":"Ganguly","year":"2016"},{"issue":"5","key":"10.1016\/j.engappai.2025.110674_b18","doi-asserted-by":"crossref","first-page":"6859","DOI":"10.1109\/TII.2022.3181692","article-title":"A self-interpretable soft sensor based on deep learning and multiple attention mechanism: From data selection to sensor modeling","volume":"19","author":"Guo","year":"2022","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.engappai.2025.110674_b19","unstructured":"Hamerly, G., Elkan, C., et al., 2001. Bayesian approaches to failure prediction for disk drives. In: ICML. 1, (2001), pp. 202\u2013209, Citeseer."},{"issue":"2","key":"10.1016\/j.engappai.2025.110674_b20","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1109\/TC.2022.3160365","article-title":"StreamDFP: a general stream mining framework for adaptive disk failure prediction","volume":"72","author":"Han","year":"2022","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/j.engappai.2025.110674_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2021.108063","article-title":"Prognostics and health management: A review from the perspectives of design, development and decision","volume":"217","author":"Hu","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"10.1016\/j.engappai.2025.110674_b22","series-title":"2015 IEEE International Symposium on Workload Characterization","first-page":"150","article-title":"Characterizing disk failures with quantified disk degradation signatures: An early experience","author":"Huang","year":"2015"},{"issue":"3","key":"10.1016\/j.engappai.2025.110674_b23","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1109\/TR.2002.802886","article-title":"Improved disk-drive failure warnings","volume":"51","author":"Hughes","year":"2002","journal-title":"IEEE Trans. Reliab."},{"key":"10.1016\/j.engappai.2025.110674_b24","series-title":"Ai alignment: A comprehensive survey","author":"Ji","year":"2023"},{"key":"10.1016\/j.engappai.2025.110674_b25","series-title":"2009 IEEE International Conference on Automation Science and Engineering","first-page":"246","article-title":"Assessement of current health of hard disk drives","author":"Kamarthi","year":"2009"},{"key":"10.1016\/j.engappai.2025.110674_b26","series-title":"Advanced Informatics for Computing Research: Second International Conference, ICAICR 2018, Shimla, India, July 14\u201315, 2018, Revised Selected Papers, Part I 2","first-page":"366","article-title":"Failure prediction and health status assessment of storage systems with decision trees","author":"Kaur","year":"2019"},{"key":"10.1016\/j.engappai.2025.110674_b27","series-title":"Using machine learning to predict hard drive failures","author":"Klein","year":"2021"},{"key":"10.1016\/j.engappai.2025.110674_b28","series-title":"Backblaze drive stats for Q3 2022","author":"Klein","year":"2023"},{"key":"10.1016\/j.engappai.2025.110674_b29","series-title":"2014 44th Annual Ieee\/Ifip International Conference on Dependable Systems and Networks","first-page":"383","article-title":"Hard drive failure prediction using classification and regression trees","author":"Li","year":"2014"},{"key":"10.1016\/j.engappai.2025.110674_b30","doi-asserted-by":"crossref","first-page":"76627","DOI":"10.1109\/ACCESS.2018.2884004","article-title":"New metrics for disk failure prediction that go beyond prediction accuracy","volume":"6","author":"Li","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2025.110674_b31","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.ress.2017.03.004","article-title":"Hard drive failure prediction using decision trees","volume":"164","author":"Li","year":"2017","journal-title":"Reliab. Eng. Syst. Saf."},{"issue":"4","key":"10.1016\/j.engappai.2025.110674_b32","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1002\/asmb.446","article-title":"Analysis of regression in game theory approach","volume":"17","author":"Lipovetsky","year":"2001","journal-title":"Appl. Stoch. Models Bus. Ind."},{"key":"10.1016\/j.engappai.2025.110674_b33","unstructured":"Lu, S., Luo, B., Patel, T., Yao, Y., Tiwari, D., Shi, W., 2020. Making disk failure predictions {SMARTer}!. In: 18th USENIX Conference on File and Storage Technologies. FAST 20, pp. 151\u2013167."},{"issue":"6","key":"10.1016\/j.engappai.2025.110674_b34","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.1007\/s10618-019-00647-x","article-title":"catch22: Canonical time-series characteristics: Selected through highly comparative time-series analysis","volume":"33","author":"Lubba","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"issue":"1","key":"10.1016\/j.engappai.2025.110674_b35","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.engappai.2025.110674_b36","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.engappai.2025.110674_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2820615","article-title":"RAIDShield: characterizing, monitoring, and proactively protecting against disk failures","volume":"11","author":"Ma","year":"2015","journal-title":"ACM Trans. Storage (TOS)"},{"key":"10.1016\/j.engappai.2025.110674_b38","unstructured":"Mahdisoltani, F., Stefanovici, I., Schroeder, B., 2017. Improving storage system reliability with proactive error prediction. In: Proceedings of the 2017 USENIX Conference on Usenix Annual Technical Conference. pp. 391\u2013402."},{"key":"10.1016\/j.engappai.2025.110674_b39","unstructured":"Murray, J.F., Hughes, G.F., Kreutz-Delgado, K., 2003. Hard drive failure prediction using non-parametric statistical methods. In: Proceedings of Icann\/Iconip."},{"issue":"5","key":"10.1016\/j.engappai.2025.110674_b40","article-title":"Machine learning methods for predicting failures in hard drives: A multiple-instance application.","volume":"6","author":"Murray","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2025.110674_b41","series-title":"2016 International Joint Conference on Neural Networks","first-page":"4850","article-title":"A combined Bayesian network method for predicting drive failure times from SMART attributes","author":"Pang","year":"2016"},{"issue":"3","key":"10.1016\/j.engappai.2025.110674_b42","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1177\/1094342009106191","article-title":"The raid-6 liber8tion code","volume":"23","author":"Plank","year":"2009","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"10.1016\/j.engappai.2025.110674_b43","series-title":"2017 International Symposium on Performance Evaluation of Computer and Telecommunication Systems","first-page":"1","article-title":"Disk failure prediction in heterogeneous environments","author":"Rinc\u00f3n","year":"2017"},{"issue":"2","key":"10.1016\/j.engappai.2025.110674_b44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2491472.2491475","article-title":"Datacenter scale evaluation of the impact of temperature on hard disk drive failures","volume":"9","author":"Sankar","year":"2013","journal-title":"ACM Trans. Storage ( TOS)"},{"key":"10.1016\/j.engappai.2025.110674_b45","series-title":"Get S.M.A.R.T. for reliability","author":"Seagate","year":"1999"},{"issue":"11","key":"10.1016\/j.engappai.2025.110674_b46","doi-asserted-by":"crossref","DOI":"10.1177\/1550147718806480","article-title":"Random-forest-based failure prediction for hard disk drives","volume":"14","author":"Shen","year":"2018","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"10.1016\/j.engappai.2025.110674_b47","series-title":"Proceedings of the 56th Annual Design Automation Conference 2019","first-page":"1","article-title":"System-level hardware failure prediction using deep learning","author":"Sun","year":"2019"},{"key":"10.1016\/j.engappai.2025.110674_b48","series-title":"2024 Second International Conference on Cyber-Energy Systems and Intelligent Energy","first-page":"1","article-title":"A self-interpretable deep learning soft sensor based on spatio-temporal causal discovery graph","author":"Tian","year":"2024"},{"issue":"11","key":"10.1016\/j.engappai.2025.110674_b49","doi-asserted-by":"crossref","DOI":"10.1111\/cts.70077","article-title":"Integrating real-world data and machine learning: A framework to assess covariate importance in real-world use of alternative intravenous dosing regimens for atezolizumab","volume":"17","author":"Vora","year":"2024","journal-title":"Clin. Transl. Sci."},{"issue":"2","key":"10.1016\/j.engappai.2025.110674_b50","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1109\/TII.2020.3016121","article-title":"Failure prediction of hard disk drives based on adaptive Rao\u2013Blackwellized particle filter error tracking method","volume":"17","author":"Wang","year":"2020","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.engappai.2025.110674_b51","article-title":"A trackable multi-domain collaborative generative adversarial network for rotating machinery fault diagnosis","volume":"224","author":"Wang","year":"2025","journal-title":"Mech. Syst. Signal Process."},{"key":"10.1016\/j.engappai.2025.110674_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2023.102027","article-title":"Adaptive variational autoencoding generative adversarial networks for rolling bearing fault diagnosis","volume":"56","author":"Wang","year":"2023","journal-title":"Adv. Eng. Inf."},{"issue":"1","key":"10.1016\/j.engappai.2025.110674_b53","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1109\/TR.2013.2241204","article-title":"Online anomaly detection for hard disk drives based on mahalanobis distance","volume":"62","author":"Wang","year":"2013","journal-title":"IEEE Trans. Reliab."},{"key":"10.1016\/j.engappai.2025.110674_b54","series-title":"2011 Prognostics and System Health Managment Confernece","first-page":"1","article-title":"Health monitoring of hard disk drive based on mahalanobis distance","author":"Wang","year":"2011"},{"key":"10.1016\/j.engappai.2025.110674_b55","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3123218","article-title":"Multi-instance deep learning based on attention mechanism for failure prediction of unlabeled hard disk drives","volume":"70","author":"Wang","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.engappai.2025.110674_b56","series-title":"Large-Scale Disk Failure Prediction: PAKDD 2020 Competition and Workshop, AI Ops 2020, February 7\u2013May 15, 2020, Revised Selected Papers 1","first-page":"85","article-title":"Tree-based model with advanced data preprocessing for large scale hard disk failure prediction","author":"Wu","year":"2020"},{"key":"10.1016\/j.engappai.2025.110674_b57","series-title":"Proceedings of the 47th International Conference on Parallel Processing","first-page":"1","article-title":"Disk failure prediction in data centers via online learning","author":"Xiao","year":"2018"},{"key":"10.1016\/j.engappai.2025.110674_b58","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2024.119433","article-title":"Rapid failure risk analysis of corroded gas pipelines using machine learning","volume":"313","author":"Xiao","year":"2024","journal-title":"Ocean Eng."},{"key":"10.1016\/j.engappai.2025.110674_b59","unstructured":"Xu, Y., Sui, K., Yao, R., Zhang, H., Lin, Q., Dang, Y., Li, P., Jiang, K., Zhang, W., Lou, J.-G., et al., 2018. Improving service availability of cloud systems by predicting disk error. In: 2018 USENIX Annual Technical Conference. USENIX ATC 18, pp. 481\u2013494."},{"issue":"11","key":"10.1016\/j.engappai.2025.110674_b60","doi-asserted-by":"crossref","first-page":"3502","DOI":"10.1109\/TC.2016.2538237","article-title":"Health status assessment and failure prediction for hard drives with recurrent neural networks","volume":"65","author":"Xu","year":"2016","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/j.engappai.2025.110674_b61","series-title":"2015 IEEE 34th Symposium on Reliable Distributed Systems Workshop","first-page":"13","article-title":"Hard drive failure prediction using big data","author":"Yang","year":"2015"},{"issue":"9","key":"10.1016\/j.engappai.2025.110674_b62","doi-asserted-by":"crossref","first-page":"2155","DOI":"10.1109\/TPDS.2020.2985346","article-title":"Minority disk failure prediction based on transfer learning in large data centers of heterogeneous disk systems","volume":"31","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.engappai.2025.110674_b63","series-title":"Advances in Data Mining. Applications and Theoretical Aspects: 10th Industrial Conference, ICDM 2010, Berlin, Germany, July 12-14, 2010. Proceedings 10","first-page":"390","article-title":"Predicting disk failures with HMM-and HSMM-based approaches","author":"Zhao","year":"2010"},{"key":"10.1016\/j.engappai.2025.110674_b64","article-title":"Class-aware adversarial multiwavelet convolutional neural network for cross-domain fault diagnosis","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.engappai.2025.110674_b65","article-title":"Proactive drive failure prediction for cloud storage system through semi-supervised learning","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"10.1016\/j.engappai.2025.110674_b66","series-title":"2013 IEEE 29th Symposium on Mass Storage Systems and Technologies","first-page":"1","article-title":"Proactive drive failure prediction for large scale storage systems","author":"Zhu","year":"2013"},{"key":"10.1016\/j.engappai.2025.110674_b67","series-title":"Measurement, Modelling and Evaluation of Computing Systems: 20th International GI\/ITG Conference, MMB 2020, Saarbr\u00dccken, Germany, March 16\u201318, 2020, Proceedings 20","first-page":"19","article-title":"To fail or not to fail: Predicting hard disk drive failure time windows","author":"Z\u00fcfle","year":"2020"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625006748?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625006748?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T11:33:13Z","timestamp":1746531193000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197625006748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":67,"alternative-id":["S0952197625006748"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2025.110674","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Explainable time series features for hard disk drive failure prediction","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2025.110674","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"110674"}}