{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T08:07:58Z","timestamp":1768637278767,"version":"3.49.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030905385","type":"print"},{"value":"9783030905392","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-90539-2_25","type":"book-chapter","created":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T13:02:56Z","timestamp":1636722176000},"page":"378-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An Explainable Model for Fault Detection in HPC Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6805-2232","authenticated-orcid":false,"given":"Martin","family":"Molan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2298-2944","authenticated-orcid":false,"given":"Andrea","family":"Borghesi","sequence":"additional","affiliation":[]},{"given":"Francesco","family":"Beneventi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3175-4628","authenticated-orcid":false,"given":"Massimiliano","family":"Guarrasi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1148-2450","authenticated-orcid":false,"given":"Andrea","family":"Bartolini","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,13]]},"reference":[{"key":"25_CR1","unstructured":"Cineca inter-university consortium web site. www.cineca.it\/\/en. Accessed 29 Jun 2018"},{"key":"25_CR2","unstructured":"Sensu go: Sensu go 5.20, docs.sensu.io\/sensu-go\/latest\/"},{"key":"25_CR3","unstructured":"Barth, W.: Nagios: system and network monitoring. No Starch Press (2008)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Bartolini, A., Borghesi, A., et al.: The D.A.V.I.D.E. big-data-powered fine-grain power and performance monitoring support. In: Proceedings of the 15th ACM International Conference on Computing Frontiers, Ischia, Italy, 2018 (2018)","DOI":"10.1145\/3203217.3205863"},{"key":"25_CR5","doi-asserted-by":"publisher","unstructured":"Bartolini, A., Beneventi, F., Borghesi, A., Cesarini, D., Libri, A., Benini, L., Cavazzoni, C.: Paving the way toward energy-aware and automated datacentre. In: Proceedings of the 48th International Conference on Parallel Processing: Workshops. ICPP 2019, Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3339186.3339215","DOI":"10.1145\/3339186.3339215"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Beneventi, F., Bartolini, A., et al.: Continuous learning of hpc infrastructure models using big data analytics and in-memory processing tools. In: Proceedings of the Conference on Design, Automation and Test in Europe, pp. 1038\u20131043. European Design and Automation Association (2017)","DOI":"10.23919\/DATE.2017.7927143"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Borghesi, A., Bartolini, A., et al.: Anomaly detection using autoencoders in hpc systems. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33019428"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Borghesi, A., Bartolini, A., et al.: A semisupervised autoencoder-based approach for anomaly detection in high performance computing systems. Eng. Appl. Artif. Intell. 85, 634\u2013644 (2019)","DOI":"10.1016\/j.engappai.2019.07.008"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Borghesi, A., Libri, A., et al.: Online anomaly detection in hpc systems. In: 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), pp. 229\u2013233. IEEE (2019)","DOI":"10.1109\/AICAS.2019.8771527"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Bulathwela, S., Perez-Ortiz, M., et al.: Truelearn: a family of bayesian algorithms to match lifelong learners to open educational resources. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i01.5395"},{"key":"25_CR11","unstructured":"Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. CoRR abs\/2011.07876 (2020). arxiv.org\/abs\/2011.07876"},{"key":"25_CR12","unstructured":"Graepel, T., Candela, J., et al.: Web-scale bayesian click-through rate prediction for sponsored search advertising in microsoft\u2019s bing search engine. Omnipress (2010)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Herbrich, R., Minka, T., Graepel, T.: Trueskill\u2122: a bayesian skill rating system. In: Advances in neural information processing systems, pp. 569\u2013576 (2007)","DOI":"10.7551\/mitpress\/7503.003.0076"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Iannone, F., Bracco, G., et al.: Marconi-fusion: the new high performance computing facility for european nuclear fusion modelling. Fusion Eng. Design 129, 354\u2013358 (2018)","DOI":"10.1016\/j.fusengdes.2017.11.004"},{"key":"25_CR15","unstructured":"Massie, M.: Monitoring with Ganglia. O\u2019Reilly Media, Sebastopol, CA (2012)"},{"key":"25_CR16","unstructured":"Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. arXiv preprint arXiv:1908.09635 (2019)"},{"key":"25_CR17","unstructured":"Molan, M., Bulathwela, S., Orlic, D.: Accessibility recommendation system. In: Proceedings of the OER20: Open Education Conference (2020)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Netti, A., Kiziltan, Z., et al.: A machine learning approach to online fault classification in hpc systems. Future Gener. Comput. Syst. (2019)","DOI":"10.1016\/j.future.2019.11.029"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Netti, A., Mueller, M., Guillen, C., Ott, M., Tafani, D., Ozer, G., Schulz, M.: Dcdb wintermute: enabling online and holistic operational data analytics on hpc systems (2019)","DOI":"10.1145\/3369583.3392674"},{"key":"25_CR20","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Pel\u00e1nek, R.: Applications of the elo rating system in adaptive educational systems. Comput. Educ. 98, 169\u2013179 (2016)","DOI":"10.1016\/j.compedu.2016.03.017"},{"key":"25_CR22","unstructured":"Sammut, C., Webb, G.I. (eds.): Attribute-value learning. Springer, US (2010)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Sharma, H., Kumar, S.: A survey on decision tree algorithms of classification in data mining. Int. J. Sci. Res. (IJSR) 5(4) (2016)","DOI":"10.21275\/v5i4.NOV162954"},{"key":"25_CR24","doi-asserted-by":"publisher","unstructured":"Tuncer, O., et al.: Diagnosing performance variations in HPC applications using machine learning. In: Kunkel, J., Yokota, R., Balaji, P., Keyes, D. (eds) High Performance Computing. ISC 2017. Lecture Notes in Computer Science, vol. 10266. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-58667-0_19","DOI":"10.1007\/978-3-319-58667-0_19"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, Z., Xue, J., Zhou, Y.: The reliability wall for exascale supercomputing. IEEE Trans. Comput. 61(6), 767\u2013779 (2012)","DOI":"10.1109\/TC.2011.106"},{"key":"25_CR26","doi-asserted-by":"publisher","unstructured":"Zamuda, A., Zarges, C., Stiglic, G., Hrovat, G.: Stability selection using a genetic algorithm and logistic linear regression on healthcare records. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, p. 143\u2013144. GECCO \u201917, Association for Computing Machinery, New York, NY, USA (2017). https:\/\/doi.org\/10.1145\/3067695.3076077","DOI":"10.1145\/3067695.3076077"}],"updated-by":[{"DOI":"10.1007\/978-3-030-90539-2_36","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000}}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-90539-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T15:11:48Z","timestamp":1699801908000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-90539-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030905385","9783030905392"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-90539-2_25","relation":{"correction":[{"id-type":"doi","id":"10.1007\/978-3-030-90539-2_36","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"13 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"4 January 2022","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The chapter was inadvertently published with the spelling error in the first author\u2019s name. It has been corrected to \u201cMartin Molan\u201d.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"74","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.28","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.13","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"In the ISC High Performance Workshop, there were 49 submissions, out of which 35 were accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}