{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:37:02Z","timestamp":1774593422419,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031304415","type":"print"},{"value":"9783031304422","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-30442-2_16","type":"book-chapter","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T10:02:09Z","timestamp":1682589729000},"page":"209-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Smart Clustering of\u00a0HPC Applications Using Similar Job Detection Methods"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9279-6397","authenticated-orcid":false,"given":"Denis","family":"Shaikhislamov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1897-1828","authenticated-orcid":false,"given":"Vadim","family":"Voevodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,28]]},"reference":[{"key":"16_CR1","unstructured":"High performance computing market size to surpass USD 64.65. https:\/\/www.globenewswire.com\/news-release\/2022\/04\/04\/2415844\/0\/en\/High-Performance-Computing-Market-Size-to-Surpass-USD-64-65-Bn-by-2030.html"},{"key":"16_CR2","doi-asserted-by":"publisher","unstructured":"Agrawal, K., Fahey, M., Mclay, R., James, D.: User environment tracking and problem detection with xalt, pp. 32\u201340, November 2014. https:\/\/doi.org\/10.1109\/HUST.2014.6","DOI":"10.1109\/HUST.2014.6"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-319-96983-1_7","volume-title":"Euro-Par 2018: Parallel Processing","author":"E Ates","year":"2018","unstructured":"Ates, E., et al.: Taxonomist: application detection through rich monitoring data. In: Aldinucci, M., Padovani, L., Torquati, M. (eds.) Euro-Par 2018. LNCS, vol. 11014, pp. 92\u2013105. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-96983-1_7"},{"key":"16_CR4","unstructured":"Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, AAAIWS 1994, pp. 359\u2013370. AAAI Press (1994). http:\/\/dl.acm.org\/citation.cfm?id=3000850.3000887"},{"key":"16_CR5","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, KDD 1996, pp. 226\u2013231. AAAI Press (1996)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Gurrutxaga, I., Arbelaitz, O., Mart\u00edn, J., Muguerza, J., P\u00e9rez, J., Perona, I.: Sihc: a stable incremental hierarchical clustering algorithm, pp. 300\u2013304, January 2009","DOI":"10.5220\/0001857103000304"},{"key":"16_CR7","doi-asserted-by":"publisher","unstructured":"Halawa, M., D\u00edaz Redondo, R., Vilas, A.: Unsupervised kpis-based clustering of jobs in HPC data centers. Sensors 20, 4111 (2020). https:\/\/doi.org\/10.3390\/s20154111","DOI":"10.3390\/s20154111"},{"key":"16_CR8","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF01908075","volume":"2","author":"LJ Hubert","year":"1985","unstructured":"Hubert, L.J., Arabie, P.: Comparing partitions. J. Classif. 2, 193\u2013218 (1985)","journal-title":"J. Classif."},{"key":"16_CR9","unstructured":"Joseph, E., Conway, S.: Major trends in the worldwide HPC market. Technical Report (2017). https:\/\/hpcuserforum.com\/presentations\/stuttgart2017\/IDC-update-HLRS.pdf"},{"key":"16_CR10","doi-asserted-by":"publisher","unstructured":"Kuhn, A., Ducasse, S., G\u00eerba, T.: Semantic clustering: identifying topics in source code. Inf. Softw. Technol. 49(3), 230\u2013243 (2007). https:\/\/doi.org\/10.1016\/j.infsof.2006.10.017, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950584906001820, 12th Working Conference on Reverse Engineering","DOI":"10.1016\/j.infsof.2006.10.017"},{"key":"16_CR11","unstructured":"Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. CoRR abs\/1405.4053 (2014)"},{"issue":"8","key":"16_CR12","doi-asserted-by":"publisher","first-page":"1521","DOI":"10.1134\/s1995080220080132","volume":"41","author":"DA Nikitenko","year":"2020","unstructured":"Nikitenko, D.A., Shvets, P.A., Voevodin, V.V.: Why do users need to take care of their HPC applications efficiency? Lobachevskii J. Math. 41(8), 1521\u20131532 (2020). https:\/\/doi.org\/10.1134\/s1995080220080132","journal-title":"Lobachevskii J. Math."},{"key":"16_CR13","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Rousseeuw, P.J.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53\u201365 (1987). https:\/\/doi.org\/10.1016\/0377-0427(87)90125-7, https:\/\/www.sciencedirect.com\/science\/article\/pii\/0377042787901257","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"16_CR15","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/978-3-030-55326-5_4","volume-title":"Parallel Computational Technologies","author":"D Shaikhislamov","year":"2020","unstructured":"Shaikhislamov, D., Voevodin, V.: Solving the problem of detecting similar supercomputer applications using machine learning methods. In: Sokolinsky, L., Zymbler, M. (eds.) PCT 2020. CCIS, vol. 1263, pp. 46\u201357. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-55326-5_4"},{"issue":"7","key":"16_CR16","doi-asserted-by":"publisher","first-page":"6817","DOI":"10.1007\/s11227-020-03533-2","volume":"77","author":"M Shin","year":"2021","unstructured":"Shin, M., Park, G., Park, C.Y., Lee, J., Kim, M.: Application-specific feature selection and clustering approach with HPC system profiling data. J. Supercomput. 77(7), 6817\u20136831 (2021). https:\/\/doi.org\/10.1007\/s11227-020-03533-2","journal-title":"J. Supercomput."},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Stefanov, K., Voevodin, V., Zhumatiy, S., Voevodin, V.: Dynamically reconfigurable distributed modular monitoring system for supercomputers (dimmon). In: 4th International Young Scientist Conference on Computational Science. Procedia Computer Science, vol. 66, pp. 625\u2013634. Elsevier B.V Netherlands (2015). https:\/\/doi.org\/10.1016\/j.procs.2015.11.071","DOI":"10.1016\/j.procs.2015.11.071"},{"key":"16_CR18","unstructured":"Steinbach, M., Karypis, G., Kumar, V.: A comparison of document clustering techniques. In: KDD Workshop on Text Mining (2000)"},{"key":"16_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-3-319-58667-0_19","volume-title":"High Performance Computing","author":"O Tuncer","year":"2017","unstructured":"Tuncer, O., et al.: Diagnosing performance variations in HPC applications using machine learning. In: Kunkel, J.M., Yokota, R., Balaji, P., Keyes, D. (eds.) ISC High Performance 2017. LNCS, vol. 10266, pp. 355\u2013373. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-58667-0_19"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Voevodin, V.V., et al.: supercomputer lomonosov-2: large scale, deep monitoring and fine analytics for the user community. Supercomput. Front. Innov. 6(2), 4\u201311 (2019). https:\/\/doi.org\/10.14529\/jsfi190201","DOI":"10.14529\/jsfi190201"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Dura\u010d\u00edk, M., Krsak, E., Hrk\u00fat, P.: Scalable source code plagiarism detection using source code vectors clustering, pp. 499\u2013502, November 2018. https:\/\/doi.org\/10.1109\/ICSESS.2018.8663708","DOI":"10.1109\/ICSESS.2018.8663708"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30442-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T10:03:37Z","timestamp":1682589817000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30442-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031304415","9783031304422"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30442-2_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"28 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Processing and Applied Mathematics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gdansk","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppam2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppam.edu.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"132","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":"77","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":"58% - 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":"3","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":"2","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}