{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:26:10Z","timestamp":1772119570368,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"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":["Cluster Comput"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s10586-023-04139-y","type":"journal-article","created":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T11:01:21Z","timestamp":1695553281000},"page":"3219-3231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["I\/O-signature-based feature analysis and classification of high-performance computing applications"],"prefix":"10.1007","volume":"27","author":[{"given":"Ju-Won","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae-Kook","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taeyoung","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,24]]},"reference":[{"key":"4139_CR1","unstructured":"(2023) Iozone. http:\/\/www.iozone.org"},{"issue":"2","key":"4139_CR2","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.datak.2007.03.016","volume":"63","author":"A Ahmad","year":"2007","unstructured":"Ahmad, A., Dey, L.: A k-mean clustering algorithm for mixed numeric and categorical data. Data Knowl. Eng. 63(2), 503\u2013527 (2007)","journal-title":"Data Knowl. Eng."},{"key":"4139_CR3","doi-asserted-by":"crossref","unstructured":"Bang, J., Kim, C., Wu K, et\u00a0al.: Hpc workload characterization using feature selection and clustering. In: Proceedings of the 3rd International Workshop on Systems and Network Telemetry and Analytics, pp. 33\u201340 (2020)","DOI":"10.1145\/3391812.3396270"},{"issue":"4","key":"4139_CR4","first-page":"1","volume":"5","author":"B Behzad","year":"2019","unstructured":"Behzad, B., Byna, S., Snir, M.: Optimizing I\/O performance of HPC applications with autotuning. ACM Trans. Parallel Comput. (TOPC) 5(4), 1\u201327 (2019)","journal-title":"ACM Trans. Parallel Comput. (TOPC)"},{"issue":"2","key":"4139_CR5","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1016\/j.eswa.2006.10.022","volume":"34","author":"A Ben-David","year":"2008","unstructured":"Ben-David, A.: Comparison of classification accuracy using Cohen\u2019s weighted kappa. Expert Syst. Appl. 34(2), 825\u2013832 (2008)","journal-title":"Expert Syst. Appl."},{"key":"4139_CR6","doi-asserted-by":"crossref","unstructured":"Betke, E., Kunkel, J.: Footprinting parallel I\/O\u2013machine learning to classify application\u2019s I\/O behavior. In: High Performance Computing: ISC High Performance 2019 International Workshops, Frankfurt, Germany, June 16\u201320, 2019, Revised Selected Papers 34, Springer, pp 214\u2013226 (2019)","DOI":"10.1007\/978-3-030-34356-9_18"},{"key":"4139_CR7","doi-asserted-by":"publisher","unstructured":"Busch, A., Noorshams, Q., Kounev, S., et\u00a0al.: Automated workload characterization for I\/O performance analysis in virtualized environments. In: Proceedings of the 6th ACM\/SPEC International Conference on Performance Engineering. Association for Computing Machinery, New York, NY, USA, ICPE \u201915, pp 265\u2013276. https:\/\/doi.org\/10.1145\/2668930.2688050 (2015)","DOI":"10.1145\/2668930.2688050"},{"issue":"3","key":"4139_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2027066.2027068","volume":"7","author":"P Carns","year":"2011","unstructured":"Carns, P., Harms, K., Allcock, W., et al.: Understanding and improving computational science storage access through continuous characterization. ACM Trans. Storage (TOS) 7(3), 1\u201326 (2011)","journal-title":"ACM Trans. Storage (TOS)"},{"key":"4139_CR9","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","volume":"61","author":"A Fern\u00e1ndez","year":"2018","unstructured":"Fern\u00e1ndez, A., Garcia, S., Herrera, F., et al.: Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intell. Res. 61, 863\u2013905 (2018)","journal-title":"J. Artif. Intell. Res."},{"key":"4139_CR10","doi-asserted-by":"crossref","unstructured":"Gainaru, A., Aupy, G., Benoit, A., et\u00a0al.: Scheduling the I\/O of HPC applications under congestion. In: 2015 IEEE International Parallel and Distributed Processing Symposium, IEEE, pp. 1013\u20131022 (2015)","DOI":"10.1109\/IPDPS.2015.116"},{"key":"4139_CR11","unstructured":"Han, H., Guo, X., Yu, H.: Variable selection using mean decrease accuracy and mean decrease gini based on random forest. In: 2016 7th IEEE International Conference on Software Engineering and Service Science (icsess), IEEE, pp. 219\u2013224 (2016)"},{"issue":"102","key":"4139_CR12","first-page":"318","volume":"157","author":"AM Karimi","year":"2022","unstructured":"Karimi, A.M., Paul, A.K., Wang, F.: I\/O performance analysis of machine learning workloads on leadership scale supercomputer. Perform. Eval. 157(102), 318 (2022)","journal-title":"Perform. Eval."},{"key":"4139_CR13","doi-asserted-by":"crossref","unstructured":"Kim, S., Sim, A., Wu, K., et\u00a0al.: Towards HPC I\/O performance prediction through large-scale log analysis. In: Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing, pp. 77\u201388 (2020)","DOI":"10.1145\/3369583.3392678"},{"key":"4139_CR14","doi-asserted-by":"crossref","unstructured":"Kougkas, A., Dorier, M., Latham, R., et\u00a0al.: Leveraging burst buffer coordination to prevent I\/O interference. In: 2016 IEEE 12th International Conference on e-Science (e-Science), IEEE, pp. 371\u2013380 (2016)","DOI":"10.1109\/eScience.2016.7870922"},{"key":"4139_CR15","doi-asserted-by":"crossref","unstructured":"Kumar, S., Ramasree, R.: Dimensionality reduction in automated evaluation of descriptive answers through zero variance, near zero variance and non frequent words techniques-a comparison. In: 2015 IEEE 9th International Conference on Intelligent Systems and Control (ISCO), IEEE, pp. 1\u20136 (2015)","DOI":"10.1109\/ISCO.2015.7282351"},{"key":"4139_CR16","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, Y., Xu, B., et\u00a0al.: Pipuls: Predicting I\/O patterns using LSTM in storage systems. In: 2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD &IS), IEEE, pp. 14\u201321 (2019)","DOI":"10.1109\/HPBDIS.2019.8735467"},{"key":"4139_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lewis, R., Kettimuthu, R., et\u00a0al.: Characterization and identification of HPC applications at leadership computing facility. In: Proceedings of the 34th ACM International Conference on Supercomputing, pp. 1\u201312 (2020)","DOI":"10.1145\/3392717.3392774"},{"key":"4139_CR18","doi-asserted-by":"crossref","unstructured":"McKenna, R., Herbein, S., Moody, A., et\u00a0al.: Machine learning predictions of runtime and io traffic on high-end clusters. In: 2016 IEEE International Conference on Cluster Computing (CLUSTER), IEEE, pp. 255\u2013258 (2016)","DOI":"10.1109\/CLUSTER.2016.58"},{"key":"4139_CR19","doi-asserted-by":"crossref","unstructured":"Neuwirth, S., Paul, A.K.: Parallel I\/O evaluation techniques and emerging HPC workloads: a perspective. In: 2021 IEEE International Conference on Cluster Computing (CLUSTER), IEEE, pp. 671\u2013679 (2021)","DOI":"10.1109\/Cluster48925.2021.00100"},{"key":"4139_CR20","unstructured":"Neuwirth, S.M.: Accelerating network communication and I\/O in scientific high performance computing environments. PhD thesis (2019)"},{"key":"4139_CR21","doi-asserted-by":"crossref","unstructured":"Nitzberg, B., Schopf, J.M., Jones, J.P.: Pbs pro: Grid computing and scheduling attributes. Grid resource management: state of the art and future trends, pp. 183\u2013190 (2004)","DOI":"10.1007\/978-1-4615-0509-9_13"},{"key":"4139_CR22","unstructured":"Scheiner, S.M.: Manova: multiple response variables and multispecies interactions. In: Design and Analysis of Ecological Experiments. Chapman and Hall\/CRC, Boca Raton, pp. 94\u2013112 (2020)"},{"issue":"3","key":"4139_CR23","first-page":"19","volume":"3","author":"JF Schmidt","year":"2016","unstructured":"Schmidt, J.F., Kunkel, J.M.: Predicting I\/O performance in HPC using artificial neural networks. Supercomput. Front. Innov. 3(3), 19\u201333 (2016)","journal-title":"Supercomput. Front. Innov."},{"issue":"12","key":"4139_CR24","doi-asserted-by":"publisher","first-page":"3026","DOI":"10.1109\/TC.2013.187","volume":"63","author":"B Seo","year":"2013","unstructured":"Seo, B., Kang, S., Choi, J., et al.: Io workload characterization revisited: a data-mining approach. IEEE Trans. Comput. 63(12), 3026\u20133038 (2013)","journal-title":"IEEE Trans. Comput."},{"issue":"2","key":"4139_CR25","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1177\/1094342006064482","volume":"20","author":"SS Shende","year":"2006","unstructured":"Shende, S.S., Malony, A.D.: The tau parallel performance system. Int. J. High Perform. Comput. Appl. 20(2), 287\u2013311 (2006)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"5","key":"4139_CR26","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/TC.2020.2964767","volume":"69","author":"J Sun","year":"2020","unstructured":"Sun, J., Sun, G., Zhan, S., et al.: Automated performance modeling of HPC applications using machine learning. IEEE Trans. Comput. 69(5), 749\u2013763 (2020)","journal-title":"IEEE Trans. Comput."},{"issue":"4","key":"4139_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4172\/2161-0487.1000197","volume":"5","author":"MJ Warrens","year":"2015","unstructured":"Warrens, M.J.: Five ways to look at Cohen\u2019s kappa. J. Psychol. Psychother. 5(4), 1 (2015)","journal-title":"J. Psychol. Psychother."},{"key":"4139_CR28","doi-asserted-by":"crossref","unstructured":"Xie, B., Tan, Z., Carns, P., et\u00a0al.: Interpreting write performance of supercomputer I\/O systems with regression models. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, pp. 557\u2013566 (2021)","DOI":"10.1109\/IPDPS49936.2021.00064"},{"issue":"2","key":"4139_CR29","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1111\/j.2517-6161.1953.tb00140.x","volume":"15","author":"F Yates","year":"1953","unstructured":"Yates, F., Grundy, P.M.: Selection without replacement from within strata with probability proportional to size. J. R. Stat. Soc.: Ser. B (Methodol.) 15(2), 253\u2013261 (1953)","journal-title":"J. R. Stat. Soc.: Ser. B (Methodol.)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-023-04139-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-023-04139-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-023-04139-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T17:20:54Z","timestamp":1730136054000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-023-04139-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,24]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["4139"],"URL":"https:\/\/doi.org\/10.1007\/s10586-023-04139-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3329294\/v1","asserted-by":"object"}]},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,24]]},"assertion":[{"value":"7 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}