{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:07:49Z","timestamp":1764997669852,"version":"3.44.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T00:00:00Z","timestamp":1745193600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T00:00:00Z","timestamp":1745193600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s41060-025-00770-7","type":"journal-article","created":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T17:12:21Z","timestamp":1745255541000},"page":"5361-5376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Active learning in process mining: an active sampling using dimensionality reduction and iterative selection"],"prefix":"10.1007","volume":"20","author":[{"given":"Rafael","family":"Aguilar Magalh\u00e3es","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anderson","family":"Andolfato Filho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo Alves","family":"Portela Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1041-2768","authenticated-orcid":false,"given":"Anderson","family":"Ara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,21]]},"reference":[{"key":"770_CR1","doi-asserted-by":"crossref","unstructured":"Aalst: Big software on the run: In vivo software analytics based on process mining (keynote). In: Proceedings of the 2015 International Conference on Software and System Process, pp. 1\u20135 (2015)","DOI":"10.1145\/2785592.2785593"},{"key":"770_CR2","doi-asserted-by":"crossref","unstructured":"Rubin, V., G\u00fanther, C.W., Aalst, W.M.P., Kindler, E., Dongen, B.F., Sch\u00e1fer, W.: Process mining framework for software processes. In: Software Process Dynamics and Agility, pp. 169\u2013181 (2007)","DOI":"10.1007\/978-3-540-72426-1_15"},{"key":"770_CR3","unstructured":"Settles, B.: Active learning literature survey. Technical Report Computer Sciences Technical Report 1648, University of Wisconsin\u2013Madison (2010)"},{"key":"770_CR4","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1613\/jair.295","volume":"4","author":"DA Cohn","year":"1996","unstructured":"Cohn, D.A., Ghahramani, Z., Jordan, M.I.: Active learning with statistical models. J. Artif. Intell. Res. 4, 129\u2013145 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"770_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.catena.2024.107629","volume":"234","author":"HN Nguyen","year":"2024","unstructured":"Nguyen, H.N., et al.: Active learning-based random forest algorithm used for soil texture classification mapping in central Vietnam. Catena 234, 1\u201313 (2024). https:\/\/doi.org\/10.1016\/j.catena.2024.107629","journal-title":"Catena"},{"key":"770_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13643-023-02257-7","volume":"12","author":"G Ferdinands","year":"2023","unstructured":"Ferdinands, G., Schram, R., Bruin, J., Bagheri, A., Oberski, D.L., Tummers, L., Teijema, J.J., Schoot, R.: Performance of active learning models for screening prioritization in systematic reviews: a simulation study into the average time to discover relevant records. System. Rev. 12, 1\u201312 (2023). https:\/\/doi.org\/10.1186\/s13643-023-02257-7","journal-title":"System. Rev."},{"key":"770_CR7","doi-asserted-by":"publisher","first-page":"28751","DOI":"10.1109\/ACCESS.2023.3260771","volume":"11","author":"D Onita","year":"2023","unstructured":"Onita, D.: Active learning based on transfer learning techniques for text classification. IEEE Access 11, 28751\u201328760 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3260771","journal-title":"IEEE Access"},{"key":"770_CR8","unstructured":"Fukumizu, K.: Active learning in multilayer perceptrons. In: Advances in Neural Information Processing Systems, pp. 485\u2013492 (1995)"},{"issue":"1","key":"770_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-07882-8","volume":"10","author":"J Hoja","year":"2019","unstructured":"Hoja, J., Schneider, E., Tkatchenko, A.: Active learning accelerates global minimum search of nanoclusters. Nat. Commun. 10(1), 1\u20139 (2019)","journal-title":"Nat. Commun."},{"issue":"6","key":"770_CR10","volume":"154","author":"JP Unsleber","year":"2021","unstructured":"Unsleber, J.P., Mattera, A., Meuwly, M.: Active learning of reaction coordinates for the discovery of chemical reactions. J. Chem. Phys. 154(6), 064105 (2021)","journal-title":"J. Chem. Phys."},{"key":"770_CR11","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s10994-009-5100-3","volume":"75","author":"T Kanamori","year":"2009","unstructured":"Kanamori, T., Shimodaira, H.: Pool-based active learning in approximate linear regression. Mach. Learn. 75, 249\u2013274 (2009)","journal-title":"Mach. Learn."},{"key":"770_CR12","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.ins.2018.09.060","volume":"474","author":"D Wu","year":"2019","unstructured":"Wu, D., Lin, C.-T., Huang, J.: Active learning for regression using greedy sampling. Inf. Sci. 474, 90\u2013105 (2019). https:\/\/doi.org\/10.1016\/j.ins.2018.09.060","journal-title":"Inf. Sci."},{"key":"770_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114885","volume":"176","author":"S Dong","year":"2021","unstructured":"Dong, S.: Multi class svm algorithm with active learning for network traffic classification. Expert Syst. Appl. 176, 114885 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.114885","journal-title":"Expert Syst. Appl."},{"key":"770_CR14","doi-asserted-by":"publisher","first-page":"24287","DOI":"10.1007\/s11042-021-10836-w","volume":"80","author":"L Yao","year":"2021","unstructured":"Yao, L., Wan, Y., Ni, H., Xu, B.: Action unit classification for facial expression recognition using active learning and svm. Multimedia Tools Appl. 80, 24287\u201324301 (2021). https:\/\/doi.org\/10.1007\/s11042-021-10836-w","journal-title":"Multimedia Tools Appl."},{"key":"770_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.mtcomm.2024.109731","volume":"40","author":"R Mo","year":"2024","unstructured":"Mo, R., Wu, L., Wang, G., Wang, Q., Ren, J.: Multi-objective optimization of multi-principal element alloys via high-throughput simulation and active learning. Mater. Today Commun. 40, 109731 (2024). https:\/\/doi.org\/10.1016\/j.mtcomm.2024.109731","journal-title":"Mater. Today Commun."},{"key":"770_CR16","doi-asserted-by":"crossref","unstructured":"Eck, M.L., et al.: Pm2: a process mining project methodology. In: CAiSE 2015: Advanced Information Systems Engineering, vol. 9097, pp. 297\u2013313 (2015)","DOI":"10.1007\/978-3-319-19069-3_19"},{"key":"770_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-49851-4","volume-title":"Process Mining-Data Science in Action","author":"W Aalst","year":"2016","unstructured":"Aalst, W.: Process Mining-Data Science in Action, 2nd edn. Springer, New York (2016)","edition":"2"},{"key":"770_CR18","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1007\/978-3-319-98648-7_27","volume-title":"Business Process Management","author":"C Di Francescomarino","year":"2018","unstructured":"Di Francescomarino, C., Ghidini, C., Maggi, F.M., Milani, F.: Predictive process monitoring methods: Which one suits me best? In: Weske, M., Montali, M., Weber, I., Brocke, J. (eds.) Business Process Management, pp. 462\u2013479. Springer, Cham (2018)"},{"key":"770_CR19","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.accinf.2018.11.002","volume":"32","author":"M Jans","year":"2018","unstructured":"Jans, M., Hosseinpour, M.: How active learning and process mining can act as continuous auditing catalyst. Int. J. Account. Inf. Syst. 32, 44\u201358 (2018). https:\/\/doi.org\/10.1016\/j.accinf.2018.11.002","journal-title":"Int. J. Account. Inf. Syst."},{"key":"770_CR20","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1007\/s10844-024-00654-8","volume":"62","author":"F Folino","year":"2024","unstructured":"Folino, F., Folino, G., Guarascio, M., Pontieri, L.: Data- & compute-efficient deviance mining via active learning and fast ensembles. J. Intell. Inf. Syst. 62, 995\u20131019 (2024). https:\/\/doi.org\/10.1007\/s10844-024-00654-8","journal-title":"J. Intell. Inf. Syst."},{"key":"770_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Y.: Active Learning. Lecture Notes. 10-701, Machine Learning, Spring 2011 (2011)","DOI":"10.1007\/978-0-387-30164-8_6"},{"key":"770_CR22","doi-asserted-by":"crossref","unstructured":"RayChaudhuri, T., Hamey, L.: Minimisation of data collection by active learning. In: Proceedings of the IEEE International Conference on Neural Networks, vol. 3, pp. 1338\u20131341. IEEE, Perth (1995)","DOI":"10.1109\/ICNN.1995.487351"},{"key":"770_CR23","doi-asserted-by":"crossref","unstructured":"Cai, W., Zhang, Y., Zhou, J.: Maximizing expected model change for active learning in regression. In: Proceedings of the IEEE 13th International Conference on Data Mining, pp. 51\u201360. IEEE, Dallas (2013)","DOI":"10.1109\/ICDM.2013.104"},{"key":"770_CR24","doi-asserted-by":"publisher","unstructured":"Hamad, R., J\u00e4rpe, E., Lundstr\u00f6m, J.: Stability analysis of the t-sne algorithm for human activity pattern data (2018). https:\/\/doi.org\/10.1109\/SMC.2018.00318","DOI":"10.1109\/SMC.2018.00318"},{"issue":"301","key":"770_CR25","first-page":"1","volume":"23","author":"TT Cai","year":"2022","unstructured":"Cai, T.T., Ma, R.: Theoretical foundations of t-sne for visualizing high-dimensional clustered data. J. Mach. Learn. Res. 23(301), 1\u201354 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"770_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116981","volume":"199","author":"H Anahideh","year":"2022","unstructured":"Anahideh, H., Asudeh, A., Thirumuruganathan, S.: Fair active learning. Expert Syst. Appl. 199, 116981 (2022). https:\/\/doi.org\/10.1016\/j.eswa.2022.116981","journal-title":"Expert Syst. Appl."},{"key":"770_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108605","volume":"176","author":"HS Tan","year":"2024","unstructured":"Tan, H.S., Wang, K., Mcbeth, R.: Exploring umap in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation. Comput. Biol. Med. 176, 108605 (2024). https:\/\/doi.org\/10.1016\/j.compbiomed.2024.108605","journal-title":"Comput. Biol. Med."},{"issue":"6","key":"770_CR28","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1162\/neco.2007.19.6.1503","volume":"19","author":"H Shimazaki","year":"2007","unstructured":"Shimazaki, H., Shinomoto, S.: A method for selecting the bin size of a time histogram. Neural Comput. 19(6), 1503\u20131527 (2007). https:\/\/doi.org\/10.1162\/neco.2007.19.6.1503","journal-title":"Neural Comput."},{"key":"770_CR29","doi-asserted-by":"crossref","unstructured":"Cai, W., Zhang, Y., Zhou, J.: Maximizing expected model change for active learning in regression. In: Proceedings of the 13th IEEE International Conference on Data Mining. IEEE, Shanghai (2013)","DOI":"10.1109\/ICDM.2013.104"},{"key":"770_CR30","unstructured":"Bhaskara, A., Vadgama, S., Xu, H.: Greedy sampling for approximate clustering in the presence of outliers. In: Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS), pp. 1\u201313 (2019)"},{"issue":"14","key":"770_CR31","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1016\/j.patrec.2010.03.014","volume":"31","author":"R Genuer","year":"2010","unstructured":"Genuer, R., Poggi, J.-M., Tuleau-Malot, C.: Variable selection using random forests. Pattern Recogn. Lett. 31(14), 2225\u20132236 (2010). https:\/\/doi.org\/10.1016\/j.patrec.2010.03.014","journal-title":"Pattern Recogn. Lett."},{"key":"770_CR32","doi-asserted-by":"publisher","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edn. Springer, New York (2009). https:\/\/doi.org\/10.1007\/978-0-387-84858-7, https:\/\/link.springer.com\/book\/10.1007\/978-0-387-84858-7","DOI":"10.1007\/978-0-387-84858-7"},{"issue":"6","key":"770_CR33","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bull. 1(6), 80\u201383 (1945)","journal-title":"Biometrics Bull."},{"key":"770_CR34","volume-title":"Nonparametric Statistical Methods","author":"M Hollander","year":"2013","unstructured":"Hollander, M., Wolfe, D.A., Chicken, E.: Nonparametric Statistical Methods. Wiley, New York (2013)"},{"issue":"2","key":"770_CR35","doi-asserted-by":"publisher","first-page":"116","DOI":"10.4103\/jpcs.jpcs_18_20","volume":"6","author":"S Onchiri","year":"2020","unstructured":"Onchiri, S., Mangera, C.M.: F-test of overall significance in regression analysis simplified. J. Pract. Cardiovasc. Sci. 6(2), 116\u2013122 (2020). https:\/\/doi.org\/10.4103\/jpcs.jpcs_18_20","journal-title":"J. Pract. Cardiovasc. Sci."},{"key":"770_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117107","volume":"202","author":"A Ara","year":"2022","unstructured":"Ara, A., Maia, M., Louzada, F., Mac\u00eado, S.: Regression random machines: an ensemble support vector regression model with free kernel choice. Expert Syst. Appl. 202, 117107 (2022). https:\/\/doi.org\/10.1016\/j.eswa.2022.117107","journal-title":"Expert Syst. Appl."},{"key":"770_CR37","unstructured":"Scikit-learn: sklearn.feature_selection.f_regression. Accessed: 2024, 09, 21 (2021). https:\/\/scikit-learn.org\/0.24\/modules\/generated\/sklearn.feature_selection.f_regression.html"},{"key":"770_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-1418-1","volume-title":"An Introduction to Statistical Learning: with Applications in R","author":"G James","year":"2021","unstructured":"James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning: with Applications in R, 2nd edn. Springer, New York (2021)","edition":"2"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-025-00770-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-025-00770-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-025-00770-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T12:16:49Z","timestamp":1758975409000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-025-00770-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,21]]},"references-count":38,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["770"],"URL":"https:\/\/doi.org\/10.1007\/s41060-025-00770-7","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"type":"print","value":"2364-415X"},{"type":"electronic","value":"2364-4168"}],"subject":[],"published":{"date-parts":[[2025,4,21]]},"assertion":[{"value":"27 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}