{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:50:23Z","timestamp":1782222623739,"version":"3.54.5"},"reference-count":62,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Transactions in GIS"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Classifying urban traffic crash severity remains challenging because severe incidents are underrepresented in highly imbalanced datasets. This challenge is further intensified by spatiotemporal shifts in data distributions, which can degrade model performance over time. To address these challenges, this study proposes an integrated framework that combines Geographic Information Systems (GIS), resampling techniques, and active learning. GIS\u2010based random undersampling and the Synthetic Minority Oversampling Technique (SMOTE) were applied to generate a balanced dataset while preserving spatial and temporal structures. Five classification algorithms were evaluated, with Random Forest achieving the strongest baseline performance. To adapt to evolving data, an active learning framework was implemented to iteratively select uncertain samples for expert annotation, guided by Shapley Additive Explanations (SHAP). After annotating 20 samples, the proposed model achieved an F1\u2010score of 0.9064 and an AUC\u2013PR of 0.9087, outperforming the baseline models. The results demonstrate that integrating GIS\u2010informed resampling with explainability\u2010guided active learning improves robustness and predictive accuracy under dynamic urban conditions. The proposed approach supports more reliable crash severity classification and offers practical insights for data\u2010driven traffic safety analysis and intervention planning.<\/jats:p>","DOI":"10.1111\/tgis.70220","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:16:19Z","timestamp":1772990179000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A\n                    <scp>GIS<\/scp>\n                    \u2010Integrated Active Learning Framework for Crash Severity Classification in Imbalanced Traffic Data"],"prefix":"10.1111","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2971-4678","authenticated-orcid":false,"given":"Reza","family":"Mohammadi","sequence":"first","affiliation":[{"name":"Spatial Decision Making &amp; Smart Cities Lab, Faculty of Geodesy and Geomatics Engineering K. N. Toosi University of Technology  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8419-4425","authenticated-orcid":false,"given":"Mohammad","family":"Taleai","sequence":"additional","affiliation":[{"name":"Spatial Decision Making &amp; Smart Cities Lab, Faculty of Geodesy and Geomatics Engineering K. N. Toosi University of Technology  Tehran Iran"},{"name":"School of Built Environment, Faculty of Arts, Design &amp; Architecture University of New South Wales (UNSW)  Sydney New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106314"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470594001"},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","unstructured":"Al Mamun A. A.Enan D. A.Indah J.Mwakalonge G.Comert andM.Chowdhury.2024.\u201cCrash Severity Risk Modeling Strategies Under Data Imbalance.\u201dhttps:\/\/doi.org\/10.48550\/arXiv.2412.02094.","DOI":"10.1177\/03611981251376371"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/03611981251337460"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2023.107378"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1992.10475879"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112832"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1538\u20104632.1995.tb00338.x"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.18612"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/math8091478"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.AAP.2015.03.036"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.JSR.2025.02.018"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.TRC.2024.104642"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_10_18_1","first-page":"224","volume-title":"Proceedings of the 2021 International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA)","author":"Chen Y.","year":"2021"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/13588265.2022.2028471"},{"key":"e_1_2_10_20_1","first-page":"335","volume-title":"Proceedings of the 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2011)","author":"Doquire G.","year":"2011"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/infrastructures5070061"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2021.108019"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/APP14167176"},{"key":"e_1_2_10_24_1","unstructured":"Herdiana I. M. A.Kamal Triyani M. N.Estri andRenny.2025.\u201cA More Precise Elbow Method for Optimum K\u2010Means Clustering.\u201dhttps:\/\/doi.org\/10.48550\/arXiv.2502.00851."},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.04476"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/17457300.2021.1928233"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/ELECTRONICS14020272"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/13588265.2024.2406972"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2018.08.025"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/su13169137"},{"key":"e_1_2_10_31_1","unstructured":"Kim J. K.2024. \u201cStatistics in Survey Sampling.\u201d ArXiv Preprint ArXiv:2401.07625.https:\/\/doi.org\/10.48550\/arXiv.2401.07625."},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2023.107271"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3091681"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207798"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/tgis.12890"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1111\/tgis.13138"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/MATH12121898"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.07353"},{"key":"e_1_2_10_40_1","unstructured":"Moosavi S. M. H.Samavatian S.Parthasarathy andR.Ramnath.2019. \u201cA Countrywide Traffic Accident Dataset.\u201d ArXiv Preprint ArXiv:1906.05409.https:\/\/doi.org\/10.48550\/arXiv.1906.05409."},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3347146.3359078"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2021.106240"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201010970\u20107"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2015.12.003"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21903-5_8"},{"key":"e_1_2_10_46_1","unstructured":"Nuggehalli S. J.Zhang L.Jain andR.Nowak.2023.\u201cImproved Algorithm for Deep Active Learning Under Imbalance via Optimal Separation.\u201dhttps:\/\/doi.org\/10.48550\/arXiv.2312.09196."},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/13588265.2022.2074643"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105610"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429292507"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2020.104616"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2019.02.008"},{"key":"e_1_2_10_52_1","unstructured":"Settles B.2009.\u201cActive Learning Literature Survey.\u201d"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538\u20107305.1948.tb01338.x"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1108\/DTA\u201010\u20102021\u20100296"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596486"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3211947"},{"key":"e_1_2_10_57_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"key":"e_1_2_10_58_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201009226\u20101"},{"key":"e_1_2_10_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105936"},{"key":"e_1_2_10_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917223"},{"key":"e_1_2_10_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42452\u2010020\u20103125\u20101"},{"key":"e_1_2_10_62_1","unstructured":"Zhan X. Q.Wang B.Research et\u00a0al.2022.\u201cA Comparative Survey of Deep Active Learning.\u201dhttps:\/\/arxiv.org\/pdf\/2203.13450."},{"key":"e_1_2_10_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/S13177\u2010024\u201000440\u20101"}],"container-title":["Transactions in GIS"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tgis.70220","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/tgis.70220","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tgis.70220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:04:19Z","timestamp":1782219859000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/tgis.70220"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":62,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/tgis.70220"],"URL":"https:\/\/doi.org\/10.1111\/tgis.70220","archive":["Portico"],"relation":{},"ISSN":["1361-1682","1467-9671"],"issn-type":[{"value":"1361-1682","type":"print"},{"value":"1467-9671","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]},"assertion":[{"value":"2025-05-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70220"}}