{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:57:58Z","timestamp":1790791078997,"version":"4.1.0"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["NSFSC0937"],"award-info":[{"award-number":["NSFSC0937"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intelligent Policing Key Laboratory of Sichuan Province","award":["ZNJW2025KFQN006"],"award-info":[{"award-number":["ZNJW2025KFQN006"]}]},{"name":"Key Laboratory of Intelligent Policing and National Security Risk Management","award":["ZHZZQN2503"],"award-info":[{"award-number":["ZHZZQN2503"]}]},{"name":"Intelligent Policing and National Security Risk Management Laboratory","award":["ZHKFYB2602"],"award-info":[{"award-number":["ZHKFYB2602"]}]},{"name":"Key Laboratory of Automotive Measurement, Control and Safety","award":["QCCK2025-005"],"award-info":[{"award-number":["QCCK2025-005"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate prediction of freeway incident duration is important for traffic management and emergency resource allocation. This study evaluates 32 machine-learning model configurations using 828 incident records from the G2504 Hangzhou Ring Freeway in China. Four fixed feature sets containing the top 6, 11, 16, and 21 predictors were defined from a Minimum Redundancy Maximum Relevance (MRMR) ranking. Each feature setting was evaluated using a 15% hold-out test set, seven repeated random splits, and sevenfold cross-validation within the training subset. All 32 machine-learning models were tuned within the training subset using sevenfold cross-validation. To provide a concise description of the tuning procedure, the selected Medium Gaussian support vector machine, which provided the most balanced overall performance, is reported as a representative example. Performance was assessed using the mean absolute error (MAE) and the mean absolute percentage error (MAPE). The Medium Gaussian support vector machine provided the most balanced overall performance, and prediction accuracy generally improved from 6 to 16 predictors, with little additional benefit from 21 predictors. Compared with classical linear regression, the Medium Gaussian support vector machine reduced MAE by 5.7%\u20139.7% and MAPE by 21.2%\u201331.9% across the four feature settings. A sensitivity comparison showed substantially higher errors when incidents longer than 60 minutes were retained, reinforcing that the main findings apply to routine incidents. Interpretation analyses identified Response Time and severity-related variables as important predictors, while residual errors remained larger for longer and more complex incidents. The model is intended primarily for post-arrival updating and clearance-support decisions for routine freeway incidents, rather than prediction at the initial alarm stage.<\/jats:p>","DOI":"10.1371\/journal.pone.0359353","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:27:02Z","timestamp":1790789222000},"page":"e0359353","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting freeway incident duration using machine learning"],"prefix":"10.1371","volume":"21","author":[{"given":"Yanni","family":"Ju","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Policing and National Security Risk Management, Sichuan Police College","place":["Luzhou, China"]},{"name":"Sichuan Police College","place":["Luzhou, China"],"department":["Department of Road Traffic Management"]},{"name":"Intelligent Policing Key Laboratory of Sichuan Province","place":["Luzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingqi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Automobile and Traffic Engineering, Nanjing Forestry University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mostafa K.","family":"Ardakani","sequence":"additional","affiliation":[{"name":"Kent State University","place":["Ohio, United States of America"],"department":["Department of Information Systems and Business Analytics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanqiu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Automobile and Traffic Engineering, Nanjing Forestry University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5535-6467","authenticated-orcid":true,"given":"Gen","family":"Li","sequence":"additional","affiliation":[{"name":"College of Automobile and Traffic Engineering, Nanjing Forestry University","place":["Nanjing, Jiangsu, China"]},{"name":"Xihua University","place":["Chengdu, China"],"department":["Key Laboratory of Automotive Measurement, Control and Safety"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"pone.0359353.ref001","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.aap.2012.12.037","article-title":"Hazard based models for freeway traffic incident duration","volume":"52","author":"A Tavassoli Hojati","year":"2013","journal-title":"Accid Anal Prev"},{"key":"pone.0359353.ref002","doi-asserted-by":"crossref","first-page":"100267","DOI":"10.1016\/j.amar.2023.100267","article-title":"Incorporating real-time weather conditions into analyzing clearance time of freeway accidents: A grouped random parameters hazard-based duration model with time-varying covariates","volume":"38","author":"Q Zeng","year":"2023","journal-title":"Analytic Methods in Accident Res"},{"key":"pone.0359353.ref003","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s12544-024-00632-6","article-title":"Predicting the duration of motorway incidents using machine learning","volume":"16","author":"R Corbally","year":"2024","journal-title":"Eur Transp Res Rev"},{"issue":"2","key":"pone.0359353.ref004","doi-asserted-by":"crossref","first-page":"100209","DOI":"10.1016\/j.multra.2025.100209","article-title":"Explainable artificial intelligence visions on incident duration using eXtreme Gradient Boosting and SHapley Additive exPlanations","volume":"4","author":"K Hamad","year":"2025","journal-title":"Multimodal Transportation"},{"key":"pone.0359353.ref005","doi-asserted-by":"crossref","first-page":"123621","DOI":"10.1016\/j.techfore.2024.123621","article-title":"Prediction of the traffic incident duration using statistical and machine-learning methods: A systematic literature review","volume":"207","author":"H Korkmaz","year":"2024","journal-title":"Technol Forecasting Social Change"},{"key":"pone.0359353.ref006","doi-asserted-by":"crossref","first-page":"100123","DOI":"10.1016\/j.amar.2020.100123","article-title":"Statistical and machine-learning methods for clearance time prediction of road incidents: A methodology review","volume":"27","author":"J Tang","year":"2020","journal-title":"Analytic Methods in Accident Research"},{"issue":"12","key":"pone.0359353.ref007","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.3390\/su9122331","article-title":"Identification of critical factors for non-recurrent congestion induced by urban freeway crashes and its mitigating strategies","volume":"9","author":"Y Chung","year":"2017","journal-title":"Sustainability"},{"key":"pone.0359353.ref008","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.trb.2018.08.013","article-title":"Role of road network features in the evaluation of incident impacts on urban traffic mobility","volume":"117","author":"C Sun","year":"2018","journal-title":"Transportation Research Part B: Methodological"},{"issue":"22","key":"pone.0359353.ref009","doi-asserted-by":"crossref","first-page":"14982","DOI":"10.3390\/su142214982","article-title":"Study on the Impact of Road Traffic Accident Duration Based on Statistical Analysis and Spatial Distribution Characteristics: An Empirical Analysis of Houston","volume":"14","author":"X Sun","year":"2022","journal-title":"Sustainability"},{"issue":"2","key":"pone.0359353.ref010","first-page":"85","article-title":"An exploratory hazard-based analysis of highway incident duration","volume":"34","author":"D Nam","year":"2000","journal-title":"Transportation Research Part A: Policy and Practice"},{"issue":"4","key":"pone.0359353.ref011","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1049\/iet-its.2014.0036","article-title":"Traffic incident duration analysis and prediction models based on the survival analysis approach","volume":"9","author":"R Li","year":"2015","journal-title":"IET Intelligent Trans Sys"},{"key":"pone.0359353.ref012","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.trc.2015.03.009","article-title":"Competing risk mixture model and text analysis for sequential incident duration prediction","volume":"54","author":"R Li","year":"2015","journal-title":"Transportation Res Part C: Emerging Technologies"},{"key":"pone.0359353.ref013","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.trc.2017.11.004","article-title":"Jointly analyzing freeway traffic incident clearance and response time using a copula-based approach","volume":"86","author":"Y Zou","year":"2018","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"pone.0359353.ref014","doi-asserted-by":"crossref","first-page":"107806","DOI":"10.1016\/j.aap.2024.107806","article-title":"Unraveling the determinants of traffic incident duration: A causal investigation using the framework of causal forests with debiased machine learning","volume":"208","author":"Y Guo","year":"2024","journal-title":"Accid Anal Prev"},{"issue":"4","key":"pone.0359353.ref015","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1109\/TITS.2011.2161634","article-title":"Prediction of Lane Clearance Time of Freeway Incidents Using the M5P Tree Algorithm","volume":"12","author":"C Zhan","year":"2011","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"3","key":"pone.0359353.ref016","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1080\/23249935.2020.1733132","article-title":"Predicting incident duration using random forests","volume":"16","author":"K Hamad","year":"2020","journal-title":"Transportmetrica A: Transport Science"},{"key":"pone.0359353.ref017","doi-asserted-by":"crossref","first-page":"6401082","DOI":"10.1155\/2020\/6401082","article-title":"Traffic incident clearance time prediction and influencing factor analysis using extreme gradient boosting model","volume":"2020","author":"J Tang","year":"2020","journal-title":"J Adv Transp"},{"issue":"11","key":"pone.0359353.ref018","doi-asserted-by":"crossref","first-page":"4019","DOI":"10.1109\/TITS.2018.2878637","article-title":"Dynamic Prediction of the Incident Duration Using Adaptive Feature Set","volume":"20","author":"B Ghosh","year":"2019","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"1","key":"pone.0359353.ref019","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1177\/0361198119899041","article-title":"Sequential prediction for large-scale traffic incident duration: application and comparison of survival models","volume":"2674","author":"X Li","year":"2020","journal-title":"Transp Res Rec"},{"key":"pone.0359353.ref020","doi-asserted-by":"crossref","first-page":"103721","DOI":"10.1016\/j.trc.2022.103721","article-title":"Incident duration prediction using a bi-level machine learning framework with outlier removal and intra\u2013extra joint optimisation","volume":"141","author":"A Grigorev","year":"2022","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"17","key":"pone.0359353.ref021","doi-asserted-by":"crossref","first-page":"10903","DOI":"10.3390\/ijerph191710903","article-title":"Prediction of Duration of Traffic Incidents by Hybrid Deep Learning Based on Multi-Source Incomplete Data","volume":"19","author":"Q Shang","year":"2022","journal-title":"Int J Environ Res Public Health"},{"issue":"1","key":"pone.0359353.ref022","doi-asserted-by":"crossref","first-page":"21478","DOI":"10.1038\/s41598-022-25988-4","article-title":"Traffic accident duration prediction using text mining and ensemble learning on expressways","volume":"12","author":"J Chen","year":"2022","journal-title":"Sci Rep"},{"issue":"4","key":"pone.0359353.ref023","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e25957","article-title":"Traffic accident duration prediction using multi-mode data and ensemble deep learning","volume":"10","author":"J Chen","year":"2024","journal-title":"Heliyon"},{"issue":"16","key":"pone.0359353.ref024","doi-asserted-by":"crossref","first-page":"6821","DOI":"10.3390\/su16166821","article-title":"A Novel Accident Duration Prediction Method Based on a Conditional Table Generative Adversarial Network and Transformer","volume":"16","author":"Y Wang","year":"2024","journal-title":"Sustainability"},{"issue":"1","key":"pone.0359353.ref025","doi-asserted-by":"crossref","first-page":"2018643","DOI":"10.1080\/08839514.2021.2018643","article-title":"Prediction in traffic accident duration based on heterogeneous ensemble learning","volume":"36","author":"Y Zhao","year":"2022","journal-title":"Appl Artif Intell"},{"key":"pone.0359353.ref026","doi-asserted-by":"crossref","first-page":"108405","DOI":"10.1016\/j.aap.2026.108405","article-title":"Enhancing vision-based traffic crash detection performance consistency across day-night scenes: A depth-aware and domain-adaptive network","volume":"228","author":"Y Yang","year":"2026","journal-title":"Accid Anal Prev"},{"key":"pone.0359353.ref027","doi-asserted-by":"crossref","first-page":"108282","DOI":"10.1016\/j.aap.2025.108282","article-title":"A new framework for modelling traffic conflict interval time based on correlated random parameter duration model with heterogeneity in means and variances","volume":"224","author":"G Li","year":"2026","journal-title":"Accid Anal Prev"},{"key":"pone.0359353.ref028","doi-asserted-by":"crossref","first-page":"104420","DOI":"10.1016\/j.jtrangeo.2025.104420","article-title":"A systematic review of resilience assessment and enhancement of urban integrated transportation networks","volume":"129","author":"Y Yang","year":"2025","journal-title":"J Transp Geogr"},{"key":"pone.0359353.ref029","first-page":"1","article-title":"Exploring factors of e-bike rider\u2019s hit-and-run behavior of e-bike crashes on urban and rural roads using Light Gradient Boosting machine and SHapley additive explanations","author":"G Li","year":"2026","journal-title":"Transport Letters"},{"issue":"2","key":"pone.0359353.ref030","doi-asserted-by":"crossref","first-page":"204","DOI":"10.3390\/systems14020204","article-title":"A real-time early warning framework for multi-dimensional driving risk of heavy-duty trucks using trajectory data","volume":"14","author":"Q Luo","year":"2026","journal-title":"Systems"},{"issue":"5","key":"pone.0359353.ref031","doi-asserted-by":"crossref","first-page":"831","DOI":"10.3390\/sym18050831","article-title":"Unveiling risk reconfiguration in freeway merging areas: A spatiotemporal framework for conflict prediction and hotspot migration in CAV mixed traffic","volume":"18","author":"Q Luo","year":"2026","journal-title":"Symmetry"},{"key":"pone.0359353.ref032","author":"MATLAB R 2024b","year":"2024"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:27:09Z","timestamp":1790789229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359353"}},"subtitle":[],"editor":[{"given":"Chenfeng","family":"Xiong","sequence":"first","affiliation":[{"name":"Villanova University","place":["UNITED STATES OF AMERICA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":32,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359353","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}