{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T18:37:58Z","timestamp":1792780678525,"version":"4.5.0"},"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T00:00:00Z","timestamp":1792713600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shandong Provincial Natural Science Foundation project","award":["ZR2025QC741"],"award-info":[{"award-number":["ZR2025QC741"]}]},{"name":"Innovative Team Pro-ject of Ji\u2019nan Government","award":["202333036"],"award-info":[{"award-number":["202333036"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Traffic accidents arise from the dynamic evolution of traffic flow under spatio-temporal effects, and their occurrence and severity are significantly influenced by temporal and spatial variations in traffic conditions. Traditional studies predominantly rely on static accident-time data, which limits prediction accuracy. To address this gap, this study proposes a deep learning framework that integrates data preprocessing, spatio-temporal effect analysis, PCA-FCM-based risk labeling, and a CNN-BiLSTM hybrid model. Compared with CNN-LSTM, the proposed model replaces unidirectional LSTM with bidirectional LSTM to capture both forward and backward temporal dependencies. Based on the HighD naturalistic trajectory dataset, the CNN-BiLSTM model achieves an MSE of 0.362, RMSE of 0.601, MAE of 0.197 and MAPE of 0.044, outperforming LSTM, BiLSTM and CNN-LSTM with moderate running time. In accident risk classification, it reaches an overall accuracy of 90%, with class-level precision of 0.90\u20130.93 and F1 scores of 0.82\u20130.96. The results demonstrate that the proposed method effectively captures spatio-temporal dynamic characteristics and provides an efficient tool for expressway accident risk prediction.<\/jats:p>","DOI":"10.1371\/journal.pone.0360312","type":"journal-article","created":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:42:46Z","timestamp":1792777366000},"page":"e0360312","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects"],"prefix":"10.1371","volume":"21","author":[{"given":"Liang","family":"Zhao","sequence":"first","affiliation":[{"name":"Shandong Jiaotong University","place":["Jinan, China"],"department":["School of Transportation and Logistics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duo","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jiaotong University","place":["Jinan, China"],"department":["School of Transportation and Logistics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Bai","sequence":"additional","affiliation":[{"name":"Shandong Jiaotong University","place":["Jinan, China"],"department":["School of Transportation and Logistics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2682-4054","authenticated-orcid":true,"given":"Tianzheng","family":"Wei","sequence":"additional","affiliation":[{"name":"Shandong Jiaotong University","place":["Jinan, China"],"department":["School of Transportation and Logistics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Lu","sequence":"additional","affiliation":[{"name":"Shandong Jiaotong University","place":["Jinan, China"],"department":["School of Transportation and Logistics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuguang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong Zhengqu Traffic Engineering Co., Ltd","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,23]]},"reference":[{"key":"pone.0360312.ref001","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.jsr.2017.06.004","article-title":"Factors contributing to commercial vehicle rear-end conflicts in China: A study using on-board event data recorders","volume":"62","author":"G Bianchi Piccinini","year":"2017","journal-title":"J Safety Res"},{"key":"pone.0360312.ref002","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.aap.2017.07.021","article-title":"Glass half-full: On-road glance metrics differentiate crashes from near-crashes in the 100-Car data","volume":"107","author":"BD Seppelt","year":"2017","journal-title":"Accid Anal Prev"},{"key":"pone.0360312.ref003","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.aap.2018.11.010","article-title":"Utilizing UAV video data for in-depth analysis of drivers\u2019 crash risk at interchange merging areas","volume":"123","author":"X Gu","year":"2019","journal-title":"Accid Anal Prev"},{"issue":"6","key":"pone.0360312.ref004","first-page":"206","article-title":"Stability and safety analysis of mixed traffic flow considering multiple preceding and following vehicles","volume":"24","author":"W Du","year":"2024","journal-title":"J Transp Syst Eng Inf Technol"},{"key":"pone.0360312.ref005","doi-asserted-by":"crossref","first-page":"129759","DOI":"10.1016\/j.physa.2024.129759","article-title":"Linear internal stability for mixed traffic flow of CAVs with different automation levels","volume":"642","author":"Z Yao","year":"2024","journal-title":"Phys A: Stat Mech Appl"},{"issue":"05","key":"pone.0360312.ref006","first-page":"165","article-title":"Impact of speed dispersion on traffic safety","volume":"5","author":"Q Fu","year":"2024","journal-title":"Transp Sci Technol Manage"},{"key":"pone.0360312.ref007","first-page":"30","article-title":"Analysis on the relationship between vehicle speed and traffic safety","volume":"13","author":"R Zhang","year":"2020","journal-title":"TranspoWorld"},{"key":"pone.0360312.ref008","doi-asserted-by":"crossref","first-page":"129448","DOI":"10.1016\/j.physa.2023.129448","article-title":"MFOA-Bi-LSTM: An optimized bidirectional long short-term memory model for short-term traffic flow prediction","volume":"634","author":"B Naheliya","year":"2024","journal-title":"Phys A: Stat Mech Appl"},{"issue":"3","key":"pone.0360312.ref009","first-page":"174","article-title":"Spatial transplantation for modeling of freeway traffic crash risk based on dynamic traffic flow","volume":"23","author":"Y Yang","year":"2023","journal-title":"J Transp Syst Eng Inf Technol"},{"issue":"6","key":"pone.0360312.ref010","article-title":"CACC vehicle mixed traffic flow model based on dynamic safety distance","volume":"46","author":"H Lin","year":"2022","journal-title":"J Beijing Jiaotong Univ"},{"key":"pone.0360312.ref011","author":"B Pei","year":"2019"},{"key":"pone.0360312.ref012","doi-asserted-by":"crossref","first-page":"127277","DOI":"10.1016\/j.physa.2022.127277","article-title":"Applying an interpretable machine learning framework to the traffic safety order analysis of expressway exits based on aggregate driving behavior data","volume":"597","author":"H Qi","year":"2022","journal-title":"Phys A: Stat Mech Appl"},{"issue":"4","key":"pone.0360312.ref013","first-page":"61","article-title":"Urban road network characteristics and their influence on traffic accidents","author":"Y Xiao","year":"2023","journal-title":"South Architecture"},{"issue":"21","key":"pone.0360312.ref014","first-page":"74","article-title":"Statistical analysis of urban road traffic accidents","volume":"11","author":"J Li","year":"2021","journal-title":"Technol Innov Appl"},{"issue":"11","key":"pone.0360312.ref015","first-page":"4013","article-title":"Characteristics and mechanism of road traffic accidents","volume":"23","author":"Y Gao","year":"2023","journal-title":"J Safety Environ"},{"issue":"1","key":"pone.0360312.ref016","first-page":"272","article-title":"Research review on traffic safety risk management of rainy weather for traffic disasters","volume":"67","author":"Z Lin","year":"2022","journal-title":"Highway"},{"key":"pone.0360312.ref017","doi-asserted-by":"crossref","first-page":"105249","DOI":"10.1016\/j.aap.2019.07.025","article-title":"Bayesian spatial-temporal model for the main and interaction effects of roadway and weather characteristics on freeway crash incidence","volume":"132","author":"H Wen","year":"2019","journal-title":"Accid Anal Prev"},{"key":"pone.0360312.ref018","author":"C Zhang","year":"2017"},{"key":"pone.0360312.ref019","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.neunet.2021.10.021","article-title":"Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction","volume":"145","author":"A Ali","year":"2022","journal-title":"Neural Netw"},{"key":"pone.0360312.ref020","doi-asserted-by":"crossref","first-page":"108559","DOI":"10.1016\/j.future.2026.108559","article-title":"Exploiting attention-driven weather-aware multimodal spatio-temporal fusion for urban traffic flow prediction","volume":"183","author":"A Ali","year":"2026","journal-title":"Future Generation Comp Syst"},{"key":"pone.0360312.ref021","doi-asserted-by":"crossref","first-page":"116898","DOI":"10.1016\/j.chaos.2025.116898","article-title":"Dynamic multi-graph spatio-temporal learning for citywide traffic flow prediction in transportation systems","volume":"199","author":"A Ali","year":"2025","journal-title":"Chaos, Solitons & Fractals"},{"key":"pone.0360312.ref022","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1016\/j.ins.2021.08.042","article-title":"Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks","volume":"577","author":"A Ali","year":"2021","journal-title":"Info Sci"},{"key":"pone.0360312.ref023","first-page":"61","article-title":"An Energy Efficient Algorithm for Virtual Machine Allocation in Cloud Datacenters","volume-title":"Commun Comp Info Sci","author":"A Ali","year":"2016"},{"issue":"20","key":"pone.0360312.ref024","doi-asserted-by":"crossref","first-page":"31401","DOI":"10.1007\/s11042-020-10486-4","article-title":"A data aggregation based approach to exploit dynamic spatio-temporal correlations for citywide crowd flows prediction in fog computing","volume":"80","author":"A Ali","year":"2021","journal-title":"Multimed Tools Appl"},{"key":"pone.0360312.ref025","doi-asserted-by":"crossref","first-page":"100886","DOI":"10.1016\/j.cosrev.2025.100886","article-title":"Advanced computational models for urban traffic flow prediction: A comprehensive review and future directions","volume":"60","author":"A Ali","year":"2026","journal-title":"Comp Sci Rev"},{"issue":"4","key":"pone.0360312.ref026","doi-asserted-by":"crossref","first-page":"861","DOI":"10.3390\/electronics15040861","article-title":"GISLC: Gated-inception model for skin lesion classification","volume":"15","author":"T Alsarhan","year":"2026","journal-title":"Electronics"},{"key":"pone.0360312.ref027","doi-asserted-by":"crossref","unstructured":"Yang L, Wang W, Zhang Y, Liu Y, Chen Y-C, Xue G, et al. SingSprite: Non-Tactile Appliance Interaction for the Blind through Power-Supply Acoustic Signatures. In: Proceedings of the 2026 ACM\/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems, 2026. 933\u201346. https:\/\/doi.org\/10.1145\/3774906.3800505","DOI":"10.1145\/3774906.3800505"},{"issue":"8","key":"pone.0360312.ref028","doi-asserted-by":"crossref","first-page":"085260","DOI":"10.1088\/1402-4896\/ada4eb","article-title":"Consensus tracking control of incommensurate fractional order multiagent systems using sliding mode for secure communication systems","volume":"100","author":"A Sharafian","year":"2025","journal-title":"Phys Scr"},{"key":"pone.0360312.ref029","doi-asserted-by":"crossref","unstructured":"Schneider P, Butz M, Heinzemann C, Oehlerking J, Woehrle M. Scenario-based threat metric evaluation based on the highd dataset. In: 2020 IEEE Intelligent Vehicles Symposium (IV), 2020. 213\u20138. https:\/\/doi.org\/10.1109\/iv47402.2020.9304726","DOI":"10.1109\/IV47402.2020.9304726"},{"issue":"5","key":"pone.0360312.ref030","first-page":"64","article-title":"Prediction method of highway conflict based on HighD dataset","volume":"20","author":"W Jie","year":"2023","journal-title":"Modern Transportation Technology"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0360312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:42:53Z","timestamp":1792777373000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0360312"}},"subtitle":[],"editor":[{"given":"Lei","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,23]]},"references-count":30,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0360312","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,23]]}}}