{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T17:30:54Z","timestamp":1793467854302,"version":"4.5.0"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005374","name":"Nanjing University of Posts and Telecommunications","doi-asserted-by":"publisher","award":["NY222030"],"award-info":[{"award-number":["NY222030"]}],"id":[{"id":"10.13039\/501100005374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52202408"],"award-info":[{"award-number":["52202408"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52572370"],"award-info":[{"award-number":["52572370"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Accident Analysis & Prevention"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.aap.2026.108791","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T14:13:49Z","timestamp":1791209629000},"page":"108791","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Structure\u2013behavior integrated risk prediction of vehicle groups using Graph Neural Networks"],"prefix":"10.1016","volume":"238","author":[{"given":"Jing","family":"Gan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dapeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Ran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.aap.2026.108791_b1","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.trc.2019.07.015","article-title":"A hazard-based duration model to quantify the impact of connected driving environment on safety during mandatory lane-changing","volume":"106","author":"Ali","year":"2019","journal-title":"Transp. Res. C"},{"key":"10.1016\/j.aap.2026.108791_b2","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1109\/TITS.2016.2598873","article-title":"Safety in vehicle platooning: A systematic literature review","volume":"18","author":"Axelsson","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2022.103021","article-title":"STAG: A novel interaction-aware path prediction method based on spatio-temporal attention graphs for connected automated vehicles","volume":"138","author":"Azadani","year":"2023","journal-title":"Ad Hoc Netw."},{"issue":"1","key":"10.1016\/j.aap.2026.108791_b4","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"10.1016\/j.aap.2026.108791_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2026.108400","article-title":"Exploring novel surrogate safety indicators measuring conflict riskiness and severity: A case study in Sacramento, United States","volume":"228","author":"Chen","year":"2026","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b6","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C., 2016. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"10.1016\/j.aap.2026.108791_b7","doi-asserted-by":"crossref","first-page":"1.1","DOI":"10.1016\/j.aap.2024.107564","article-title":"Advancing urban traffic accident forecasting through sparse spatio-temporal dynamic learning","volume":"200","author":"Cui","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2024.107486","article-title":"Safety-oriented automated vehicle longitudinal control considering both stability and damping behavior","volume":"198","author":"Dai","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b9","series-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"Defferrard","year":"2016"},{"key":"10.1016\/j.aap.2026.108791_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2023.106970","article-title":"Iterative learning control for lane-changing trajectories upstream off-ramp bottlenecks and safety evaluation","volume":"183","author":"Dong","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b11","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s42421-023-00067-w","article-title":"Appraising machine and deep learning techniques for traffic conflict prediction with class imbalance","volume":"5","author":"Formosa","year":"2023","journal-title":"Data Sci. Transp."},{"key":"10.1016\/j.aap.2026.108791_b12","first-page":"1","article-title":"A freeway traffic flow prediction model based on a generalized dynamic spatio-temporal graph convolutional network","author":"Gan","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b13","doi-asserted-by":"crossref","first-page":"21723","DOI":"10.1109\/TITS.2024.3452275","article-title":"A novel voronoi-based spatio-temporal graph convolutional network for traffic crash prediction considering geographical spatial distributions","volume":"25","author":"Gan","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b14","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.aap.2018.01.001","article-title":"Available sight distance on existing highways: Meeting stopping sight distance requirements of an aging population","volume":"112","author":"Gargoum","year":"2018","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b15","doi-asserted-by":"crossref","DOI":"10.1155\/atr\/3748345","article-title":"Traffic incident duration prediction: A systematic review of techniques","volume":"2024","author":"Grigorev","year":"2024","journal-title":"J. Adv. Transp."},{"key":"10.1016\/j.aap.2026.108791_b16","first-page":"1","article-title":"Safety evaluation of unsignalized intersection with heterogeneous traffic using post encroachment time and conflicting vehicle speed","volume":"88","author":"Hasain","year":"2022","journal-title":"Eur. Transp.\/Trasp. Eur."},{"key":"10.1016\/j.aap.2026.108791_b17","article-title":"Modeling conflict risk with real-time traffic data for road safety assessment: A copula-based joint approach","volume":"4","author":"Hu","year":"2022","journal-title":"Transp. Saf. Environ."},{"key":"10.1016\/j.aap.2026.108791_b18","article-title":"Traffic conflict prediction using connected vehicle data","volume":"39","author":"Islam","year":"2023","journal-title":"Anal. Methods Accid. Res."},{"key":"10.1016\/j.aap.2026.108791_b19","article-title":"Sensitivity analyses of stopping distance for connected vehicles at active highway-rail grade crossings","author":"Jones","year":"2017","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b20","first-page":"97","article-title":"Traffic violation modeling using K-means clustering method: A case study in Bandung, Indonesia","volume":"1","author":"Junaidi","year":"2024","journal-title":"Integr.: J. Integr. Math. Comput. Sci."},{"key":"10.1016\/j.aap.2026.108791_b21","article-title":"Dynamic and interpretable hazard-based models of traffic incident durations","volume":"2","author":"Kalair","year":"2021","journal-title":"Front. Futur. Transp."},{"key":"10.1016\/j.aap.2026.108791_b22","article-title":"Framework to identify vehicle platoons under heterogeneous traffic conditions on urban roads","volume":"16","author":"Kasi","year":"2024","journal-title":"Sustain. (Switzerland)"},{"key":"10.1016\/j.aap.2026.108791_b23","doi-asserted-by":"crossref","first-page":"3196","DOI":"10.1109\/TITS.2017.2769158","article-title":"A simulation study of predicting real-time conflict-prone traffic conditions","volume":"19","author":"Katrakazas","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b24","series-title":"Advances in Neural Information Processing Systems","first-page":"3149","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"Vol. 30","author":"Ke","year":"2017"},{"key":"10.1016\/j.aap.2026.108791_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.physa.2024.129656","article-title":"Vehicle group identification and evolutionary analysis using vehicle trajectory data","volume":"639","author":"Lei","year":"2024","journal-title":"Phys. A"},{"key":"10.1016\/j.aap.2026.108791_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2019.105371","article-title":"Real-time crash risk prediction on arterials based on LSTM-CNN","volume":"135","author":"Li","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b27","doi-asserted-by":"crossref","first-page":"3330","DOI":"10.1109\/JIOT.2024.3479221","article-title":"Vehicular speed prediction method for highway scenarios based on spatio-temporal graph convolutional networks and potential field theory","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.aap.2026.108791_b28","article-title":"Gauging road safety advances using a hybrid EWM\u2013PROMETHEE II\u2013dbscan model with machine learning","volume":"12","author":"Li","year":"2024","journal-title":"Front. Public Health"},{"key":"10.1016\/j.aap.2026.108791_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2023.107286","article-title":"An integrated approach of machine learning and Bayesian spatial Poisson model for large-scale real-time traffic conflict prediction","volume":"192","author":"Li","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b30","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1007\/s12205-021-1585-5","article-title":"A dynamic control method for cavs platoon based on the MPC framework and safety potential field model","volume":"25","author":"Li","year":"2021","journal-title":"KSCE J. Civ. Eng."},{"key":"10.1016\/j.aap.2026.108791_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2020.105805","article-title":"Risk perception and the warning strategy based on safety potential field theory","volume":"148","author":"Li","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.physa.2020.125039","article-title":"A novel lane-changing model of connected and automated vehicles: Using the safety potential field theory","volume":"559","author":"Li","year":"2020","journal-title":"Phys. A"},{"key":"10.1016\/j.aap.2026.108791_b33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.apm.2023.04.010","article-title":"Longitudinal car-following control strategy integrating predictive collision risk","volume":"121","author":"Li","year":"2023","journal-title":"Appl. Math. Model."},{"key":"10.1016\/j.aap.2026.108791_b34","doi-asserted-by":"crossref","first-page":"1755","DOI":"10.1109\/TITS.2020.3026025","article-title":"GraphSAGE-based traffic speed forecasting for segment network with sparse data","volume":"23","author":"Liu","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b35","doi-asserted-by":"crossref","first-page":"2920","DOI":"10.1109\/TITS.2022.3224592","article-title":"Safety-critical and flexible cooperative on-ramp merging control of connected and automated vehicles in mixed traffic","volume":"24","author":"Liu","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b36","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1016\/j.ssci.2012.05.007","article-title":"Quantitative indicator of homeostatic risk perception in car following","volume":"50","author":"Lu","year":"2012","journal-title":"Saf. Sci."},{"key":"10.1016\/j.aap.2026.108791_b37","doi-asserted-by":"crossref","DOI":"10.1155\/2013\/408756","article-title":"A car-following model based on quantified homeostatic risk perception","volume":"2013","author":"Lu","year":"2013","journal-title":"Math. Probl. Eng."},{"key":"10.1016\/j.aap.2026.108791_b38","series-title":"2015 International Conference on Transportation Information and Safety","first-page":"107","article-title":"The traffic accident hotspot prediction: Based on the logistic regression method","author":"Lu","year":"2015"},{"key":"10.1016\/j.aap.2026.108791_b39","doi-asserted-by":"crossref","first-page":"8452","DOI":"10.1109\/TITS.2022.3173944","article-title":"Vehicle trajectory prediction in connected environments via heterogeneous context-aware graph convolutional networks","volume":"24","author":"Lu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b40","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1177\/03611981221092383","article-title":"Multi-vehicle interactive lane-changing velocity change model based on potential energy field","volume":"2676","author":"Ma","year":"2022","journal-title":"Transp. Res. Rec."},{"key":"10.1016\/j.aap.2026.108791_b41","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1177\/03611981211070549","article-title":"MAGIC dataset: Multiple conditions unmanned aerial vehicle group-based high-fidelity comprehensive vehicle trajectory dataset","volume":"2676","author":"Ma","year":"2022","journal-title":"Transp. Res. Rec."},{"key":"10.1016\/j.aap.2026.108791_b42","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.iatssr.2017.02.001","article-title":"Application of proximal surrogate indicators for safety evaluation: A review of recent developments and research needs","volume":"41","author":"Mahmud","year":"2017","journal-title":"IATSS Res."},{"key":"10.1016\/j.aap.2026.108791_b43","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1016\/j.aap.2011.01.011","article-title":"Evaluation of rear-end crash risk at work zone using work zone traffic data","volume":"43","author":"Meng","year":"2011","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b44","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/S0001-4575(00)00019-1","article-title":"Extended time-to-collision measures for road traffic safety assessment","volume":"33","author":"Minderhoud","year":"2001","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b45","doi-asserted-by":"crossref","first-page":"9554","DOI":"10.1109\/TITS.2022.3146300","article-title":"Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network","volume":"23","author":"Mo","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b46","first-page":"51","article-title":"Calibration and validation of a new time-based surrogate safety measure using fuzzy inference system","volume":"3","author":"Nadimi","year":"2016","journal-title":"J. Traffic Transp. Eng. (Engl. Ed.)"},{"key":"10.1016\/j.aap.2026.108791_b47","series-title":"Trust-MARL: Trust-based multi-agent reinforcement learning framework for cooperative on-ramp merging control in heterogeneous traffic flow","author":"Pan","year":"2025"},{"key":"10.1016\/j.aap.2026.108791_b48","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.ins.2020.01.043","article-title":"Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting","volume":"521","author":"Peng","year":"2020","journal-title":"Inf. Sci. (N Y)"},{"key":"10.1016\/j.aap.2026.108791_b49","series-title":"Advances in Neural Information Processing Systems","first-page":"6639","article-title":"Catboost: Unbiased boosting with categorical features","volume":"Vol. 31","author":"Prokhorenkova","year":"2018"},{"key":"10.1016\/j.aap.2026.108791_b50","doi-asserted-by":"crossref","first-page":"8212","DOI":"10.1109\/TVT.2022.3175746","article-title":"A nonlinear car-following controller design inspired by human-driving behaviors to increase comfort and enhance safety","volume":"71","author":"Qin","year":"2022","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.aap.2026.108791_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2025.108312","article-title":"Collision risk identification and prediction considering heterogeneous braking patterns using large-scale pre-collision trajectories","volume":"225","author":"Ren","year":"2026","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2023.107424","article-title":"Network-wide safety impacts of dedicated lanes for connected and autonomous vehicles","volume":"195","author":"Sha","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b53","first-page":"181","article-title":"Road accidents prediction with multilayer perceptron MLP modelling case study: Roads of Qazvin, Zanjan and Hamadan","volume":"2","author":"Shamsashtiany","year":"2018","journal-title":"J. Civ. Eng. Mater. Appl."},{"key":"10.1016\/j.aap.2026.108791_b54","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2023.107221","article-title":"Adaptive forward collision warning system for hazmat truck drivers: Considering differential driving behavior and risk levels","volume":"191","author":"Shao","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2026.108565","article-title":"From prediction to prevention: Safety modeling of driver takeover time with mental workload, risk perception, and driving style in ramp scenarios","volume":"233","author":"Shao","year":"2026","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b56","series-title":"2025 3rd International Conference on Smart Systems for Applications in Electrical Sciences","first-page":"1","article-title":"An intelligent traffic conflict prediction using deep learning with long-term evolution access data","author":"Somnathe","year":"2025"},{"key":"10.1016\/j.aap.2026.108791_b57","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2025.107993","article-title":"Development of a framework for risky driving scenario identification, individual risk assessment, and group risk differences estimation using naturalistic driving data from the i-DREAMS project","volume":"215","author":"Song","year":"2025","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b58","doi-asserted-by":"crossref","DOI":"10.1109\/OJITS.2025.3574866","article-title":"Multimodal learning for traffic risk prediction: Combining aerial imagery with contextual data","author":"Tian","year":"2025","journal-title":"IEEE Open J. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b59","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/S0001-4575(02)00022-2","article-title":"A comparison of headway and time to collision as safety indicators","volume":"35","author":"Vogel","year":"2003","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b60","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2024.3472754","article-title":"DualRisk: A two-branch model for sparse traffic accident risk forecasting","author":"Wang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2021.106157","article-title":"A review of surrogate safety measures and their applications in connected and automated vehicles safety modeling","volume":"157","author":"Wang","year":"2021","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b62","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/TIV.2023.3321891","article-title":"A review of vehicle group intelligence in a connected environment","volume":"9","author":"Wu","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.aap.2026.108791_b63","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.aap.2026.108791_b64","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2026.108549","article-title":"Quantifying the safety effects of left-turn signal control mode: A heterogeneous causal inference framework","volume":"233","author":"Xu","year":"2026","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b65","doi-asserted-by":"crossref","first-page":"6125","DOI":"10.1109\/TVT.2019.2910987","article-title":"A grouping-based cooperative driving strategy for CAVs merging problems","volume":"68","author":"Xu","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.aap.2026.108791_b66","article-title":"Multi-view graph convolution network reinforcement learning for CAVs cooperative control in highway mixed traffic","author":"Xu","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.aap.2026.108791_b67","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2026.108543","article-title":"An exploration of active safety technologies for commercial vehicles: Research on on-road driving risk identification based on alarm and other multi-source data","volume":"232","author":"Xu","year":"2026","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b68","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2024.107529","article-title":"A two-dimensional surrogate safety measure based on fuzzy logic model","volume":"199","author":"Xu","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b69","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2022.103989","article-title":"Analysis of the impact of maximum platoon size of CAVs on mixed traffic flow : An analytical and simulation method","volume":"147","author":"Yao","year":"2023","journal-title":"Transp. Res. C"},{"key":"10.1016\/j.aap.2026.108791_b70","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neucom.2020.09.043","article-title":"Deep spatio-temporal graph convolutional network for traffic accident prediction","volume":"423","author":"Yu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.aap.2026.108791_b71","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1080\/15389588.2024.2390086","article-title":"A study on lane-changing risk evolution of vehicle group based on potential field model in the freeway tunnel approach section","volume":"26","author":"Zhang","year":"2025","journal-title":"Traffic Inj. Prev."},{"key":"10.1016\/j.aap.2026.108791_b72","article-title":"Coordlight: Learning decentralized coordination for network-wide traffic signal control","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2026.108791_b73","doi-asserted-by":"crossref","first-page":"3605","DOI":"10.1109\/TIV.2023.3268051","article-title":"Multi-modal fusion technology based on vehicle information: A survey","volume":"8","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.aap.2026.108791_b74","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TVT.2020.3046165","article-title":"Vehicle platooning with non-ideal communication networks","volume":"70","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.aap.2026.108791_b75","first-page":"1","article-title":"A novel intelligent vehicle risk assessment method combined with multi-sensor fusion in dense traffic environment","volume":"1","author":"Zheng","year":"2018","journal-title":"J. Intell. Connect. Veh."},{"key":"10.1016\/j.aap.2026.108791_b76","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2021.106546","article-title":"Multi-vehicle interaction safety of connected automated vehicles in merging area: A real-time risk assessment approach","volume":"166","author":"Zhu","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2026.108791_b77","doi-asserted-by":"crossref","first-page":"7807","DOI":"10.1109\/TITS.2025.3556543","article-title":"Vehicle-group-based crash risk prediction and interpretation on highways","volume":"26","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Accident Analysis & Prevention"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0001457526004008?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0001457526004008?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T17:00:58Z","timestamp":1793466058000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0001457526004008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":77,"alternative-id":["S0001457526004008"],"URL":"https:\/\/doi.org\/10.1016\/j.aap.2026.108791","relation":{},"ISSN":["0001-4575"],"issn-type":[{"value":"0001-4575","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Structure\u2013behavior integrated risk prediction of vehicle groups using Graph Neural Networks","name":"articletitle","label":"Article Title"},{"value":"Accident Analysis & Prevention","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aap.2026.108791","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108791"}}