{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T06:56:25Z","timestamp":1768287385569,"version":"3.49.0"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484443"],"award-info":[{"award-number":["20230484443"]}],"id":[{"id":"10.13039\/501100005090","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":[[2026,2]]},"DOI":"10.1016\/j.aap.2025.108306","type":"journal-article","created":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T21:30:47Z","timestamp":1763328647000},"page":"108306","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Development of a bus real-time crash risk prediction framework by using a self-attention-based bidirectional long and short-term memory network with anomaly detection learning and mixed sequence features"],"prefix":"10.1016","volume":"225","author":[{"given":"Ning","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiping","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aoran","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.aap.2025.108306_b0005","article-title":"A priority based multi-level heterogeneity modelling framework for vulnerable road users","volume":"1\u201334","author":"Abdulrazaq","year":"2025","journal-title":"Transp. A Transp. Sci."},{"key":"10.1016\/j.aap.2025.108306_b0010","doi-asserted-by":"crossref","unstructured":"Abdulrazaq, M.A., Fan, W.D., 2024. Temporal dynamics of pedestrian injury severity: A seasonally constrained random parameters approach. Int. J. Transp. Sci. Technol. doi:https:\/\/doi.org\/10.1016\/j.ijtst.2024.11.009.","DOI":"10.1016\/j.ijtst.2024.11.009"},{"key":"10.1016\/j.aap.2025.108306_b0015","unstructured":"Administrative Measures for Dynamic Supervision of Road Transport Vehicles, 2014. . Ministry of Transport of the People's Republic of China."},{"key":"10.1016\/j.aap.2025.108306_b0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2023.107015","article-title":"Modelling braking behaviour of distracted young drivers in car-following interactions: a grouped random parameters duration model with heterogeneity-in-means","volume":"185","author":"Ali","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0025","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.trc.2019.01.016","article-title":"A hybrid approach for identifying factors affecting driver reaction time using naturalistic driving data","volume":"100 January","author":"Arbabzadeh","year":"2019","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"10.1016\/j.aap.2025.108306_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2022.106933","article-title":"Identification of high-risk roadway segments for wrong-way driving crash using rare event modeling and data augmentation techniques","volume":"181","author":"Ashraf","year":"2023","journal-title":"Accid. Anal. Prev."},{"issue":"4","key":"10.1016\/j.aap.2025.108306_b0035","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1016\/j.aap.2011.02.009","article-title":"Jerky driving\u2014an indicator of accident proneness?","volume":"43","author":"Bagdadi","year":"2011","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0040","doi-asserted-by":"crossref","unstructured":"Bai, C., Yang, C., Rong, D., Guo, W., Gao, X., Yao, W., Jin, S., 2025. Multi-source temporal attention fusion network (MTAFN) for driving risk assessment based on naturalistic driving data. Expert Syst. Appl. 279 February , 127502. doi:10.1016\/j.eswa.2025.127502.","DOI":"10.1016\/j.eswa.2025.127502"},{"key":"10.1016\/j.aap.2025.108306_b0045","doi-asserted-by":"crossref","unstructured":"Barabino, B., Bonera, M., Maternini, G., Porcu, F., Ventura, R., 2024. Refining a crash risk framework for urban bus safety assessment: Evidence from Sardinia (Italy). Reliab. Eng. Syst. Saf. 245 September 2023 . doi:10.1016\/j.ress.2024.110003.","DOI":"10.1016\/j.ress.2024.110003"},{"issue":"7","key":"10.1016\/j.aap.2025.108306_b0050","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"Bradley","year":"1997","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.aap.2025.108306_b0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2020.102697","article-title":"Real-time crash prediction on expressways using deep generative models","volume":"117","author":"Cai","year":"2020","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"10.1016\/j.aap.2025.108306_b0060","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.aap.2025.108306_b0065","doi-asserted-by":"crossref","unstructured":"Chen, K., Xu, C., Liu, P., Li, Z., Wang, Y., 2024. Evaluating the performance of traffic conflict measures in real-time crash risk prediction using pre-crash vehicle trajectories. Accid. Anal. Prev. 203 December 2023 , 107640. doi:10.1016\/j.aap.2024.107640.","DOI":"10.1016\/j.aap.2024.107640"},{"key":"10.1016\/j.aap.2025.108306_b0070","doi-asserted-by":"crossref","unstructured":"Chen, T., Lu, Y., Fu, X., Sze, N.N., Ding, H., 2022. A resampling approach to disaggregate analysis of bus-involved crashes using panel data with excessive zeros. Accid. Anal. Prev. 164 October 2021 , 106496. doi:10.1016\/j.aap.2021.106496.","DOI":"10.1016\/j.aap.2021.106496"},{"key":"10.1016\/j.aap.2025.108306_b0075","doi-asserted-by":"crossref","unstructured":"Elamrani Abou Elassad, Z., Mousannif, H., Al Moatassime, H., 2020. A real-time crash prediction fusion framework: An imbalance-aware strategy for collision avoidance systems. Transp. Res. Part C Emerg. Technol. 118 July , 102708. doi:10.1016\/j.trc.2020.102708.","DOI":"10.1016\/j.trc.2020.102708"},{"key":"10.1016\/j.aap.2025.108306_b0080","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.aap.2017.04.012","article-title":"Can vehicle longitudinal jerk be used to identify aggressive drivers? An examination using naturalistic driving data","volume":"104","author":"Feng","year":"2017","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0085","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.aap.2019.03.002","article-title":"A comparative analysis of black spot identification methods and road accident segmentation methods","volume":"128","author":"Ghadi","year":"2019","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2023.104089","article-title":"Autonomous anomaly detection on traffic flow time series with reinforcement learning","volume":"150","author":"He","year":"2023","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"10.1016\/j.aap.2025.108306_b0095","series-title":"Public Transport inn developing Countries","author":"Iles","year":"2005"},{"key":"10.1016\/j.aap.2025.108306_b0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2020.105508","article-title":"Influence of traffic congestion on driver behavior in post-congestion driving","volume":"141","author":"Li","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0105","article-title":"The application of novel connected vehicles emulated data on real-time crash potential prediction for arterials","volume":"144 March","author":"Li","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0110","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.2025.108306_b0115","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, T., Yang, J., Chen, H., 2025. A hybrid exploratory approach for understanding risk driving behaviors of bus drivers: A case study of Nanjing, China. Transp. Res. Part F Traffic Psychol. Behav. 109 December 2024 , 520\u2013539. doi:10.1016\/j.trf.2024.12.030.","DOI":"10.1016\/j.trf.2024.12.030"},{"key":"10.1016\/j.aap.2025.108306_b0120","series-title":"A unified approach to interpreting model predictions","first-page":"30","author":"Lundberg","year":"2017"},{"key":"10.1016\/j.aap.2025.108306_b0125","article-title":"A dynamic method to predict driving risk on sharp curves using multi-source data","volume":"191 July","author":"Ma","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0130","doi-asserted-by":"crossref","unstructured":"Ma, Y., Xie, Z., Chen, S., Qiao, F., Li, Z., 2023b. Real-time detection of abnormal driving behavior based on long short-term memory network and regression residuals. Transp. Res. Part C Emerg. Technol. 146 February 2022 , 103983. doi:10.1016\/j.trc.2022.103983.","DOI":"10.1016\/j.trc.2022.103983"},{"key":"10.1016\/j.aap.2025.108306_b0135","article-title":"Prediction and analysis of likelihood of freeway crash occurrence considering risky driving behavior","volume":"192 April","author":"Ma","year":"2023","journal-title":"Accid. Anal. Prev."},{"issue":"12","key":"10.1016\/j.aap.2025.108306_b0140","doi-asserted-by":"crossref","first-page":"23002","DOI":"10.1109\/TITS.2022.3207798","article-title":"Wasserstein generative adversarial network to address the imbalanced data problem in real-time crash risk prediction","volume":"23","author":"Man","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2025.108306_b0145","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.aap.2016.07.007","article-title":"A farewell to brake reaction times? Kinematics-dependent brake response in naturalistic rear-end emergencies","volume":"95","author":"Markkula","year":"2016","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2020.105703","article-title":"Automatic incident detection on freeways based on Bluetooth traffic monitoring","volume":"146","author":"Mercader","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0155","series-title":"When does label smoothing help?","first-page":"32","author":"M\u00fcller","year":"2019"},{"key":"10.1016\/j.aap.2025.108306_b0160","doi-asserted-by":"crossref","unstructured":"Nan, S., Tu, R., Li, T., Sun, J., Chen, H., 2022. From driving behavior to energy consumption: A novel method to predict the energy consumption of electric bus. Energy 261 September 2021 . doi:10.1016\/j.energy.2022.125188.","DOI":"10.1016\/j.energy.2022.125188"},{"key":"10.1016\/j.aap.2025.108306_b0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2021.106107","article-title":"Using long short term memory and convolutional neural networks for driver drowsiness detection","volume":"156","author":"Quddus","year":"2021","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0170","volume":"arXiv2106.07998","author":"Romijnders","year":"2021","journal-title":"Revisiting the Calibration of Modern Neural Networks. Arxiv Prepr."},{"key":"10.1016\/j.aap.2025.108306_b0175","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.aap.2015.03.013","article-title":"Impact of real-time traffic characteristics on freeway crash occurrence: Systematic review and meta-analysis","volume":"79","author":"Roshandel","year":"2015","journal-title":"Accid. Anal. Prev."},{"issue":"3","key":"10.1016\/j.aap.2025.108306_b0180","doi-asserted-by":"crossref","first-page":"1650","DOI":"10.1109\/TITS.2020.2975043","article-title":"End-to-end autonomous driving risk analysis: a behavioural anomaly detection approach","volume":"22","author":"Ryan","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aap.2025.108306_b0185","article-title":"An integrated methodology for real-time driving risk status prediction using naturalistic driving data","volume":"156 April","author":"Shangguan","year":"2021","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0190","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.aap.2019.05.005","article-title":"A feature learning approach based on XGBoost for driving assessment and risk prediction","volume":"129 May","author":"Shi","year":"2019","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0195","doi-asserted-by":"crossref","unstructured":"Stipancic, J., Miranda-Moreno, L., Saunier, N., 2018. Vehicle manoeuvers as surrogate safety measures: Extracting data from the gps-enabled smartphones of regular drivers. Accid. Anal. Prev. 115 February 2017 , 160\u2013169. doi:10.1016\/j.aap.2018.03.005.","DOI":"10.1016\/j.aap.2018.03.005"},{"key":"10.1016\/j.aap.2025.108306_b0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2023.107420","article-title":"An interpretable clustering approach to safety climate analysis: Examining driver group distinctions","volume":"196","author":"Sun","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0205","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.trf.2005.10.002","article-title":"Bus driver well-being review: 50 years of research","volume":"9 2","author":"Tse","year":"2006","journal-title":"Transp. Res. Part F Traffic Psychol. Behav."},{"key":"10.1016\/j.aap.2025.108306_b0210","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1016\/j.trc.2016.08.014","article-title":"Drivers\u2019 rear end collision avoidance behaviors under different levels of situational urgency","volume":"71","author":"Wang","year":"2016","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"10.1016\/j.aap.2025.108306_b0215","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, X., Wang, T., Quddus, M., 2025. Freeway real-time crash prediction using floating car data. Transp. Res. Part C Emerg. Technol. 171 November 2024 , 105009. doi:10.1016\/j.trc.2025.105009.","DOI":"10.1016\/j.trc.2025.105009"},{"key":"10.1016\/j.aap.2025.108306_b0220","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, C., Liu, P., Li, Z., Chen, K., 2024. Assessing the predictability of surrogate safety measures as crash precursors based on vehicle trajectory data prior to crashes. Accid. Anal. Prev. 201 December 2023 , 107573. doi:10.1016\/j.aap.2024.107573.","DOI":"10.1016\/j.aap.2024.107573"},{"key":"10.1016\/j.aap.2025.108306_b0225","article-title":"Real-time driving risk prediction using a self-attention-based bidirectional long short-term memory network based on multi-source data","volume":"204 May","author":"Xie","year":"2024","journal-title":"Accid. Anal. Prev."},{"issue":"1","key":"10.1016\/j.aap.2025.108306_b0230","article-title":"Rapid Driving style Recognition in Car\u2010Following using Machine Learning and Vehicle Trajectory Data","volume":"2019","author":"Xue","year":"2019","journal-title":"J. Adv. Transp."},{"key":"10.1016\/j.aap.2025.108306_b0235","article-title":"Driving risk identification of urban arterial and collector roads based on multi-scale data","volume":"206 March","author":"Yan","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0240","article-title":"Real-time crash prediction on express managed lanes of Interstate highway with anomaly detection learning","volume":"201 April","author":"Yang","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.aap.2025.108306_b0245","article-title":"Trajectory data based freeway high-risk events prediction and its influencing factors analyses","volume":"154 January","author":"Yu","year":"2021","journal-title":"Accid. Anal. Prev."},{"issue":"4","key":"10.1016\/j.aap.2025.108306_b0250","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1177\/0361198119840611","article-title":"Real-time crash risk prediction using long short-term memory recurrent neural network","volume":"2673","author":"Yuan","year":"2019","journal-title":"Transp. Res. Rec."},{"key":"10.1016\/j.aap.2025.108306_b0255","doi-asserted-by":"crossref","unstructured":"Zhang, H., Shen, Y., Bao, Q., Qu, Q., Zhang, R., Yang, M., Han, T., 2024. Rethinking real-time risk prediction from multi-step time series forecasting on highway car-following scenarios. Accid. Anal. Prev. 207 August , 107748. doi:10.1016\/j.aap.2024.107748.","DOI":"10.1016\/j.aap.2024.107748"},{"key":"10.1016\/j.aap.2025.108306_b0260","doi-asserted-by":"crossref","unstructured":"Zhang, J., Mao, S., Zhang, S., Yin, J., Yang, L., Gao, Z., 2025. EF-former for short-term passenger flow prediction during large-scale events in urban rail transit systems. Inf. Fusion 117 October 2024 , 102916. doi:10.1016\/j.inffus.2024.102916.","DOI":"10.1016\/j.inffus.2024.102916"},{"key":"10.1016\/j.aap.2025.108306_b0265","article-title":"Real-time crash potential prediction on freeways using connected vehicle data","volume":"36","author":"Zhang","year":"2022","journal-title":"Anal. Methods Accid. Res"},{"key":"10.1016\/j.aap.2025.108306_b0270","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, H., Ren, G., 2024. Prediction of jaywalker-vehicle conflicts based on encoder-decoder framework utilizing multi-source data. Accid. Anal. Prev. 195 November 2023 , 107403. doi:10.1016\/j.aap.2023.107403.","DOI":"10.1016\/j.aap.2023.107403"},{"issue":"1","key":"10.1016\/j.aap.2025.108306_b0275","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/s10489-022-03501-8","article-title":"Unsupervised anomaly detection based method of risk evaluation for road traffic accident","volume":"53","author":"Zhao","year":"2023","journal-title":"Appl. Intell."},{"key":"10.1016\/j.aap.2025.108306_b0280","article-title":"A novel approach for real time crash prediction at signalized intersections","volume":"117 May","author":"Zheng","year":"2020","journal-title":"Transp. Res. Part C Emerg. Technol."}],"container-title":["Accident Analysis & Prevention"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S000145752500394X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S000145752500394X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T17:13:42Z","timestamp":1766078022000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S000145752500394X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":56,"alternative-id":["S000145752500394X"],"URL":"https:\/\/doi.org\/10.1016\/j.aap.2025.108306","relation":{},"ISSN":["0001-4575"],"issn-type":[{"value":"0001-4575","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Development of a bus real-time crash risk prediction framework by using a self-attention-based bidirectional long and short-term memory network with anomaly detection learning and mixed sequence features","name":"articletitle","label":"Article Title"},{"value":"Accident Analysis & Prevention","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aap.2025.108306","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108306"}}