Let's Connect
Follow Us
Watch Us
(+385) 1 2380 262
journal.prometfpz.unizg.hr
Promet - Traffic&Transportation journal

Accelerating Discoveries in Traffic Science

Accelerating Discoveries in Traffic Science

Login Submit

PDF
PUBLISHED
13.03.2025
DOI
https://doi.org/10.7307/ptt.v37i2.763
ISSUE
2025 (Vol 37), Issue 2
LICENSE
Copyright (c) 2025 Meiling HE, Guangrong MENG, Xiaohui WU, Xun HAN, Jiangyang FAN
Creative Commons 4.0 logo
This work is licensed under a
Creative Commons Attribution-NonCommercial-
NoDerivatives 4.0 International License.

Road Traffic Accident Prediction Based on Multi-Source Data – A Systematic Review

Authors:Meiling HE, Guangrong MENG, Xiaohui WU, Xun HAN, Jiangyang FAN

Abstract

With the acceleration of urbanisation and the rapid increase in road traffic volume, the scientific prediction of traffic accidents has become crucial for improving road safety and enhancing traffic efficiency. However, traffic accident prediction is a complex and multifaceted problem that requires the comprehensive consideration of multiple factors, including people, vehicles, roads and the environment. This paper provides a detailed analysis of traffic accident prediction based on multi-source data. By thoroughly considering data sources, data processing and prediction methods, this paper introduces the various aspects of traffic accident prediction from different perspectives. It helps readers understand the characteristics of different data and methods, the process of accident prediction and the key technologies involved. At the end of the paper, the main challenges and future directions in road crash prediction research are summarised. For example, the lack of efficient data sharing between different departments and fields poses significant challenges to the integration of multi-source data. In the future, combining deep learning models with time-sensitive data, such as social media and vehicle network data, could effectively improve the accuracy of real-time accident prediction.

Keywords:multi-source data, road traffic accident, data processing, statistical learning, machine learning, deep learning

References

  1. [1] WHO.Who kicks off a decade of action for road safety.2021.https://www.who.int/news/item/28-10-2021-who-kicks-off-a-decade-of-action-for-road-safety
  2. [2] WHO.Global status report on road safety 2023.2023.https://www.who.int/publications/i/item/9789240086517
  3. [3] Zhang Z, et al. Traffic accident prediction based on lstm-gbrt model. J. Control Sci. Eng. 2020;2020:4206919. DOI:10.1155/2020/4206919.
  4. [4] Trirat P, Yoon S, Lee J. Mg-tar: Multi-view graph convolutional networks for traffic accident risk prediction. IEEE Trans. Intell. Transp. Syst. 2023;24(4):3779-3794. DOI:10.1109/TITS.2023.3237072.
  5. [5] Xiong X, et al. Multi-level prediction framework of driving risk based on the matter-element extension model. Transp. Res. Rec. 2024;2678(8):950-965. DOI:10.1177/03611981231223750.
  6. [6] Liu X, et al. Attention based spatio-temporal graph convolutional network with focal loss for crash risk evaluation on urban road traffic network based on multi-source risks. Accid. Anal. Prev. 2023;192:107262. DOI:10.1016/j.aap.2023.107262.
  7. [7] Pilutti T, Ulsoy A G. Fuzzy-logic-based virtual rumble strip for road departure warning systems. IEEE Trans. Intell. Transp. Syst. 2003;4(1):1-12. DOI:10.1109/TITS.2003.811810.
  8. [8] Tan D, Chen W, Wang H. On the use of monte-carlo simulation and deep fourier neural network in lane departure warning. IEEE Intell. Transp. Syst. Mag. 2018;10(1):168-168. DOI:10.1109/MITS.2017.2776726.
  9. [9] Qu X B, et al. Safety evaluation for expressways: A comparative study for macroscopic and microscopic indicators. Traffic Inj. Prev. 2014;15(1):89-93. DOI:10.1080/15389588.2013.782400.
  10. [10] Rajaram V, Subramanian SC. Heavy vehicle collision avoidance control in heterogeneous traffic using varying time headway. Mechatronics. 2018;50:328-340. DOI:10.1016/j.mechatronics.2017.11.010.
  11. [11] Ward JR, et al. Extending time to collision for probabilistic reasoning in general traffic scenarios. Transp. Res. Part C Emerg. Technol. 2015;51:66-82. DOI:10.1016/j.trc.2014.11.002.
  12. [12] Wang C, Quddus MA, Ison SG. The effect of traffic and road characteristics on road safety: A review and future research direction. Saf. Sci. 2013;57:264-275. DOI:10.1016/j.ssci.2013.02.012.
  13. [13] Sohail A, et al. Data-driven approaches for road safety: A comprehensive systematic literature review. Saf. Sci. 2023;158:105949. DOI:10.1016/j.ssci.2022.105949.
  14. [14] Lukusa MT, Hing Phoa FK. A horvitz-type estimation on incomplete traffic accident data analyzed via a zero-inflated poisson model. Accid. Anal. Prev. 2020;134:105235. DOI:10.1016/j.aap.2019.07.011.
  15. [15] Luo Q, Liu C. Exploration of road closure time characteristics of tunnel traffic accidents: A case study in pennsylvania, usa. Tunn. Undergr. Space Technol. 2023;132:104894. DOI:10.1016/j.tust.2022.104894.
  16. [16] D'Andrea E, et al. Real-time detection of traffic from twitter stream analysis. IEEE Trans. Intell. Transp. Syst. 2015;16(4):2269-2283. DOI:10.1109/TITS.2015.2404431.
  17. [17] Gu Y, Qian ZS, Chen F. From twitter to detector: Real-time traffic incident detection using social media data. Transp. Res. Pt. C-Emerg. Technol. 2016;67:321-342. DOI:10.1016/j.trc.2016.02.011.
  18. [18] Zheng M, et al. Network space analysis–based identification of road traffic accident hotspots: A case study. Int. J. Crashworthiness. 2023;28(1):108-115. DOI:10.1080/13588265.2022.2109446.
  19. [19] Jiang F, Yuen KKR, Lee EWM. A long short-term memory-based framework for crash detection on freeways with traffic data of different temporal resolutions. Accid. Anal. Prev. 2020;141:105520. DOI:10.1016/j.aap.2020.105520.
  20. [20] Wen X, et al. Applications of machine learning methods in traffic crash severity modelling: Current status and future directions. Transp. Rev. 2021;41(6):855-879. DOI:10.1080/01441647.2021.1954108.
  21. [21] Bahiru TK, Singh DK, Tessfaw EA. Comparative study on data mining classification algorithms for predicting road traffic accident severity. 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT). 2018. p. 1655-1660. DOI:10.1109/ICICCT.2018.8473265.
  22. [22] Yuan J, Abdel-Aty M. Approach-level real-time crash risk analysis for signalized intersections. Accid. Anal. Prev. 2018;119:274-289. DOI:10.1016/j.aap.2018.07.031.
  23. [23] Zhang Z, et al. A deep learning approach for detecting traffic accidents from social media data. Transp. Res. Pt. C-Emerg. Technol. 2018;86:580-596. DOI:10.1016/j.trc.2017.11.027.
  24. [24] Bao J, Liu P, Ukkusuri SV. A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data. Accid. Anal. Prev. 2019;122:239-254. DOI:10.1016/j.aap.2018.10.015.
  25. [25] Goh K, et al. Factors affecting the probability of bus drivers being at-fault in bus-involved accidents. Accid. Anal. Prev. 2014;66:20-26. DOI:10.1016/j.aap.2013.12.022.
  26. [26] Young SD, Wang W, Chakravarthy B. Crowdsourced traffic data as an emerging tool to monitor car crashes. JAMA Surg. 2019;154(8):777-778. DOI:10.1001/jamasurg.2019.1167.
  27. [27] Chen J, Tao W. Traffic accident duration prediction using text mining and ensemble learning on expressways. Sci. Rep. 2022;12(1):21478. DOI:10.1038/s41598-022-25988-4.
  28. [28] Gutierrez-Osorio C, Pedraza C. Modern data sources and techniques for analysis and forecast of road accidents: a review. Journal of Traffic and Transportation Engineering (English Edition). 2020;7(4):432-446. DOI:10.1016/j.jtte.2020.05.002.
  29. [29] Deng M, et al. An analysis of physiological responses as indicators of driver takeover readiness in conditionally automated driving. Accid. Anal. Prev. 2024;195:107372. DOI:10.1016/j.aap.2023.107372.
  30. [30] Moriya K, Matsushima S, Yamanishi K. Traffic risk mining from heterogeneous road statistics. IEEE Trans. Intell. Transp. Syst. 2018;19(11):3662-3675. DOI:10.1109/TITS.2018.2856533.
  31. [31] Basso F, et al. A deep learning approach for real-time crash prediction using vehicle-by-vehicle data. Accid. Anal. Prev. 2021;162:106409. DOI:10.1016/j.aap.2021.106409.
  32. [32] Yang Z, et al. Driving risk assessment using cluster analysis based on naturalistic driving data. 2014 17th International IEEE Conference on Intelligent Transportation Systems (ITSC). 2014. p. 2584-2589. DOI:10.1109/ITSC.2014.6958104.
  33. [33] Cao Q, et al. Reallocation of heterogeneous sensors on road networks for traffic accident detection. IEEE Trans. Instrum. Meas. 2023;72:1-11. DOI:10.1109/TIM.2023.3291790.
  34. [34] Chang HL, et al. Tracking traffic congestion and accidents using social media data: A case study of Shanghai. Accid. Anal. Prev. 2022;169:106618. DOI:10.1016/j.aap.2022.106618.
  35. [35] Lu H, et al. Using adverse weather data in social media to assist with city-level traffic situation awareness and alerting. Appl. Sci. 2018;8(7):1193. DOI:10.3390/app8071193.
  36. [36] Sinnott RO, Yin S. Accident black spot identification and verification through social media. 2015 IEEE International Conference on Data Science and Data Intensive Systems (DSDIS). 2015. p. 17-24. DOI:10.1109/DSDIS.2015.34.
  37. [37] Dabiri S, Heaslip K. Developing a twitter-based traffic event detection model using deep learning architectures. Expert Syst. Appl. 2019;118:425-439. DOI:10.1016/j.eswa.2018.10.017.
  38. [38] Durduran SS. A decision making system to automatic recognize of traffic accidents on the basis of a gis platform. Expert Syst. Appl. 2010;37(12):7729-7736. DOI:10.1016/j.eswa.2010.04.068.
  39. [39] Shafabakhsh GA, Famili A, Bahadori MS. Gis-based spatial analysis of urban traffic accidents: Case study in Mashhad, Iran. J. Traffic Transp. Eng.-Engl. Ed. 2017;4(3):290-299. DOI:10.1016/j.jtte.2017.05.005.
  40. [40] Guo J, et al. Gps-based citywide traffic congestion forecasting using cnn-rnn and c3d hybrid model. Transportmetrica A. 2021;17(2):190-211. DOI:10.1080/23249935.2020.1745927.
  41. [41] Shahzad M. Review of road accident analysis using gis technique. Int. J. Inj. Control Saf. Promot. 2020;27(4):472-481. DOI:10.1080/17457300.2020.1811732.
  42. [42] Ding T Q, et al. Accident probability prediction and analysis of bus drivers based on occupational characteristics. Appl. Sci.-Basel. 2024;14(1):279. DOI:10.3390/app14010279.
  43. [43] Zhang ZB, et al. An assessment of the relationship between driving skills and driving behaviors among chinese bus drivers. Adv. Mech. Eng. 2019;11(1). DOI:10.1177/1687814018824916.
  44. [44] Nasri M, Aghabayk K. Assessing risk factors associated with urban transit bus involved accident severity: A case study of a middle east country. Int. J. Crashworthiness. 2021;26(4):413-423. DOI:10.1080/13588265.2020.1718465.
  45. [45] Luan S, et al. Effects of built environment on bicycle wrong way riding behavior: A data -driven approach. Accid. Anal. Prev. 2020;144:105613. DOI:10.1016/j.aap.2020.105613.
  46. [46] Liang XY, Meng XH, Zheng L. Investigating conflict behaviours and characteristics in shared space for pedestrians, conventional bicycles and e-bikes. Accid. Anal. Prev. 2021;158:106167. DOI:10.1016/j.aap.2021.106167.
  47. [47] Amin-Naseri M, et al. Evaluating the reliability, coverage, and added value of crowdsourced traffic incident reports from waze. Transp. Res. Rec. 2018;2672(43):34-43. DOI:10.1177/0361198118790619.
  48. [48] Li JB, et al. Feedback on a shared big dataset for intelligent tbm part i: Feature extraction and machine learning methods. Undergr. Space. 2023;11:1-25. DOI:10.1016/j.undsp.2023.01.001.
  49. [49] Tao W, et al. Feature optimization method for white feather broiler health monitoring technology. Eng. Appl. Artif. Intell. 2023;123:106372. DOI:10.1016/j.engappai.2023.106372.
  50. [50] Zhang ZS, et al. A study on the method for cleaning and repairing the probe vehicle data. IEEE Trans. Intell. Transp. Syst. 2013;14(1):419-427. DOI:10.1109/TITS.2012.2217378.
  51. [51] Yan M, Shen Y. Traffic accident severity prediction based on random forest. Sustainability. 2022;14(3):1729. DOI:10.3390/su14031729.
  52. [52] Madley-Dowd P, et al. The proportion of missing data should not be used to guide decisions on multiple imputation. J. Clin. Epidemiol. 2019;110:63-73. DOI:10.1016/j.jclinepi.2019.02.016.
  53. [53] Dal Bianco G, et al. A practical and effective sampling selection strategy for large scale deduplication. IEEE Trans. Knowl. Data Eng. 2015;27(9):2305-2319. DOI:10.1109/TKDE.2015.2416734.
  54. [54] Xie S. Feature extraction of auto insurance size of loss data using functional principal component analysis. Expert Syst. Appl. 2022;198:116780. DOI:10.1016/j.eswa.2022.116780.
  55. [55] Xu J. A weighted linear discriminant analysis framework for multi-label feature extraction. Neurocomputing. 2018;275:107-120. DOI:10.1016/j.neucom.2017.05.008.
  56. [56] Akaho S. Conditionally independent component analysis for supervised feature extraction. Neurocomputing. 2002;49(1):139-150. DOI:10.1016/S0925-2312(02)00518-0.
  57. [57] Fattahi M, Moattar MH, Forghani Y. Locally alignment based manifold learning for simultaneous feature selection and extraction in classification problems. Knowledge-Based Syst. 2023;259:110088. DOI:10.1016/j.knosys.2022.110088.
  58. [58] Sharma AK, et al. Hog transformation based feature extraction framework in modified resnet50 model for brain tumor detection. Biomed. Signal Process. Control. 2023;84:104737. DOI:10.1016/j.bspc.2023.104737.
  59. [59] Suarez-Alvarez MM, et al. Statistical approach to normalization of feature vectors and clustering of mixed datasets. Proc. R. Soc. A-Math. Phys. Eng. Sci. 2012;468(2145):2630-2651. DOI:10.1098/rspa.2011.0704.
  60. [60] Sengupta A, et al. A bayesian approach to quantifying uncertainties and improving generalizability in traffic prediction models. Transp. Res. Pt. C-Emerg. Technol. 2024;162:104585. DOI:10.1016/j.trc.2024.104585.
  61. [61] Munkhdalai L, et al. Mixture of activation functions with extended min-max normalization for forex market prediction. IEEE Access. 2019;7:183680-183691. DOI:10.1109/ACCESS.2019.2959789.
  62. [62] Jain S, Shukla S, Wadhvani R. Dynamic selection of normalization techniques using data complexity measures. Expert Syst. Appl. 2018;106:252-262. DOI:10.1016/j.eswa.2018.04.008.
  63. [63] AlMamlook RE, et al. Comparison of machine learning algorithms for predicting traffic accident severity. 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT). 2019. p. 272-276. DOI:10.1109/JEEIT.2019.8717393.
  64. [64] Parsa AB, et al. Real-time accident detection: coping with imbalanced data. Accid. Anal. Prev. 2019;129:202-210. DOI:10.1016/j.aap.2019.05.014.
  65. [65] Shangguan AQ, et al. Traffic accident severity prediction based on oversampling and cnn for imbalanced data. 2021 Proceedings of The 40th Chinese Control Conference(CCC). 2021. p. 7004-7008. DOI:10.23919/CCC52363.2021.9549759.
  66. [66] Wang C, et al. An analysis of fatal accident rates of passenger cars on urban roads considering imbalanced data samples. Journal of Transport Information and Safety. 2023;41(5):43-53. DOI:10.3963/j.jssn.1674-4861.2023.05.005.
  67. [67] Ferrer CA, Aragón E. Note on "a comprehensive analysis of synthetic minority oversampling technique (smote) for handling class imbalance". Inf. Sci. 2023;630:322-324. DOI:10.1016/j.ins.2022.10.005.
  68. [68] Shi X, et al. Solving the data imbalance problem of p300 detection via random under-sampling bagging svms. 2015 International Joint Conference on Neural Networks (IJCNN). 2015. p. 1-5. DOI:10.1109/IJCNN.2015.7280834.
  69. [69] Pereira RM, Costa YMG, Silla Jr. CN. Mltl: a multi-label approach for the tomek link undersampling algorithm. Neurocomputing. 2020;383:95-105. DOI:10.1016/j.neucom.2019.11.076.
  70. [70] Mujalli RO, López G, Garach L. Bayes classifiers for imbalanced traffic accidents datasets. Accid. Anal. Prev. 2016;88:37-51. DOI:10.1016/j.aap.2015.12.003.
  71. [71] Tahir M, et al. Real-time event-driven road traffic monitoring system using cctv video analytics. IEEE Access. 2023;11:139097-139111. DOI:10.1109/ACCESS.2023.3340144.
  72. [72] Zhao C, et al. Unsupervised anomaly detection based method of risk evaluation for road traffic accident. Appl. Intell. 2023;53(1):369-384. DOI:10.1007/s10489-022-03501-8.
  73. [73] Monisha M, et al. A new generalization of the zero-truncated negative binomial distribution by a lagrange expansion with associated regression model and applications. Int. J. Data Sci. Anal. 2023:1-5. DOI:10.1007/s41060-023-00449-x.
  74. [74] Ding Y, et al. Deep imbalanced regression using cost-sensitive learning and deep feature transfer for bearing remaining useful life estimation. Appl. Soft Comput. 2022;127:109271. DOI:10.1016/j.asoc.2022.109271.
  75. [75] Lv WF, Cui W, Huang J. Research on a datex iii based dynamic traffic information publish platform. 2008 2nd International Symposium on Intelligent Information Technology Application. 2008. p. 412-416. DOI:10.1109/IITA.2008.81.
  76. [76] Jakovljevic D, Balen J, Vidovic K. Integration of traffic and travel data exchange in command and control platform. 2016 1st International Conference on Smart Systems and Technologies (SST). 2016. p. 281-286. DOI:10.1109/SST.2016.7765674.
  77. [77] Anonymous. Traffic management data dictionary (tmdd) and message set for external traffic management center communications (ms/etmcc) guide. ITE J. 2001;71(4):24-24.
  78. [78] Mohammed SJ, Hasson ST, IEEE. Modeling and simulation of data dissemination in vanet based on a clustering approach. 2022 International Conference on Computer Science and Software Engineering (CSASE). 2022. p. 54-59. DOI:10.1109/CSASE51777.2022.9759671.
  79. [79] Raut YC, et al. Early alert system using relative positioning in vehicular ad-hoc network. 2014 Annual International Conference on Emerging Research Areas - Magnetics, Machines and Drives (AICERA/ICMMD). 2014. p. 1-8. DOI:10.1109/AICERA.2014.6908167.
  80. [80] Sou SI, Tonguz OK. Enhancing vanet connectivity through roadside units on highways. IEEE Trans. Veh. Technol. 2011;60(8):3586-3602. DOI:10.1109/TVT.2011.2165739.
  81. [81] Nasr E, et al. An iot approach to vehicle accident detection, reporting, and navigation. 2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET). 2016. p. 231-236. DOI:10.1109/IMCET.2016.7777457.
  82. [82] Kumar A, Das D, IEEE. Intelligentchain: blockchain and machine learning based intelligent security application for internet of vehicles (iov). 2022 IEEE 95th Vehicular Technology Conference: (VTC-Spring). 2022. p. 1-5. DOI:10.1109/VTC2022-Spring54318.2022.9860946.
  83. [83] Marcillo P, Caraguay A, Hernandez-Alvarez M. A systematic literature review of learning-based traffic accident prediction models based on heterogeneous sources. Appl. Sci.-Basel. 2022;12(9):4529. DOI:10.3390/app12094529.
  84. [84] Wang L, et al. Real-time crash prediction for expressway weaving segments. Transp. Res. Pt. C-Emerg. Technol. 2015;61:1-10. DOI:10.1016/j.trc.2015.10.008.
  85. [85] Harb R, et al. Exploring precrash maneuvers using classification trees and random forests. Accid. Anal. Prev. 2009;41(1):98-107. DOI:10.1016/j.aap.2008.09.009.
  86. [86] Li P, Abdel-Aty M, Yuan J. Real-time crash risk prediction on arterials based on lstm-cnn. Accid. Anal. Prev. 2020;135:105371. DOI:10.1016/j.aap.2019.105371.
  87. [87] Z. C, et al. Macro-level accident fatality prediction using a combined model based on arima and multivariable linear regression. 2016 International Conference on Progress in Informatics and Computing (PIC). 2016. p. 133-137. DOI:10.1109/PIC.2016.7949481.
  88. [88] Zhang J, et al. Prediction of urban expressway total traffic accident duration based on multiple linear regression and artificial neural network. 2019 5th International Conference on Transportation Information and Safety (ICTIS). 2019. p. 503-510. DOI:10.1109/ictis.2019.8883690.
  89. [89] Getahun KA. Time series modeling of road traffic accidents in amhara region. J. Big Data. 2021;8(1):102. DOI:10.1186/s40537-021-00493-z.
  90. [90] Chen ZY, et al. Macro-level accident fatality prediction using a combined model based on arima and multivariable linear regression. 2016 4th IEEE International Conference on Progress in Informatics and Computing (IEEE PIC). 2016. p. 133-137. DOI:10.1109/PIC.2016.7949481.
  91. [91] Donnelly-Swift E, Kelly A. Factors associated with single-vehicle and multi-vehicle road traffic collision injuries in ireland. Int. J. Inj. Control Saf. Promot. 2016;23(4):351-361. DOI:10.1080/17457300.2015.1047861.
  92. [92] Wong CK. Designs for safer signal-controlled intersections by statistical analysis of accident data at accident blacksites. IEEE Access. 2019;7:111302-111314. DOI:10.1109/ACCESS.2019.2928038.
  93. [93] Awad HA, Parry T. Investigation the effect of pavement condition characteristics on bend segments accident frequency: application of fixed and random parameters negative binomial models. 2018 International conference on transportation and development. 2018. p. 165-176. DOI:10.1061/9780784481554.017.
  94. [94] Chin HC, Quddus MA. Applying the random effect negative binomial model to examine traffic accident occurrence at signalized intersections. Accid. Anal. Prev. 2003;35(2):253-259. DOI:10.1016/S0001-4575(02)00003-9.
  95. [95] Karacasu M, Ergul B, Yavuz AA. Estimating the causes of traffic accidents using logistic regression and discriminant analysis. Int. J. Inj. Control Saf. Promot. 2014;21(4):305-312. DOI:10.1080/17457300.2013.815632.
  96. [96] Gu X, et al. Utilizing uav video data for in-depth analysis of drivers' crash risk at interchange merging areas. Accid. Anal. Prev. 2019;123:159-169. DOI:10.1016/j.aap.2018.11.010.
  97. [97] Çelik AK, Oktay E. A multinomial logit analysis of risk factors influencing road traffic injury severities in the erzurum and kars provinces of turkey. Accid. Anal. Prev. 2014;72:66-77. DOI:10.1016/j.aap.2014.06.010.
  98. [98] Asare IO, Mensah AC. Crash severity modelling using ordinal logistic regression approach. Int. J. Inj. Control Saf. Promot. 2020;27(4):412-419. DOI:10.1080/17457300.2020.1790615.
  99. [99] Fountas G, Anastasopoulos PC, Abdel-Aty M. Analysis of accident injury-severities using a correlated random parameters ordered probit approach with time variant covariates. Anal. Methods Accid. Res. 2018;18:57-68. DOI:10.1016/j.amar.2018.04.003.
  100. [100] Hyodo S, Hasegawa K. Factors affecting analysis of the severity of accidents in cold and snowy areas using the ordered probit model. Asian Transp. Stud. 2021;7:100035. DOI:10.1016/j.eastsj.2021.100035.
  101. [101] Abdel-Aty M. Analysis of driver injury severity levels at multiple locations using ordered probit models. J. Saf. Res. 2003;34(5):597-603. DOI:10.1016/j.jsr.2003.05.009.
  102. [102] Lee J, et al. Model evaluation for forecasting traffic accident severity in rainy seasons using machine learning algorithms: seoul city study. Appl. Sci.-Basel. 2020;10(1):129. DOI:10.3390/app10010129.
  103. [103] Chang LY, Chen WC. Data mining of tree-based models to analyze freeway accident frequency. J. Saf. Res. 2005;36(4):365-375. DOI:10.1016/j.jsr.2005.06.013.
  104. [104] Zhao GM, Zhou WH, Li J. Regression analysis of association between vehicle performance and driver casualty risk in traffic accidents. 2015 International Conference on Transportation Information and Safety (ICTIS). 2015. p. 345-349. DOI:10.1109/ICTIS.2015.7232070.
  105. [105] Chang LY, Wang HW. Analysis of traffic injury severity: an application of non-parametric classification tree techniques. Accid. Anal. Prev. 2006;38(5):1019-1027. DOI:10.1016/j.aap.2006.04.009.
  106. [106] Balawi M, Tenekeci G. Time series traffic collision analysis of london hotspots: patterns, predictions and prevention strategies. Heliyon. 2024;10(4):e25710. DOI:10.1016/j.heliyon.2024.e25710.
  107. [107] de Grange L, et al. Estimating the impact of incidents on urban controlled-access highways: An empirical analysis. Appl. Econ. 2017;49(18):1763-1773. DOI:10.1080/00036846.2016.1226489.
  108. [108] Dereli MA, Erdogan S. A new model for determining the traffic accident black spots using gis-aided spatial statistical methods. Transp. Res. Pt. A-Policy Pract. 2017;103:106-117. DOI:10.1016/j.tra.2017.05.031.
  109. [109] Yu L, et al. Deep spatio-temporal graph convolutional network for traffic accident prediction. Neurocomputing. 2021;423:135-147. DOI:10.1016/j.neucom.2020.09.043.
  110. [110] Abellán J, López G, de Oña J. Analysis of traffic accident severity using decision rules via decision trees. Expert Syst. Appl. 2013;40(15):6047-6054. DOI:https://doi.org/10.1016/j.eswa.2013.05.027.
  111. [111] Azhar A, et al. Classification of driver injury severity for accidents involving heavy vehicles with decision tree and random forest. Sustainability. 2022;14(7):4101. DOI:10.3390/su14074101.
  112. [112] Zhang X, Fan L. A decision tree approach for traffic accident analysis of saskatchewan highways. 2013 26th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). 2013. p. 1-4. DOI:10.1109/CCECE.2013.6567833.
  113. [113] Wu W, et al. Economic development, demographic characteristics, road network and traffic accidents in zhongshan, china: gradient boosting decision tree model. Transportmetrica A. 2020;16(3):359-387. DOI:10.1080/23249935.2020.1711543.
  114. [114] Zhang WH, Liu T, Yi J. Exploring the spatiotemporal characteristics and causes of rear-end collisions on urban roadways. Sustainability. 2022;14(18):11761. DOI:10.3390/su141811761.
  115. [115] Xiong X, Chen L, Liang J. A new framework of vehicle collision prediction by combining svm and hmm. IEEE Trans. Intell. Transp. Syst. 2018;19(3):699-710. DOI:10.1109/TITS.2017.2699191.
  116. [116] Lv YS, et al. Real-time highway accident prediction based on support vector machines. 2009 21st Chinese Control and Decision Conference. 2009. p. 4403-4407. DOI:10.1109/CCDC.2009.5192409.
  117. [117] Cui KB, Du YS, Hu Z. Short-term load forecasting based on the bkf-svm. 2009 International Conference on Networks Security, Wireless Communications and Trusted Computing. 2009. p. 528-531. DOI:10.1109/NSWCTC.2009.170.
  118. [118] Kim EJ, et al. Application of naive bayesian approach in detecting reproducible fatal collision locations on freeway. PLoS One. 2021;16(5):e0251866. DOI:10.1371/journal.pone.0251866.
  119. [119] Kumar N, Acharya D, Lohani D. An iot-based vehicle accident detection and classification system using sensor fusion. IEEE Internet Things J. 2021;8(2):869-880. DOI:10.1109/JIOT.2020.3008896.
  120. [120] Bahiru TK, et al. Comparative study on data mining classification algorithms for predicting road traffic accident severity. 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT). 2018. p. 1655-1660. DOI:10.1109/ICICCT.2018.8473265.
  121. [121] Ghadi M, Torok A, Tanczos K. Integration of probability and clustering based approaches in the field of black spot identification. Period. Polytech.-Civ. Eng. 2019;63(1):46-52. DOI:10.3311/PPci.11753.
  122. [122] Kumar S, Toshniwal D. A data mining approach to characterize road accident locations. J. Mod. Transp. 2016;24(1):62-72. DOI:10.1007/s40534-016-0095-5.
  123. [123] Anderson TK. Kernel density estimation and k-means clustering to profile road accident hotspots. Accid. Anal. Prev. 2009;41(3):359-364. DOI:10.1016/j.aap.2008.12.014.
  124. [124] Yaman TT, Bilgic E, Esen MF. Analysis of traffic accidents with fuzzy and crisp data mining techniques to identify factors affecting injury severity. J. Intell. Fuzzy Syst. 2022;42(1):575-592. DOI:10.3233/JIFS-219213.
  125. [125] Zhang YF, et al. Exploring spatiotemporal patterns of expressway traffic accidents based on density clustering and bayesian network. ISPRS Int. J. Geo-Inf. 2023;12(2):73. DOI:10.3390/ijgi12020073.
  126. [126] Zhang X, et al. Traffic accident location study based on ad-dbscan algorithm with adaptive parameters. 2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD). 2023. p. 1160-1165. DOI:10.1109/CSCWD57460.2023.10152613.
  127. [127] Zhong WF, Du LJ. Predicting traffic casualties using support vector machines with heuristic algorithms: A study based on collision data of urban roads. Sustainability. 2023;15(4):2944. DOI:10.3390/su15042944.
  128. [128] Montazeri GM, Fotouhi A. Traffic condition recognition using the k-means clustering method. Sci. Iran. 2011;18(4):930-937. DOI:10.1016/j.scient.2011.07.004.
  129. [129] Syahputri K, et al. Clustering the vulnerability of traffic accidents in medan city with fuzzy c-means algorithm. 2nd Talenta Conference on Engineering, Science and Technology. 2020;801(1):012030. DOI:10.1088/1757-899X/801/1/012030.
  130. [130] Nogueira P, et al. Learning from accidents: spatial intelligence applied to road accidents with insights from a case study in setubal district, portugal. ISPRS Int. J. Geo-Inf. 2023;12(3):93. DOI:10.3390/ijgi12030093.
  131. [131] Khan SW, et al. Anomaly detection in traffic surveillance videos using deep learning. Sensors. 2022;22(17):6563. DOI:10.3390/s22176563.
  132. [132] Zhao HT, et al. Deep learning-based prediction of traffic accidents risk for internet of vehicles. China Commun. 2022;19(2):214-224. DOI:10.23919/JCC.2022.02.017.
  133. [133] Pérez-Sala L, et al. Deep learning model of convolutional neural networks powered by a genetic algorithm for prevention of traffic accidents severity. Chaos Solitons Fractals. 2023;169:113245. DOI:10.1016/j.chaos.2023.113245.
  134. [134] Huang T, Wang S, Sharma A. Highway crash detection and risk estimation using deep learning. Accid. Anal. Prev. 2020;135:105392. DOI:10.1016/j.aap.2019.105392.
  135. [135] Chang YL, et al. Consolidated convolutional neural network for hyperspectral image classification. Remote Sens. 2022;14(7):1571. DOI:10.3390/rs14071571.
  136. [136] Sun YS, et al. Detecting anomalous traffic behaviors with seasonal deep kalman filter graph convolutional neural networks. J. King Saud Univ.-Comput. Inf. Sci. 2022;34(8):4729-4742. DOI:10.1016/j.jksuci.2022.05.017.
  137. [137] Wang S, et al. Traffic accident risk prediction via multi-view multi-task spatio-temporal networks. IEEE Trans. Knowl. Data Eng. 2021;35(12):12323-12336. DOI:10.1109/TKDE.2021.3135621.
  138. [138] Sameen MI, Pradhan B. Severity prediction of traffic accidents with recurrent neural networks. Appl. Sci.-Basel. 2017;7(6):476. DOI:10.3390/app7060476.
  139. [139] Shang Q, Xie T, Yu Y. Prediction of duration of traffic incidents by hybrid deep learning based on multi-source incomplete data. Int. J. Environ. Res. Public Health. 2022;19(17):10903. DOI:10.3390/ijerph191710903.
  140. [140] Ren H, et al. A deep learning approach to the citywide traffic accident risk prediction. 2018 21st IEEE International Conference on Intelligent Transportation Systems (ITSC). 2018. p. 3346-3351. DOI: 10.1109/ITSC.2018.8569437.
  141. [141] Lin DJ, et al. Intelligent traffic accident prediction model for internet of vehicles with deep learning approach. IEEE Trans. Intell. Transp. Syst. 2022;23(3):2340-2349. DOI:10.1109/TITS.2021.3074987.
  142. [142] Hu Z, Zhou J, Zhang E. Improving traffic safety through traffic accident risk assessment. Sustainability. 2023;15(4):3748. DOI:10.3390/su15043748.
  143. [143] Senarath Y, et al. Practitioner-centric approach for early incident detection using crowdsourced data for emergency services. 2021 21st IEEE International Conference on Data Mining (IEEE ICDM). 2021. p. 1318-1323. DOI:10.1109/ICDM51629.2021.00164.
  144. [144] Yang D, et al. Freeway accident detection and classification based on the multi-vehicle trajectory data and deep learning model. Transp. Res. Pt. C-Emerg. Technol. 2021;130:103303. DOI:10.1016/j.trc.2021.103303.
  145. [145] Wu MY, et al. A multi-attention dynamic graph convolution network with cost-sensitive learning approach to road-level and minute-level traffic accident prediction. IET Intell. Transp. Syst. 2023;17(2):270-284. DOI:10.1049/itr2.12254.
  146. [146] Kashifi MT, Al-Turki M, Sharify AW. Deep hybrid learning framework for spatiotemporal crash prediction using big traffic data. International Journal of Transportation Science and Technology (IJTST). 2022;12(3):793-808. DOI:10.1016/j.ijtst.2022.07.003.
  147. [147] de Medrano R, Aznarte JL. A new spatio-temporal neural network approach for traffic accident forecasting. Appl. Artif. Intell. 2021;35(10):782-801. DOI:10.1080/08839514.2021.1935588.
  148. [148] Lv YS, et al. Real-time highway traffic accident prediction based on the k-nearest neighbor method. 2009 International Conference on Measuring Technology and Mechatronics Automation. 2009. p. 547-550. DOI:10.1109/ICMTMA.2009.657.
  149. [149] Lv YS, et al. Traffic flow prediction with big data: a deep learning approach. IEEE Trans. Intell. Transp. Syst. 2015;16(2):865-873. DOI:10.1109/TITS.2014.2345663.
  150. [150] Ma XL, et al. Large-scale transportation network congestion evolution prediction using deep learning theory. PLoS One. 2015;10(3):e0119044. DOI:10.1371/journal.pone.0119044.
  151. [151] Yang ZK, Zhang WP, Feng J. Predicting multiple types of traffic accident severity with explanations: A multi-task deep learning framework. Saf. Sci. 2022;146:105522. DOI:10.1016/j.ssci.2021.105522.
  152. [152] Cho I, et al. Reinforcement learning for predicting traffic accidents. 2023 5th International Conference on Artificial Intelligence in Information and Communication (ICAIIC). 2023. p. 684-688. DOI:10.1109/ICAIIC57133.2023.10067034.
  153. [153] Ji XY, et al. Digital twin empowered model free prediction of accident-induced congestion in urban road networks. 2022 IEEE 95th Vehicular Technology Conference: (VTC-Spring). 2022. p. 1-6. DOI:10.1109/VTC2022-Spring54318.2022.9860491.
  154. [154] Zhang HT, et al. Overfitting and underfitting analysis for deep learning based end-to-end communication systems. 2019 11th IEEE International Conference on Wireless Communications and Signal Processing (WCSP). 2019. p. 1-6. DOI:10.1109/wcsp.2019.8927876.
  155. [155] Watanabe S, Yamana H, IEEE. Overfitting measurement of deep neural networks using no data. 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA). 2021. p. 1-10. DOI:10.1109/DSAA53316.2021.9564119.
  156. [156] Li QP, Yan M, Xu J. Optimizing convolutional neural network performance by mitigating underfitting and overfitting. 2021 IEEE/ACIS 19th International Conference on Computer and Information Science (ICIS). 2021. p. 126-131. DOI:10.1109/ICIS51600.2021.9516868.
  157. [157] Liu Y, et al. Ensemble learning with correlation-based penalty. 2014 IEEE 12th International Conference on Dependable, Autonomic and Secure Computing (DASC). 2014. p. 350-353. DOI:10.1109/DASC.2014.69.
  158. [158] Liu Y, IEEE. New discoveries in balanced ensemble learning. 2012 International Joint Conference on Neural Networks (IJCNN). 2012. p. 1-8. DOI: 10.1109/IJCNN.2012.6252423.
  159. [159] Guo Y, et al. Research review of space-frequency domain image enhancement methods. Computer Engineering and Application. 2022;58(11):23-32. DOI:1002-8331(2022)58:11<23:KPYTXZ>2.0.TX;2-4.
  160. [160] Wu XX, Liu JG. A new early stopping algorithm for improving neural network generalization. 2009 2nd International Conference on Intelligent Computation Technology and Automation. 2009. p. 15-18. DOI:10.1109/ICICTA.2009.11.
  161. [161] Chen H, et al. Image recognition algorithm based on artificial intelligence. Neural Comput. Appl. 2022;34(9):6661-6672. DOI:10.1007/s00521-021-06058-8.
  162. [162] Scala F, et al. A general approach to dropout in quantum neural networks. Adv. Quantum Technol. 2023:2300220. DOI:10.1002/qute.202300220.
  163. [163] Spiliotis A, et al. Integration and field evaluation of an iov system for enhancing road safety. Appl. Sci.-Basel. 2022;12(23):12262. DOI:10.3390/app122312262.
  164. [164] Essa M, Sayed T. Self-learning adaptive traffic signal control for real-time safety optimization. Accid. Anal. Prev. 2020;146:105713. DOI:10.1016/j.aap.2020.105713.
Show more

SPECIAL ISSUE IS OUT

Innovation and New Technologies in Transport and Logistics

Guest Editor: Eleonora Papadimitriou, PhD

Editors: Marko Matulin, PhD; Dario Babić, PhD; Marko Ševrović, PhD.

RECENT PAPERS

Browse through the selection of our recent research
Evaluating Barriers and Enablers of Willingness-To-Work as a Crowdshipper – A Comparison of Business-To-Business and Business-To-Customer Models from a Slovenian PerspectiveStudy on Longitudinal Collision Risk of Closely Spaced Parallel Runways Paired ApproachRoad Traffic Accident Prediction Based on Multi-Source Data – A Systematic ReviewAn M-DeepSORT Algorithm for Pedestrian Detection and Tracking Based on Video Images – A Case Study in Ji-nan Subway Station

Accelerating Discoveries in Traffic Science |
2024 © Promet - Traffic&Transportation journal