Abstract
Studies of traffic accident analysis, as well as prediction, have traditionally relied on small-scale datasets with limited coverage, so limiting the scope and usefulness of these analyses. There is also the issue that many large-scale databases are either confidential, outdated, or missing important contextual factors like environmental stimuli (weather, points of interest, etc.). There are presently 37 million records stored in the US Accidents dataset, including crashes that occurred anywhere in the 48 contiguous states between 2016 and 2021. We were able to piece together details like date, time, place, weather, season, and landmarks from this information. Used deep neural networks that have a trainable embedding component, a fully connected network, and a recurrent network for time-sensitive data and time-insensitive data, respectively (for capturing spatial heterogeneity). Our research includes the prediction of the occurrence of accident incidents using deep neural networks and an understanding of Accident Severity against machine learning models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798–1828 (2013)
Najafabadi, M.M., Villanustre, F., Khoshgoftaar, T.M., Seliya, N., Wald, R., Muharemagic, E.: Deep learning applications and challenges in big data analytics. J. Big Data 2(1), 1–21 (2015). https://doi.org/10.1186/s40537-014-0007-7
Dabiri, S., Heaslip, K.: Developing a Twitter-based traffic event detection model using deep learning architectures. Expert Syst. Appl. 118, 425–439 (2019)
Li, P., Abdel-Aty, M., Yuan, J.: Real-time crash risk prediction on arterials based on LSTM-CNN. Accid. Anal. Prev. 135, 105371 (2020)
Chen, C.. Fan, X., Zheng, C., Xiao, L., Cheng, M., Wang, C.: SDCAE: stack denoising convolutional autoencoder model for accident risk prediction via traffic big data. In: Proceedings of the Sixth International Conference on Advanced Cloud and Big Data (CBD), Lanzhou, China, 15 August 2018, pp. 328–333. IEEE, New York (2018)
Bao, J., Liu, P., Ukkusuri, S.V.: A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data. Accid. Anal. Prev. 122, 239–254 (2019)
Yu, L., Du, B., Hu, X., Sun, L., Han, L., Lv, W.: Deep Spatio-temporal graph convolutional network for traffic accident prediction. Neurocomputing 423, 135–147 (2020)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Moosavi, S., Samavatian, M. H., Parthasarathy, S., Ramnath, R.: A Countrywide Traffic Accident Dataset. arXiv. https://doi.org/10.48550/arXiv.1906.05409 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kandacharam, S., Rajathilagam, B. (2023). Prediction of Accident and Accident Severity Based on Heterogeneous Data. In: Molla, A.R., Sharma, G., Kumar, P., Rawat, S. (eds) Distributed Computing and Intelligent Technology. ICDCIT 2023. Lecture Notes in Computer Science, vol 13776. Springer, Cham. https://doi.org/10.1007/978-3-031-24848-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-24848-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-24847-4
Online ISBN: 978-3-031-24848-1
eBook Packages: Computer ScienceComputer Science (R0)