Abstract
This paper proposes to predict traffic accidents based on IoTs and deep learning to address the current problem of inaccurate traffic accident prediction. Since traditional traffic accident prediction often applies classical prediction algorithms to a small portion of data, the obtained models can only predict a small range of traffic accidents. Most accident prediction models are limited by the lack of data features, do not consider the problems of practical application scenarios, and do not incorporate regional heterogeneity, so the prediction accuracy of accident prediction models is poor. This paper analyzes and summarizes the relationship between traffic accidents and influencing factors from five aspects, such as people, vehicles, roads and environment, and proves the influence of regional heterogeneity on accidents, which paves the way for traffic accident prediction. The data and heterogeneous spatial data are preprocessed and feature selected, respectively. Logistic regression and random forest algorithm are used to train the corresponding prediction models. The results show that the prediction model combined with regional heterogeneity has better comprehensive performance than the original data.
Similar content being viewed by others
Data availability
Enquiries about data availability should be directed to the authors.
References
Chen C (2020) Research on missing value recovery method of traffic data based on sparse representation. Jiangsu Univ
Chen Y, Wei S, Zhang L (2020) Road traffic accident prediction model based on GM (1, n). J North China Univ Technol: Nat Sci Edit 1:47–50
Deng J, Zhang Q (2019) Traffic flow prediction model based on data mining technology. Comput Syst Appl 28(07):114–120
Fang Y (2020) Research on expressway traffic incident detection algorithm based on ensemble learning. Jilin Univ
Gu H (2020) Research on variable lane clearing control based on traffic flow prediction. North Univ Technol
He L, Chen L, Jiang J (2019) Traffic flow prediction based on spatiotemporal data. Traffic Trans 32(S1):75–80
Hong Z (2020) Urban traffic flow prediction method based on multi graph neural network. Zhejiang Univ Technol
Huang Y (2020) Short term traffic flow prediction strategy based on heterogeneous wireless network. Zhejiang Univ Technol
Li S (2020a) Short term traffic flow prediction based on spatiotemporal fusion model of path clustering. Hefei Univ Technol
Li J (2020b) Short term traffic flow prediction based on long short term memory network model. Shandong Univ
Li M, Huang C (2019) Short term traffic flow prediction based on ensemble learning. J Jinan Univ (NATURAL SCIENCE EDITION) 33(05):389–395
Li T, Wang Q (2020) Prediction of road network traffic flow under the background of spatiotemporal analysis. Comput Eng Appl 56(17):258–265
Peng P (2020) Research on road traffic flow prediction method based on deep learning. Zhejiang Univ Technol
Poorzaker Arabani S, Ebrahimpour Komleh H (2018) The improvement of forecasting ATMs cash demand of iran banking network using convolutional neural network. Arabian J Sci Eng 44:3733–3743
Qiu S (2020a) Research on signal control time division method based on intersection flow prediction data. Jilin Univ
Qiu Y (2020b) Research on regional traffic coordinated control based on short-term traffic flow prediction. Zhejiang Normal Univ
She H (2020) Research and application of traffic congestion control based on state prediction. Univ Sci Technol China
Song S (2019) Short term traffic flow prediction based on floating car data. Dalian Univ Technol
Sun S, Ma H, Jia Z, Li M, Sun S, Ma H, Jia Z, Li M (2021) Risk factors analysis of 880 cases of open limb injury complicated with early infection caused by car accident. J Shandong Univ (Med Edit), Vol. 59, No. 1, pp. 72–77, Istic PKU Ca
Tang S (2020a) Research on short-term traffic flow prediction method based on EEMD. Hefei Univ Technol
Tang L (2020b) Research and implementation of intelligent traffic situation prediction technology based on attention mechanism. Zhejiang Univ Technol
Tang R, Chen Q, Lei X (2019) Gqpso-wnn short term traffic flow prediction based on phase space reconstruction. Comput Appl Softw 36(07):311–316
Wang S, Xiao J, Du F et al (2020) A traffic accident prediction method based on hybrid geographic weighted regression: cn111210052a
Xie J (2020) Research and application of traffic flow prediction method based on deep learning. Zhejiang Univ Technol
Xue S (2020) Study on traffic flow prediction of urban road network based on spatiotemporal convolution network. Jiangxi Normal Univ
Xu D, Yin Y, Zhang X et al (2020) Maritime traffic accident prediction based on improved three parameter grey model. China Navig 043(001):12–17
Yang W, Zhang Z, Wushouer S et al (2020) Gbrt traffic accident prediction model based on time series. J Univ Electron Sci Technol, (4)
Yin H, Zhou W (2020) Application of deep learning in expressway traffic accident prediction in Jiangsu Province. China Traffic Inf 000(002):125–129
Zhang T (2020a) Research on short term traffic forecasting algorithm based on deep learning. Dalian Maritime Univ
Zhang B (2020b) Research on traffic state recognition and visualization technology based on ship big data. Dalian Maritime Univ
Zhang D (2020c) Traffic state identification and prediction of Urban expressway based on multi-source data. South China Univ Technol
Zhang Y, Fu Y (2020) Prediction of ship traffic accidents based on arima-bp neural network. J Shanghai Maritime Univ, (3).
Zhao Q (2019) Research on recurrent neural network algorithm for short-term traffic flow analysis and prediction. Xi'an Univ Technol
Zhou Z (2020) Research on travel time prediction of commuter section based on KNN and xgboost. Nanjing Univ
Zhu K (2020) Research and application of traffic flow forecasting method based on BRB and rnn-gcn. Harbin Normal Univ
Zhu Y, Guo T (2019) Short term traffic flow prediction at intersections based on GA-BP neural network. Transp Res 5(02):45–51
Zou Y, Deng M (2019) Traffic flow prediction method based on long-term convolution depth network. Surv Sp Geogr Inf, 42 (07): 131–133, 137
Acknowledgements
This work is supported by high data analysis road video surveillance and perceived technology research project number 2019G1 smart road big data application technology research project number 2016Y4.
Funding
The authors have not disclosed any funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have not disclosed any competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chuanxia, S., Han, Z. & Peixuan, Y. Machine learning and IoTs for forecasting prediction of smart road traffic flow. Soft Comput 27, 323–335 (2023). https://doi.org/10.1007/s00500-022-07618-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-022-07618-3