Predicting Road Traffic Accidents—Artificial Neural Network Approach
Authors
Gatarić, DraganRuškić, Nenad

Aleksić, Branko
Đurić, Tihomir
Pezo, Lato

Lončar, Biljana

Pezo, Milada L.

Article (Published version)
Metadata
Show full item recordAbstract
Road traffic accidents are a significant public health issue, accounting for almost 1.3 million deaths worldwide annually, with millions more experiencing non-fatal injuries. A variety of subjective and objective factors contribute to the occurrence of traffic accidents, making it difficult to predict and prevent them on new road sections. Artificial neural networks (ANN) have demonstrated their effectiveness in predicting traffic accidents using limited data sets. This study presents two ANN models to predict traffic accidents on common roads in the Republic of Serbia and the Republic of Srpska (Bosnia and Herzegovina) using objective factors that can be easily determined, such as road length, terrain type, road width, average daily traffic volume, and speed limit. The models predict the number of traffic accidents, as well as the severity of their consequences, including fatalities, injuries and property damage. The developed optimal neural network models showed good generalization c...apabilities for the collected data foresee, and could be used to accurately predict the observed outputs, based on the input parameters. The highest values of r2 for developed models ANN1 and ANN2 were 0.986, 0.988, and 0.977, and 0.990, 0.969, and 0.990, accordingly, for training, testing and validation cycles. Identifying the most influential factors can assist in improving road safety and reducing the number of accidents. Overall, this research highlights the potential of ANN in predicting traffic accidents and supporting decision-making in transportation planning.
Keywords:
artificial neural networks / modelling / prediction / traffic accident / traffic safetySource:
Algorithms, 2023, 16, 5, 257-Funding / projects:
- Ministry of Education, Science and Technological Development, Republic of Serbia, Grant no. 200017 (University of Belgrade, Institute of Nuclear Sciences 'Vinča', Belgrade-Vinča) (RS-200017)
- Ministry of Education, Science and Technological Development, Republic of Serbia, Grant no. 200051 (Institute of General and Physical Chemistry, Belgrade) (RS-200051)
- Ministry of Education, Science and Technological Development, Republic of Serbia, Grant no. 200134 (University of Novi Sad, Faculty of Technology) (RS-200134)
Institution/Community
VinčaTY - JOUR AU - Gatarić, Dragan AU - Ruškić, Nenad AU - Aleksić, Branko AU - Đurić, Tihomir AU - Pezo, Lato AU - Lončar, Biljana AU - Pezo, Milada L. PY - 2023 UR - https://vinar.vin.bg.ac.rs/handle/123456789/11078 AB - Road traffic accidents are a significant public health issue, accounting for almost 1.3 million deaths worldwide annually, with millions more experiencing non-fatal injuries. A variety of subjective and objective factors contribute to the occurrence of traffic accidents, making it difficult to predict and prevent them on new road sections. Artificial neural networks (ANN) have demonstrated their effectiveness in predicting traffic accidents using limited data sets. This study presents two ANN models to predict traffic accidents on common roads in the Republic of Serbia and the Republic of Srpska (Bosnia and Herzegovina) using objective factors that can be easily determined, such as road length, terrain type, road width, average daily traffic volume, and speed limit. The models predict the number of traffic accidents, as well as the severity of their consequences, including fatalities, injuries and property damage. The developed optimal neural network models showed good generalization capabilities for the collected data foresee, and could be used to accurately predict the observed outputs, based on the input parameters. The highest values of r2 for developed models ANN1 and ANN2 were 0.986, 0.988, and 0.977, and 0.990, 0.969, and 0.990, accordingly, for training, testing and validation cycles. Identifying the most influential factors can assist in improving road safety and reducing the number of accidents. Overall, this research highlights the potential of ANN in predicting traffic accidents and supporting decision-making in transportation planning. T2 - Algorithms T1 - Predicting Road Traffic Accidents—Artificial Neural Network Approach VL - 16 IS - 5 SP - 257 DO - 10.3390/a16050257 ER -
@article{ author = "Gatarić, Dragan and Ruškić, Nenad and Aleksić, Branko and Đurić, Tihomir and Pezo, Lato and Lončar, Biljana and Pezo, Milada L.", year = "2023", abstract = "Road traffic accidents are a significant public health issue, accounting for almost 1.3 million deaths worldwide annually, with millions more experiencing non-fatal injuries. A variety of subjective and objective factors contribute to the occurrence of traffic accidents, making it difficult to predict and prevent them on new road sections. Artificial neural networks (ANN) have demonstrated their effectiveness in predicting traffic accidents using limited data sets. This study presents two ANN models to predict traffic accidents on common roads in the Republic of Serbia and the Republic of Srpska (Bosnia and Herzegovina) using objective factors that can be easily determined, such as road length, terrain type, road width, average daily traffic volume, and speed limit. The models predict the number of traffic accidents, as well as the severity of their consequences, including fatalities, injuries and property damage. The developed optimal neural network models showed good generalization capabilities for the collected data foresee, and could be used to accurately predict the observed outputs, based on the input parameters. The highest values of r2 for developed models ANN1 and ANN2 were 0.986, 0.988, and 0.977, and 0.990, 0.969, and 0.990, accordingly, for training, testing and validation cycles. Identifying the most influential factors can assist in improving road safety and reducing the number of accidents. Overall, this research highlights the potential of ANN in predicting traffic accidents and supporting decision-making in transportation planning.", journal = "Algorithms", title = "Predicting Road Traffic Accidents—Artificial Neural Network Approach", volume = "16", number = "5", pages = "257", doi = "10.3390/a16050257" }
Gatarić, D., Ruškić, N., Aleksić, B., Đurić, T., Pezo, L., Lončar, B.,& Pezo, M. L.. (2023). Predicting Road Traffic Accidents—Artificial Neural Network Approach. in Algorithms, 16(5), 257. https://doi.org/10.3390/a16050257
Gatarić D, Ruškić N, Aleksić B, Đurić T, Pezo L, Lončar B, Pezo ML. Predicting Road Traffic Accidents—Artificial Neural Network Approach. in Algorithms. 2023;16(5):257. doi:10.3390/a16050257 .
Gatarić, Dragan, Ruškić, Nenad, Aleksić, Branko, Đurić, Tihomir, Pezo, Lato, Lončar, Biljana, Pezo, Milada L., "Predicting Road Traffic Accidents—Artificial Neural Network Approach" in Algorithms, 16, no. 5 (2023):257, https://doi.org/10.3390/a16050257 . .