Predicting Road Traffic Accidents—Artificial Neural Network Approach
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 predi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/16/5/257 |
| _version_ | 1797601462732193792 |
|---|---|
| author | Dragan Gatarić Nenad Ruškić Branko Aleksić Tihomir Đurić Lato Pezo Biljana Lončar Milada Pezo |
| author_facet | Dragan Gatarić Nenad Ruškić Branko Aleksić Tihomir Đurić Lato Pezo Biljana Lončar Milada Pezo |
| author_sort | Dragan Gatarić |
| collection | DOAJ |
| description | 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 <i>r</i><sup>2</sup> 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. |
| first_indexed | 2024-03-11T04:01:09Z |
| format | Article |
| id | doaj.art-f68f05b2a3a64ae6aeffb45bfde19a09 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-11T04:01:09Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-f68f05b2a3a64ae6aeffb45bfde19a092023-11-18T00:09:00ZengMDPI AGAlgorithms1999-48932023-05-0116525710.3390/a16050257Predicting Road Traffic Accidents—Artificial Neural Network ApproachDragan Gatarić0Nenad Ruškić1Branko Aleksić2Tihomir Đurić3Lato Pezo4Biljana Lončar5Milada Pezo6Faculty of Transport and Traffic Engineering, University of East Sarajevo, 71123 Doboj, Bosnia and HerzegovinaDepartment of Traffic Engineering, Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, SerbiaFaculty of Transport and Traffic Engineering, University of East Sarajevo, 71123 Doboj, Bosnia and HerzegovinaFaculty of Transport and Traffic Engineering, University of East Sarajevo, 71123 Doboj, Bosnia and HerzegovinaInstitute of General and Physical Chemistry, University of Belgrade, Studentski Trg 12-16, 11000 Belgrade, SerbiaFaculty of Technology Novi Sad, University of Novi Sad, Bulevar Cara Lazara 1, 21000 Novi Sad, SerbiaDepartment of Thermal Engineering and Energy, “VINČA” Institute of Nuclear Sciences, National Institute of the Republic of Serbia, University of Belgrade, Mike Petrovića Alasa 12-14, 11351 Belgrade, SerbiaRoad 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 <i>r</i><sup>2</sup> 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.https://www.mdpi.com/1999-4893/16/5/257traffic safetytraffic accidentpredictionmodellingartificial neural networks |
| spellingShingle | Dragan Gatarić Nenad Ruškić Branko Aleksić Tihomir Đurić Lato Pezo Biljana Lončar Milada Pezo Predicting Road Traffic Accidents—Artificial Neural Network Approach Algorithms traffic safety traffic accident prediction modelling artificial neural networks |
| title | Predicting Road Traffic Accidents—Artificial Neural Network Approach |
| title_full | Predicting Road Traffic Accidents—Artificial Neural Network Approach |
| title_fullStr | Predicting Road Traffic Accidents—Artificial Neural Network Approach |
| title_full_unstemmed | Predicting Road Traffic Accidents—Artificial Neural Network Approach |
| title_short | Predicting Road Traffic Accidents—Artificial Neural Network Approach |
| title_sort | predicting road traffic accidents artificial neural network approach |
| topic | traffic safety traffic accident prediction modelling artificial neural networks |
| url | https://www.mdpi.com/1999-4893/16/5/257 |
| work_keys_str_mv | AT dragangataric predictingroadtrafficaccidentsartificialneuralnetworkapproach AT nenadruskic predictingroadtrafficaccidentsartificialneuralnetworkapproach AT brankoaleksic predictingroadtrafficaccidentsartificialneuralnetworkapproach AT tihomirđuric predictingroadtrafficaccidentsartificialneuralnetworkapproach AT latopezo predictingroadtrafficaccidentsartificialneuralnetworkapproach AT biljanaloncar predictingroadtrafficaccidentsartificialneuralnetworkapproach AT miladapezo predictingroadtrafficaccidentsartificialneuralnetworkapproach |