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 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.

[1]  N. Voća,et al.  Optimization of Caper Drying Using Response Surface Methodology and Artificial Neural Networks for Energy Efficiency Characteristics , 2023, Energies.

[2]  M. Pucarević,et al.  Chemometric Approach to Pesticide Residue Analysis in Surface Water , 2022, Water.

[3]  L. Pezo,et al.  Seasonal Variations in Essential Oil Composition of Immortelle Cultivated in Serbia , 2022, Horticulturae.

[4]  L. Pezo,et al.  Artificial neural network and random forest regression models for modelling fatty acid and tocopherol content in oil of winter rapeseed , 2022, Journal of Food Composition and Analysis.

[5]  L. Pezo,et al.  Agricultural Parameters and Essential Oil Content Composition Prediction of Aniseed, Based on Growing Year, Locality and Fertilization Type—An Artificial Neural Network Approach , 2022, Life.

[6]  L. Pezo,et al.  Model for Determining Noise Level Depending on Traffic Volume at Intersections , 2022, Sustainability.

[7]  J. Su,et al.  Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian Optimization , 2022, Eng. Appl. Artif. Intell..

[8]  N. Voća,et al.  Prediction of the Production of Separated Municipal Solid Waste by Artificial Neural Networks in Croatia and the European Union , 2022, Sustainability.

[9]  Amir Mosavi,et al.  Inference and Local Influence Assessment in a Multifactor Skew-Normal Linear Mixed Model , 2022, Mathematics.

[10]  B. De Baets,et al.  Embedding metric learning into an extreme learning machine for scene recognition , 2022, Expert Syst. Appl..

[11]  Chaozhong Wu,et al.  A grey convolutional neural network model for traffic flow prediction under traffic accidents , 2022, Neurocomputing.

[12]  Hao Ma,et al.  A novel multi-innovation gradient support vector machine regression method. , 2022, ISA transactions.

[13]  Tingjian Ge,et al.  On the interpretability of machine learning methods in crash frequency modeling and crash modification factor development. , 2022, Accident; analysis and prevention.

[14]  Sarbani Roy,et al.  OccupancySense: Context-based indoor occupancy detection & prediction using CatBoost model , 2022, Appl. Soft Comput..

[15]  J. Mahmood,et al.  Accurate estimation of tool wear levels during milling, drilling and turning operations by designing novel hyperparameter tuned models based on LightGBM and Stacking , 2022, Measurement.

[16]  Dalibor Pešić,et al.  Determination the influence of road factors on the occurrence of traffic accidents with dead pedestrians on the territory of Belgrade by independent estimates , 2021, Put i saobraćaj.

[17]  Z. Kai,et al.  Optimization method of first-arrival waveform inversion based on the L-BFGS algorithm , 2021, Applied Geophysics.

[18]  Tanzina Afrin,et al.  A Long Short-Term Memory-based correlated traffic data prediction framework , 2021, Knowl. Based Syst..

[19]  Ruidong Chang,et al.  Application of Artificial Neural Networks in Construction Management: Current Status and Future Directions , 2021, Applied Sciences.

[20]  Jingjing Chen,et al.  Motorcycle Ban and Traffic Safety: Evidence from a Quasi-Experiment at Zhejiang, China , 2021, Journal of Advanced Transportation.

[21]  Remigio Berruto,et al.  Machine Learning in Agriculture: A Comprehensive Updated Review , 2021, Sensors.

[22]  Francis W. L. Esmonde-White,et al.  Exploration of Principal Component Analysis: Deriving Principal Component Analysis Visually Using Spectra , 2021, Applied spectroscopy.

[23]  Fuxin Niu,et al.  Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons , 2020 .

[24]  M. M. Reis,et al.  Identification of Cold Spots Using Non-Destructive Hyperspectral Imaging Technology in Model Food Processed by Coaxially Induced Microwave Pasteurization and Sterilization , 2020, Foods.

[25]  L. Pezo,et al.  Prediction of denitrification capacity of alkalotolerant bacterial isolates from soil - an artificial neural network model , 2020 .

[26]  Zhihao Zhang,et al.  Traffic Accident Prediction Based on LSTM-GBRT Model , 2020, J. Control. Sci. Eng..

[27]  Fadel M. Megahed,et al.  A Review of Data Analytic Applications in Road Traffic Safety. Part 1: Descriptive and Predictive Modeling , 2020, Sensors.

[28]  M. Pal,et al.  Deep neural network-based predictive modeling of road accidents , 2020, Neural Computing and Applications.

[29]  Vladan J. Tubic,et al.  Traffic accidents costs on state roads of the first order , 2019 .

[30]  Dalibor Pešić,et al.  Identifying contributing factors on occurrence traffic accidents applying in-depth studies and Bayesian neural networks , 2019, Put i saobraćaj.

[31]  Abhishek Chakraborty,et al.  Development of pedestrian crash prediction model for a developing country using artificial neural network , 2019, International journal of injury control and safety promotion.

[32]  Jing Chen,et al.  Traffic Accident’s Severity Prediction: A Deep-Learning Approach-Based CNN Network , 2019, IEEE Access.

[33]  Long Chen,et al.  Analysis of Roadway Traffic Accidents Based on Rough Sets and Bayesian Networks , 2018 .

[34]  Z. Halim,et al.  Artificial intelligence techniques for driving safety and vehicle crash prediction , 2016, Artificial Intelligence Review.

[35]  Milos N. Mladenovic,et al.  Contribution to Accident Prediction Models Development for Rural Two-Lane Roads in Serbia , 2016 .

[36]  Ahmet Tortum,et al.  An Artificial Neural Network Model for Highway Accident Prediction: A Case Study of Erzurum, Turkey , 2015 .

[37]  Jochen Köhler,et al.  Prediction of road accidents: A Bayesian hierarchical approach. , 2013, Accident; analysis and prevention.

[38]  Hülya Olmuş,et al.  Analysis of Traffic Accidents Caused by Drivers by Using Log-Linear Models , 2012 .

[39]  Mohammed Salifu,et al.  Crash prediction model for two-lane rural highways in the Ashanti region of Ghana , 2011 .

[40]  Mojtaba Ziyadi,et al.  Prediction of accident severity using artificial neural networks , 2011 .

[41]  A Veeraragavan,et al.  Random parameter models for accident prediction on two-lane undivided highways in India. , 2011, Journal of safety research.

[42]  Mohamed Abdel-Aty,et al.  Multilevel data and bayesian analysis in traffic safety. , 2010, Accident; analysis and prevention.

[43]  Salvatore Cafiso,et al.  Development of comprehensive accident models for two-lane rural highways using exposure, geometry, consistency and context variables. , 2010, Accident; analysis and prevention.

[44]  Srinivas R. Geedipally,et al.  Examination of Methods to Estimate Crash Counts by Collision Type , 2010 .

[45]  Ross Woods,et al.  Analytical assessment and parameter estimation of a low-dimensional groundwater model. , 2009 .

[46]  N. Voća,et al.  Estimation of the storage properties of rapeseeds using an artificial neural network , 2022, Industrial Crops and Products.

[47]  Marina Milenković,et al.  Impact of road and traffic characteristics on the traffic accidents , 2017 .

[48]  Mehdi Hosseinpour,et al.  Exploring the effects of roadway characteristics on the frequency and severity of head-on crashes: case studies from Malaysian federal roads. , 2014, Accident; analysis and prevention.

[49]  J. Bared,et al.  Accident Models for Two-Lane Rural Segments and Intersections , 1998 .

[50]  Youngohc Yoon,et al.  A Comparison of Discriminant Analysis versus Artificial Neural Networks , 1993 .