Modeling Damage Reduction in Road Accidents

Use of advanced technologies in automobiles as well as the use of intelligent road traffic control and monitoring systems continues to have significant losses and, consequently, the effort to identify the causes of road accidents is of particular importance. The pattern of identifying the causes of road accidents, on the one hand, helps the police in accurately identifying the cause of the accident, and on the other hand, employing insurers to pay for the culprit, speed and accuracy and gathering relevant information. Damage and processing make it easier for automakers to secure their products and fix their modeling defects. Road officials can also use the outputs of the model to identify the causes of car damage to fix road and road engineering bugs. The purpose of this study was to reduce the number of traffic accidents and injuries using neural networks. The method of doing the research is field and practical method, namely modeling and manufacturing of an electronic system, testing and testing and recording the results of practical experiments performed with the mentioned device. This study proposes a model for identifying the causes of road damage. The model provides useful information to the police and insurance companies before recording the moment they hit all the sensors installed in the vehicle, as well as processing and interpreting them. The pattern design and its hardware requirements installed inside the vehicle are explained. The pattern recognition system is based on a neural network system whose rules have been derived from the results of numerous practical experiments. Extracting the rules and modeling the neural network inference engine from the graphs of practical experiments has led to a model that identifies and presents basic collision-generating events.