With the advancement in vehicular technology and automotive industry, Intelligent Transportation System (ITS) focuses on the safety and comfort of road users. The transportation system faces a key challenge of increase in road crashes, with the substantial growth in the count of vehicles on roads. Road accidents not only increase the risk for vulnerable road users but also lead to traffic delays or congestion. The amount of traffic delay is dependent on the severity of the accident. In this paper, we have implemented a Dense Neural Network (DNN) for the classification of road accidents according to their impact on traffic delays. Four classes (Class 1, 2, 3, and 4) have been identified on the basis of the severity of road accidents. Class 1 refers to the least severe accidents resulting in short traffic delays and Class 4 refers to the accidents resulting in long traffic delays. Different machine learning classification algorithms have been implemented. Further, 1-layer, 2-layer, and 4-layer DNN has been implemented. The results of machine learning algorithms and DNN have been compared using recall, precision, accuracy, and F1-score. It is evident from the results that 4-layer DNN resulted in a stable and precise outcome.
Traffic Delay Analysis for Intelligent Transportation System using Deep Learning
2023-09-29
513738 byte
Conference paper
Electronic Resource
English
Traffic Flow Prediction For Intelligent Transportation System Using Machine Learning
DOAJ | 2023
|