Efficient framework for Blackspot analysis and re-route selection using RBLMCN and GPWBWO.

Vehicular traffic re-routing plays an essential role to improve mobility and mitigate accident Blackspots (BSs). In this paper, an effective technique for Blackspot Analysis and Re-route Selection utilizing Radial basis levenberg–marquardtcontext network And Good point Weighted beluga whale optimizationwith Geographic information systems (BARS-RAGWG) is proposed. This proposed technique includes some key steps. Initially, the source and destination of vehicle users are determined, and by utilizing Geographic Information Systems (GIS), routes between them are identified. Then, the data undergoes BS analysis in which accident BSs from the dataset are increased utilizing the Zeroth Order Generative Adversarial Networks (Zo-GAN) to augment the training dataset's size. Next, utilizing the K-Means Clustering (KMC) algorithm, the data is clustered based on road types. Subsequently, by using a Bayesian technique, the safety index is calculated centered on the number of accidents, types of highways, and assigned weight values. For evaluating locations as BSs, grade assignment is done utilizing fuzzy rules. By using the Radial Basis Levenberg–Marquardt Context Network (RBLMCN), the accident BSs are classified. Lastly, by utilizing Good Point Weighted Beluga Whale Optimization (GPWBWO), optimal routes are selected. As per the experimental result, the proposed approach withstands maximum accuracy than prevailing approaches. [ABSTRACT FROM AUTHOR]