CBW_CRNet: Chebyshev Beluga Whale Optimization based Convolutional Recurrent Network for Vehicle Positioning and Tracking for 6G Networks

Accurate vehicle positioning and tracking are considered as the fundamental aspect for the seamless operation of intelligent transport system. It is accomplished through the vehicle detection and tracking mechanism. There is several issue in detecting the vehicle due to the environmental aspects. Thus, this research introduces novel deep learning methods for vehicle positioning and tracking by considering received signal strength, angle of arrival and time of flight. The vehicle positioning and tracking is devised using the proposed Chebyshev Beluga Whale Optimization based Convolutional Recurrent Network (CBW_CRNet) Model. The hybrid convolutional network and long short-term memory (LSTM) based recurrent network are used to develop the suggested vehicle positioning and tracking model. The Chebyshev Beluga Whale (CBW) optimization technique is used to optimize the loss function. Based on accuracy, precision, recall, F1-Score, and error, the suggested CBW_CRNet analysis yielded results of 98.4, 98.3, 98.5, 98.14, and 1.6, respectively.