1 results listed
Accurate offline localization is a critical challenge in
IoV and Wireless Sensor Networks (WSNs), where GNSS-denied
environments, sensor noise, and computational constraints hinder
real-time positioning. This paper explores the integration of
Belief Propagation (BP) with Swarm Intelligence (SI) to enhance
localization accuracy and scalability. BP employs probabilistic
message passing to iteratively refine node positions, while SI techniques leverage adaptive optimization for faster convergence. A
mathematical model incorporating Gaussian probability updates
is implemented to manage uncertainty. Visualization experiments
illustrate how mobility, communication range, and obstacles
impact localization performance. Comparative analyses show that
the proposed BP and SI hybrid method achieves average of 98%
localization accuracy with 0.7589m RMSE, in different scenarios,
outperforming standalone SI methods. This study contributes to
next-generation IoV localization strategies, improving real-time
adaptive positioning in intelligent transportation networks.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Ossama Bin Raza
Michael Bidollahkhani
Pınar Haskul
Parisa Memarmoshref