Smart transportation travel model based on multiple data sources fusion for defense systems

Since the 1980s, information fusion as an emerging discipline has been rapidly developed in the fields of military surveillance and defense systems, intelligent transportation and environmental monitoring. In this paper, we study the application of multi-data fusion technology to traffic flow in the context of traffic flow information fusion. Firstly, the data sources of smart highways are collected using traffic flow theory and further fused with multiple data sources using the minimum variance weighted average method. Secondly, travelers on smart highways make real-time travel decisions based on the fused information; travelers on ordinary highways select travel routes based on the previous day's road network traffic conditions and historical travel experience. In this paper, the equivalence, existence and stability conditions of the model solutions are proved using immobility theory. The final simulation results show that: the increase of road traffic behavior coefficients and the increase of perceived time errors lead the model into an unstable state; as far as the stability of the model solution is concerned, risk-averse travelers are significantly better than risk-averse travelers, and the road network formed by the fusion of traffic flows based on multi-source data is more robust. Thus, the accuracy of prediction is improved, and the prediction accuracy of the algorithm proposed in this paper reaches 96% compared with other algorithms.