This paper combines a new dynamic neural network structure with the traditional fault detection method based on state estimation, and proposes a traffic incident detection algorithm based on dynamic neural network. This network draws on the training algorithm of static BP network, and adopts an improved algorithm to improve the training effect in view of the shortcomings of slow convergence speed and easy to fall into local minimum points in its training method. Finally, the proposed algorithm is simulated by Matlab, and satisfactory results are obtained.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore