Establish the Queue Length Function Model

Abstract:

A queue length function mapping model is built through the neural network, and can be optimized based on the white noise principle. Thus, a nonlinear mapping, which the input and output nodes are considered as independent variable and the dependent variable respectively, is obtained. After training the learning samples, which can be got from counting the data of the accident duration, traffic upstream, the passed coefficient, and the vehicles queue length, we can acquired the weights and thresholds, which are used to represent the mapping between the nodes. Also, through the optimization based on the white noise principle, the impact caused by the error can be reduced and a more accurate model is obtained as a predicting measuring tool of the queue length.

• Periodical: Advanced Materials Research (Volumes 962-965)
• Pages: 2691-2694
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.962-965.2691
• Online since: June 2014
• Authors: Yu Tang
• Keywords: Learning Samples, Neural Network (NN), Passed Coefficient, White Noise Principle

References

[1] Jun Wei Zhang , Wei MinDai, the role of space -based automobile road and highway vehicles equivalent conversion factor studies , in Highway and Transportation Research , Vol. 24 (2007).

[2] Cai Hong Liu, researchers BP neural network learning algorithm, Chongqing Normal University(2008).

[3] Information on http: /wenku. baidu. com/link?url=M4AhZRzj_EJ0dsrXmJzeK3LHc5yTod-GxuJvEiBkMVf8bmpuDHDpXJAm4UuXe0zAcwOfxcW1PsPo6L7tMOi2Ifl0b5kCvIy0IRID1dpxStG.

[4] Zhuojin Wu , MATLAB mathematical modeling applications, Beijing : Beijing University of Aeronautics and Astronautics Press (2011).