Summary
International Symposium on Nonlinear Theory and Its Applications
2016
Session Number:A2L-D
Session:
Number:A2L-D-6
Speeding Up of the Traffic Congestion Mitigation by Stochastic Optimization in Deep Learning
Shinnnosuke Nakamura, Takumi Uemura, Gou Koutaki, Keiichi Uchimura,
pp.-
Publication Date:2016/11/27
Online ISSN:2188-5079
Summary:
In recent years, many researchers are interested in method of mitigating traffic congestion by optimizing the parameters of the traffic signals. In oder to mitigate traffic congestion in widespread area, Nishihara et al. proposed the mitigation method of traffic congestion using both the advanced Generic Algorithm and traffic simulator. However, this method is very time consum to simulate traffic flow. In this study, we proposed the method that shorten processing time by the simulator with learning machine.