Waterbus route optimization by pittsburgh-style Learning Classifier System
暂无分享,去创建一个
When a disaster occurs in the city center and roads and railroads etc. become unable to use, the waterbus has the great potential vehicles to transport passengers and several supplies. Since the number of passengers in such situation tend to change, according to the reconstruction degree of the city, effective and robust routes that can use two or more situations. To obtain such routes, this paper focuses on effective key routes to various situations, and proposes the method that put the pressure which decreases the number of routes. Through intensive simulations of five river stations, the following implications have been revealed, we get the routes which can transport passengers earlier than the case of not putting decreasing pressure of waterbus rout.
[1] Jaume Bacardit Peñarroya. Pittsburgh genetic-based machine learning in the data mining era: representations, generalization, and run-time , 2004 .
[2] T. Mahnig,et al. A new adaptive Boltzmann selection schedule SDS , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).