5. Conclusion
In this paper, the possibility of using the genetic algorithm to solve the
dynamic shortest path problem in urban multimodal transportation networks is
investigated. The proposed approach has been tested on a dataset of a part
of Tehran. 250 pairs of points, selected randomly as the source and
destination to evaluate the algorithm, and to tune some parameters of it. The
results were divided into three main groups where path consists of one, two or
three modes of transportation. These show that the multimodal path is not
essentially the shortest one in all cases. Moreover it is concluded that
proposed algorithm has high degree of robustness since it covers monomodal
solutions as the special case of multimodal paths. The high average amount
of success rate of algorithm shows the high performance of it.