Abstract
The design of transportation networks is generally performed on the basis of the division of a metropolitan region into communities. With the combination of the scale, population density, and travel characteristics of each community, the transportation routes and stations can be more precisely determined to meet the travel demand of residents within each of the communities as well as the transportation links among communities. To accurately divide urban communities, the original word vector sampling method is improved on the classic Deepwalk model, proposing a Random Walk (RW) algorithm in which the sampling is modified with the generalized travel cost and improved logit model. Urban spatial community detection is realized with the K-means algorithm, building the F-Deepwalk model. Using the basic road network as an example, the experimental results show that the Deepwalk model, which considers the generalized travel cost of residents, has a higher profile coefficient, and the performance of the model improves with the reduction of random walk length. At the same time, taking the Shijiazhuang urban rail transit network as an example, the accuracy of the model is further verified.