An auxiliary optimization method for complex public transit route network based on link prediction
| Autor: | Lin Zhang, Qian Wan, Xianfei Yue, Jialin Zhou, Jian Lu, Yunxuan Li |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
business.industry
Computer science Statistical and Nonlinear Physics Condensed Matter Physics computer.software_genre 01 natural sciences 010305 fluids & plasmas Set (abstract data type) Identification (information) Public transport 0103 physical sciences Data mining 010306 general physics Link (knot theory) business Spurious relationship computer Clustering coefficient |
| Zdroj: | Modern Physics Letters B. 32:1850066 |
| ISSN: | 1793-6640 0217-9849 |
| DOI: | 10.1142/s0217984918500665 |
| Popis: | Inspired by the missing (new) link prediction and the spurious existing link identification in link prediction theory, this paper establishes an auxiliary optimization method for public transit route network (PTRN) based on link prediction. First, link prediction applied to PTRN is described, and based on reviewing the previous studies, the summary indices set and its algorithms set are collected for the link prediction experiment. Second, through analyzing the topological properties of Jinan’s PTRN established by the Space R method, we found that this is a typical small-world network with a relatively large average clustering coefficient. This phenomenon indicates that the structural similarity-based link prediction will show a good performance in this network. Then, based on the link prediction experiment of the summary indices set, three indices with maximum accuracy are selected for auxiliary optimization of Jinan’s PTRN. Furthermore, these link prediction results show that the overall layout of Jinan’s PTRN is stable and orderly, except for a partial area that requires optimization and reconstruction. The above pattern conforms to the general pattern of the optimal development stage of PTRN in China. Finally, based on the missing (new) link prediction and the spurious existing link identification, we propose optimization schemes that can be used not only to optimize current PTRN but also to evaluate PTRN planning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|