Complexities’ day-to-day dynamic evolution analysis and prediction for a Didi taxi trip network based on complex network theory
Authors:
- 30 March 2018
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in Modern Physics Letters B
- Vol. 32 (09)
Abstract
Didi Dache is the most popular taxi order mobile app in China, which provides online taxi-hailing service. The obtained big database from this app could be used to analyze the complexities’ day-to-day dynamic evolution of Didi taxi trip network (DTTN) from the level of complex network dynamics. First, this paper proposes the data cleaning and modeling methods for expressing Nanjing’s DTTN as a complex network. Second, the three consecutive weeks’ data are cleaned to establish 21 DTTNs based on the proposed big data processing technology. Then, multiple topology measures that characterize the complexities’ day-to-day dynamic evolution of these networks are provided. Third, these measures of 21 DTTNs are calculated and subsequently explained with actual implications. They are used as a training set for modeling the BP neural network which is designed for predicting DTTN complexities evolution. Finally, the reliability of the designed BP neural network is verified by comparing with the actual data and the results obtained from ARIMA method simultaneously. Because network complexities are the basis for modeling cascading failures and conducting link prediction in complex system, this proposed research framework not only provides a novel perspective for analyzing DTTN from the level of system aggregated behavior, but can also be used to improve the DTTN management level.Keywords
Funding Information
- National Natural Science Foundation of China (51478110)
- National Natural Science Foundation of China (51508122)
- Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX17_0144)
- Science and Technology Program of Jiangsu Province (BY2016076-05)
This publication has 26 references indexed in Scilit:
- Network analysis of China’s aviation system, statistical and spatial structureJournal of Transport Geography, 2012
- BP Neural Network of Continuous Casting Technological Parameters and Secondary Dendrite Arm Spacing of Spring SteelJournal of Iron and Steel Research International, 2011
- Predicting missing links via local informationThe European Physical Journal B, 2009
- Superfamily phenomena and motifs of networks induced from time seriesProceedings of the National Academy of Sciences, 2008
- Empirical analysis of a scale-free railway network in ChinaPhysica A: Statistical Mechanics and its Applications, 2007
- EXPRESS PASSENGER TRANSPORT SYSTEM AS A SCALE-FREE NETWORKModern Physics Letters B, 2006
- Complex Network from Pseudoperiodic Time Series: Topology versus DynamicsPhysical Review Letters, 2006
- Back-propagation algorithm which varies the number of hidden unitsNeural Networks, 1991
- An introduction to computing with neural netsACM SIGARCH Computer Architecture News, 1988
- Centrality in social networks conceptual clarificationSocial Networks, 1978