Visual exploration of urban functions via spatio-temporal taxi OD data. (October 2018)

• Record Type: Journal Article
• Authors: Zhou, Zhiguang; Yu, Jiajun; Guo, Zhiyong; Liu, Yuhua
• Is Part Of: Journal of visual languages & computing. Volume 48(2018)
• Page Start: 169
• Page End: 177
• Publication Date: 2018-10
• Subjects: Matrix factorization -- Visual analytics -- Urban functions -- Spatio-temporal; Visual programming languages (Computer science) -- Periodicals; Visual programming (Computer science) -- Periodicals; Programming languages (Electronic computers) -- Semantics -- Periodicals; Langages de programmation visuelle -- Périodiques; Programmation visuelle -- Périodiques; Langages de programmation -- Sémantique -- Périodiques; Programming languages (Electronic computers) -- Semantics; Visual programming (Computer science); Visual programming languages (Computer science); Periodicals; Electronic journals; 005
• DOI: 10.1016/j.jvlc.2018.08.009
• Languages: English
• ISSNs: 1045-926X

Abstract

Abstract: City is a complex system containing various kinds of functional areas. They are always defined by government planning and refining based on the actual requirements of citizens, which are of significant importance to urban developments, ranging from environmental governance and rail transportation to disease prevention and public security. Taxi is a major means of urban transportation, and the taxi trips record human behaviors and mobility patterns, which offer a valuable opportunity for users to get insights into urban functions. Therefore, we propose a visual analysis system in this paper, for an insightful exploration of urban functions based on spatio-temporal taxi OD trips. First, a matrix is defined to restructure spatio-temporal attributes of taxi OD data, and a Non-negative Matrix Factorization(NMF) is applied to classify and identify urban functional areas. Then, a set of visual encodings are designed to visualize mobility patterns of urban areas with different functions, such as the radial chart, the timeline view and the force-directed view. In addition, the spatio-temporal clustering model and the visual designs are all implemented in a visualization framework, with a set of convenient interactions integrated, enabling users to quickly identify areas of different urban functions and analyze the human mobility patterns across different urban areas. Case studies based on real-world datasets and interviews with domain experts have demonstrated the effectiveness of our system.