Table of Contents Author Guidelines Submit a Manuscript
Computational Intelligence and Neuroscience
Volume 2014, Article ID 363502, 11 pages
Research Article

A Framework for Spatial Interaction Analysis Based on Large-Scale Mobile Phone Data

Key Laboratory of Road and Traffic Engineering of the Ministry of Education, 4800 Cao’an Road, Tongji University, Jiading District, Shanghai 201804, China

Received 12 July 2014; Accepted 5 October 2014; Published 4 November 2014

Academic Editor: Xiaobei Jiang

Copyright © 2014 Weifeng Li et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


The overall understanding of spatial interaction and the exact knowledge of its dynamic evolution are required in the urban planning and transportation planning. This study aimed to analyze the spatial interaction based on the large-scale mobile phone data. The newly arisen mass dataset required a new methodology which was compatible with its peculiar characteristics. A three-stage framework was proposed in this paper, including data preprocessing, critical activity identification, and spatial interaction measurement. The proposed framework introduced the frequent pattern mining and measured the spatial interaction by the obtained association. A case study of three communities in Shanghai was carried out as verification of proposed method and demonstration of its practical application. The spatial interaction patterns and the representative features proved the rationality of the proposed framework.