Identifying Route Preferences over Origin-Destination Using Cellular Network Data

DOI

10.2991/csece-18.2018.9How to use a DOI?

Keywords

cellular network data; spatio-temporal data; trajectory data mining; origin-destination

Abstract

Current research on studying people's routing behavior focus on how to provide the minimum cost routes while ignore users' preference. Therefore, to analyze user's routing preference, identifying routes they actually choose is a crucial task. Cellular network data contains sufficient spatio-temporal information, which is widely used for trajectory analysis nowadays. However, it is a big challenge to extract precise trajectory from the cellular network data due to its low positioning accuracy. Compared to Density-Based Spatial Clustering of Applications with Noise algorithm, we present a Spatio-Temporal Density Clustering algorithm considering the timing sequence of the points to promote the precision of the trajectories, which aims to filter users' most probable routes with the map matching algorithm. Our approach could find out those most probable routes and the probability of each route. Finally, we experimented with real data. The results show that our approach is efficient for both extracting the probable trajectories and identifying multi-routes that users would prefer to route.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhichao Guo
AU  - Tongyu Zhu
PY  - 2018/02
DA  - 2018/02
TI  - Identifying Route Preferences over Origin-Destination Using Cellular Network Data
BT  - Proceedings of the 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018)
PB  - Atlantis Press
SP  - 40
EP  - 44
SN  - 2352-538X
UR  - https://doi.org/10.2991/csece-18.2018.9
DO  - 10.2991/csece-18.2018.9
ID  - Guo2018/02
ER  -