User demographic characteristics inference based on big GPS trajectory data

Li，Peiran1; Zhang，Haoran2; Li，Wenjing1; Chen，Jinyu1; Zhang，Junxiang3; Song，Xuan3; Shibasaki，Ryosuke1

2023

Demographics GPS trajectory IoT Variation inference

英语

The portable devices (e.g., mobile phones) afford a great potential to track the human mobility. But it is hard to know the demograhic characteristics of the users, due to privacy concern. In this context, our study proposed a ubiquitous Internet of Things-based trustworthy approach for trustworthy user demographic characteristics inference. First, we employed a meta-graph-based data structure to represent users' life patterns and projected them into a low-dimension space as uniform features. Then, based on the life-pattern features, we derived a variation-inference-based advanced Bayesian model to infer the demographics. Finally, taking a region in Tokyo as a case study, we compared our methods with baseline methods (heuristic algorithm, deep learning), and the result proved a superior accuracy (the MAPE improved by 0.07–0.28) as well as reliability (0.78 Pearson’s correlation coefficient with survey data).

10.1016/B978-0-443-18424-6.00007-6

Handbook of Mobility Data Mining: Volume 2: Mobility Analytics and Prediction

2

75-93

其他

2-s2.0-85159496126

Scopus

1.Center for Spatial Information Science,The University of Tokyo,Kashiwa-shi,Chiba,Japan
2.School of Urban Planning and Design,Peking University,Shenzhen,China
3.Southern University of Science and Technology,University of Tokyo Joint Research Center for Super Smart Cities,Department of Computer and Engineering,Southern University of Science and Technology,Shenzhen,Guangdong,China

Li，Peiran,Zhang，Haoran,Li，Wenjing,et al. User demographic characteristics inference based on big GPS trajectory data. 2023-01-01.