Inferring Individual Human Mobility From Sparse Check-in Data
A Temporal-Context-Aware Approach
Bibliographic Data
| ID | 22107313 |
|---|---|
| Authors | Shuai Xu (0000-0001-7919-2874, Nanjing University), Xiaoming Fu (0000-0002-8012-4753, Institute of Computer Science, University of Göttingen, Göttingen, Germany), Dechang Pi (0000-0002-6593-4563, Nanjing University of Aeronautics and Astronautics), Zhuo Ma (0009-0007-4718-8601, Jiangsu Police Officer College) |
| Year | 2024 |
| Volume | 11 |
| Issue | 1 |
| Pages | 600-611 |
| Publication date | 2024-02-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | IEEE Transactions on Computational Social Systems (JOURNAL) |
| Journal identifiers | ISSN: 2329-924X • E-ISSN: 2373-7476 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) (PUBLISHER) |
| DOI | 10.1109/tcss.2022.3231601 |
| OpenAlex | W4313270580 |
| Language | EN |
| Citations received | 5 |
| References cited | 42 |
Inferring individual human mobility at a given time is not only beneficial for personalized location-based services but also crucial for tracking trajectory of the confirmed cases in the COVID-19 pandemic. However, individual-generated trajectory data from mobile Apps are characterized by implicit feedback, which means only a few individual-location interactions can be observed. Existing studies based on such sparse trajectory data are not sufficient to infer an individual’s missing mobility in his/her historical trajectory and further predict an individual’s future mobility at a given time under a unified framework. To address this concern, in this article, we propose a temporal-context-aware framework that incorporates multiple factors to model the time-sensitive individual-location interactions in a bottom-up way. Based on the idea of feature fusion, the driving effect of heterogeneous information on an individual’s mobility is gradually strengthened, so that the temporal-spatial context when a check-in occurs can be accurately perceived. We leverage Bayesian personalized ranking (BPR) to optimize the model, where a novel negative sampling method is employed to alleviate data sparseness. Based on three real-world datasets, we evaluate the proposed approach with regard to two different tasks, namely, missing mobility inference and future mobility prediction at a given time. Experimental results encouragingly demonstrate that our approach outperforms multiple baselines in terms of two evaluation metrics. Furthermore, the predictability of individual mobility within different time windows is also revealed
Bayesian inference · Bayesian probability · Data mining · Individual mobility · Inference · Machine learning · Mobility model · Trajectory · Computer Science · Context-Aware Activity Recognition Systems · Data-Driven Disease Surveillance · Human Mobility and Location-Based Analysis · Artificial Intelligence
| Unique citing works | 5 |
|---|---|
| Citations per year | 2.5 |
| Citation span | 2024 - 2026 (3) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 5 |