文章 | 地址 | 天数 | 大小 |
Human Mobility Modeling at Metropolitan Scales (MobiSys ’12) | NY & LA | 91 | 585K users |
Identifying important places in people’s lives from cellular network data. In International Conference on Pervasive Computing. 2011 | NY & LA | 78 | 168K users |
Ranges of human mobility in Los Angeles and New York? 2011 | NY & LA | 140 | 352K users |
Dp-where: Differentially private modeling of human mobility. In 2013 IEEE international conference on big data 2013 | New York | 91 | 250K users |
Identifying user habits through data mining on call data records. Engineering Applications of Artificial Intelligence 54 (2016), | Ivory Coast | 150 | 50K users |
Urban computing using call detail records: mobility pattern mining, next-location prediction and location recommendation. Ph.D. Dissertation. 2016 | China | — | 100K users |
Human Habits Investigation: from Mobility Reconstruction to Mobile Traffic Prediction. Ph.D. Dissertation. 2018 | Shanghai | 14 | 642K users |
Activity-based human mobility patterns inferred from mobile phone data: A case study of Singapore. IEEE Transactions on Big Data 3, 2 (2017) | Singapore | 14 | 3.17M users |
CellTrans: Private Car or Public Transportation? Infer Users’ Main Transportation Modes at Urban Scale with Cellular Data. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 3, 3, Article 125 (Sept. 2019), | Shenyang & Dalian | 48 | 3M users |
Estimating travel time of Dhaka city from mobile phone call detail records. In Proceedings of the Ninth International Conference on Information and Communication Technologies and Development. 2017 | Dhaka City | 30 | 2.87M users |
Clustering weekly patterns of human mobility through mobile phone data. IEEE Transactions on Mobile Computing 17, 4 (2017) | Paris | 21 | 800M records |
MultiCell: Urban Population Modeling Based on Multiple Cellphone Networks. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2, 3, Article 106 (Sept. 2018) | Shenzhen | — | 10.2M records |
Mobile edge computing-based data-driven deep learning framework for anomaly detection. IEEE Access 7 (2019) | Milan | 60 | 319M records |
Learning Behavioral Representations of Human Mobility 2020 | Italy | 67 | 17K trajectories |
Table 1. Related Work Using Cellphone Billing Records (CBR) Name Location # Days Volume
采用两个步骤来估计未观察阶段的旅行时间
【我们想要找到最佳的旅行时间分布参数(每个边的平均旅行时间和方差),使得观测到的总旅行时间(𝜏)出现的概率最大】