Predicting human contacts in mobile social networks using supervised learning
Proceedings of the Fourth Annual Workshop on Simplifying Complex Networks for Practitioners
Fast track article: Predicting missing contacts in mobile social networks
Pervasive and Mobile Computing
| Hi-index | 0.00 |
Experimentally measured contact traces, such as those obtained in a conference setting by using short range wireless sensors, are usually limited with respect to the practical number of sensors that can be deployed as well as available human volunteers. Moreover, most previous experiments in this field are partial since not everyone participating in the experiment is expected to carry a sensor device. Previously collected contact traces have significantly contributed to development of more realistic human mobility models. This in turn has influenced proposed routing algorithms for Delay Tolerant Networks where human contacts play a vital role in message delivery. By exploiting time-spatial properties of contact graphs as well as popularity and social information of mobile nodes, we propose a novel method to reconstruct the missing parts of contact graphs where only a subset of nodes are able to sense human contacts.