Predicting Human Location Using Correlated Movements

Abstract

This paper aims at estimating the current location, or predicting the next location, of a person when the recent location sequence of that person is unknown. Inspired by the fact that the behavior of an individual is greatly related to other people, a two-phase framework is proposed, which first finds persons who have highly correlated movements with a person-of-interest, then estimates the person’s location based on the position information for selected persons. For the first phase, we propose two methods: community interaction similarity-based (CISB) and behavioral similarity-based (BSB). The CISB method finds persons who have similar encounters with other members in the entire community. In the BSB method, members are selected if they show similar behavioral patterns with a given person, even though there are no direct encounters or evident co-locations between them. For the second phase, a neural network is considered in order to develop the prediction model based on the selected members. Evaluation results show that the proposed prediction model under the BSB scheme outperforms other methods, achieving top-1 accuracy of 71.13% and 69.36% for estimations of current and next locations, respectively, with the MIT dataset and 92.31% and 92.03% in case of the Dartmouth dataset.