2015 | OriginalPaper | Buchkapitel
Predicting Next Locations with Object Clustering and Trajectory Clustering
verfasst von : Meng Chen, Yang Liu, Xiaohui Yu
Erschienen in: Advances in Knowledge Discovery and Data Mining
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Next location prediction is of great importance for many location based applications. In many cases, understanding the similarity between objects and the similarity between trajectories may lead to more accurate predictions. In this paper, we propose two novel models exploiting these two types of similarities respectively. The first model, named
object-clustered Markov model
(object-MM)
, first clusters similar objects based on their spatial localities, and then builds variable-order Markov models with the trajectories of objects in the same cluster. The second model, named
trajectory-clustered Markov model
(tra-MM)
, considers the similarity between trajectories, and clusters the trajectories to form the training set used in building the Markov models. The two models are integrated to produce the final next location predictor
(objectTra-MM)
. Experiments based on a real data set demonstrate significant increase in prediction accuracy of
objectTra-MM
over existing methods.