Human mobility prediction based on turn-by-turn trajectories
完了
瀬崎 薫
Personal route prediction has emerged as an important topic within the mobility mining domain. In this context, many proposals applied an off-line learning process before being able to run the on-line prediction algorithm. The present work introduces a novel framework that integrates the route learning and the prediction algorithm in an on-line manner. By means of a thin-client and server architecture, it also puts forward a new concept for route abstraction based on the detection of spatial regions where certain routes’ velocity features frequently change. More in detail, the Complex Event Processing paradigm and the density-based clustering will be used for the route abstraction stage. In addition to that, a multigraph model will be used for the serialization of the mobility model of each user. Finally, a comparison with a well-established work of the state of the art is also devised.
変更のために新しい申請を保存します。 This will save a new application on the system for a modification.
申請中の研究者は表示されません。 / Pending researchers are not shown.
Fernando Terroso-Saenz / University of Murcia
申請中のデータセットは表示されません。 / Pending datasets are not shown.
【空間配分版】2008年東京都市圏 人の流れデータセット
年次報告の内容はメンバーのみ表示されます。