Current studentsExisting staffContact us
 

On prediction of user destination by sub-trajectory understanding: a deep learning based approach

Simple item page
dc.contributor.authorZhao, J.
dc.contributor.authorXu, J.
dc.contributor.authorZhou, R.
dc.contributor.authorZhao, P.
dc.contributor.authorLiu, C.
dc.contributor.authorZhu, F.
dc.contributor.conferenceACM International Conference on Information and Knowledge Management (CIKM) (22 Oct 2018 - 26 Oct 2018 : Torino, Italy)
dc.contributor.editorCuzzocrea, A.
dc.contributor.editorAllan, J.
dc.contributor.editorPaton, N.
dc.contributor.editorSrivastava, D.
dc.contributor.editorAgrawal, R.
dc.contributor.editorBroder, A.
dc.contributor.editorZaki, M.
dc.contributor.editorCandan, S.
dc.contributor.editorLabrinidis, A.
dc.contributor.editorSchuster, A.
dc.contributor.editorWang, H.
dc.date.issued2018
dc.description.abstractDestination prediction is known as an important problem for many location based services (LBSs). Existing solutions generally apply probabilistic models to predict destinations over a sub-trajectory, but their accuracies in fine-granularity prediction are always not satisfactory due to the data sparsity problem. This paper presents a carefully designed deep learning model called TALL model for destination prediction. It not only takes advantage of the bidirectional Long Short-Term Memory (LSTM) network for sequence modeling, but also gives more attention to meaningful locations that have strong correlations w.r.t. destination by adopting attention mechanism. Furthermore, a hierarchical model that explores the fusion of multi-granularity learning capability is further proposed to improve the accuracy of prediction. Extensive experiments on Beijing and Chengdu real datasets finally demonstrate that our proposed models outperform existing methods without considering external features.
dc.description.statementofresponsibilityJing Zhao, Jiajie Xu, S, Rui Zhou, Pengpeng Zhao, Chengfei Liu, Feng Zhu
dc.identifier.citationCIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018 / Cuzzocrea, A., Allan, J., Paton, N., Srivastava, D., Agrawal, R., Broder, A., Zaki, M., Candan, S., Labrinidis, A., Schuster, A., Wang, H. (ed./s), pp.1413-1422
dc.identifier.doi10.1145/3269206.3271708
dc.identifier.isbn9781450360142
dc.identifier.orcidZhou, R. [0000-0001-6807-4362]
dc.identifier.urihttp://hdl.handle.net/2440/120136
dc.language.isoen
dc.publisherAssociation for Computing Machinery (ACM)
dc.publisher.placeNew York
dc.relation.granthttp://purl.org/au-research/grants/arc/DP160102412
dc.relation.granthttp://purl.org/au-research/grants/arc/DP170104747
dc.relation.granthttp://purl.org/au-research/grants/arc/DP180100212
dc.rights© 2018 Association for Computing Machinery
dc.source.urihttps://doi.org/10.1145/3269206.3271708
dc.subjectTrajectory prediction; trajectory embedding; deep learning
dc.titleOn prediction of user destination by sub-trajectory understanding: a deep learning based approach
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications