Semantic-aware query processing for activity trajectories

Huiwen Liu, Jiajie Xu, Kai Zheng, Chengfei Liu, Lan Du, Xian Wu

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    Abstract

    Nowadays, users of social networks like tweets and weibo have generated massive geo-tagged records, and these records reveal their activities in the physical world together with spatio-temporal dynamics. Existing trajectory data management studies mainly focus on analyzing the spatio-temporal properties of trajectories, while leaving the understanding of their activities largely untouched. In this paper, we incorporate the semantic analysis of the activity information embedded in trajectories into query modelling and processing, with the aim of providing end users more accurate and meaningful trip recommendations. To this end, we propose a novel trajectory query that not only considers the spatio-temporal closeness but also, more importantly, leverages probabilistic topic modelling to capture the semantic relevance of the activities between data and query. To support efficient query processing, we design a novel hybrid index structure, namely ST-tree, to organize the trajectory points hierarchically, which enables us to prune the search space in spatial and topic dimensions simultaneously. The experimental results on real datasets demonstrate the efficiency and scalability of the proposed index structure and search algorithms.

    Original languageEnglish
    Title of host publicationWSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining
    Subtitle of host publicationFebruary 6–10, 2017, Cambridge, United Kingdom
    EditorsAndrew Tomkins, Min Zhang
    Place of PublicationNew York, New York
    PublisherAssociation for Computing Machinery (ACM)
    Pages283-292
    Number of pages10
    ISBN (Electronic)9781450346757
    DOIs
    Publication statusPublished - 2 Feb 2017
    Event10th ACM International Conference on Web Search and Data Mining - Cambridge, United Kingdom
    Duration: 6 Feb 201710 Feb 2017
    Conference number: 10

    Conference

    Conference10th ACM International Conference on Web Search and Data Mining
    Abbreviated titleWSDM 2017
    CountryUnited Kingdom
    CityCambridge
    Period6/02/1710/02/17

    Keywords

    • Activity trajectories query
    • Semantic relevance
    • Spatial keywords

    Cite this

    Liu, H., Xu, J., Zheng, K., Liu, C., Du, L., & Wu, X. (2017). Semantic-aware query processing for activity trajectories. In A. Tomkins, & M. Zhang (Eds.), WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining: February 6–10, 2017, Cambridge, United Kingdom (pp. 283-292). New York, New York: Association for Computing Machinery (ACM). https://doi.org/10.1145/3018661.3018678
    Liu, Huiwen ; Xu, Jiajie ; Zheng, Kai ; Liu, Chengfei ; Du, Lan ; Wu, Xian. / Semantic-aware query processing for activity trajectories. WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining: February 6–10, 2017, Cambridge, United Kingdom. editor / Andrew Tomkins ; Min Zhang. New York, New York : Association for Computing Machinery (ACM), 2017. pp. 283-292
    @inproceedings{0007d1e9cbf5495981866c00bf9714d9,
    title = "Semantic-aware query processing for activity trajectories",
    abstract = "Nowadays, users of social networks like tweets and weibo have generated massive geo-tagged records, and these records reveal their activities in the physical world together with spatio-temporal dynamics. Existing trajectory data management studies mainly focus on analyzing the spatio-temporal properties of trajectories, while leaving the understanding of their activities largely untouched. In this paper, we incorporate the semantic analysis of the activity information embedded in trajectories into query modelling and processing, with the aim of providing end users more accurate and meaningful trip recommendations. To this end, we propose a novel trajectory query that not only considers the spatio-temporal closeness but also, more importantly, leverages probabilistic topic modelling to capture the semantic relevance of the activities between data and query. To support efficient query processing, we design a novel hybrid index structure, namely ST-tree, to organize the trajectory points hierarchically, which enables us to prune the search space in spatial and topic dimensions simultaneously. The experimental results on real datasets demonstrate the efficiency and scalability of the proposed index structure and search algorithms.",
    keywords = "Activity trajectories query, Semantic relevance, Spatial keywords",
    author = "Huiwen Liu and Jiajie Xu and Kai Zheng and Chengfei Liu and Lan Du and Xian Wu",
    year = "2017",
    month = "2",
    day = "2",
    doi = "10.1145/3018661.3018678",
    language = "English",
    pages = "283--292",
    editor = "Tomkins, {Andrew } and Zhang, {Min }",
    booktitle = "WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining",
    publisher = "Association for Computing Machinery (ACM)",
    address = "United States of America",

    }

    Liu, H, Xu, J, Zheng, K, Liu, C, Du, L & Wu, X 2017, Semantic-aware query processing for activity trajectories. in A Tomkins & M Zhang (eds), WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining: February 6–10, 2017, Cambridge, United Kingdom. Association for Computing Machinery (ACM), New York, New York, pp. 283-292, 10th ACM International Conference on Web Search and Data Mining, Cambridge, United Kingdom, 6/02/17. https://doi.org/10.1145/3018661.3018678

    Semantic-aware query processing for activity trajectories. / Liu, Huiwen; Xu, Jiajie; Zheng, Kai; Liu, Chengfei; Du, Lan; Wu, Xian.

    WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining: February 6–10, 2017, Cambridge, United Kingdom. ed. / Andrew Tomkins; Min Zhang. New York, New York : Association for Computing Machinery (ACM), 2017. p. 283-292.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    TY - GEN

    T1 - Semantic-aware query processing for activity trajectories

    AU - Liu, Huiwen

    AU - Xu, Jiajie

    AU - Zheng, Kai

    AU - Liu, Chengfei

    AU - Du, Lan

    AU - Wu, Xian

    PY - 2017/2/2

    Y1 - 2017/2/2

    N2 - Nowadays, users of social networks like tweets and weibo have generated massive geo-tagged records, and these records reveal their activities in the physical world together with spatio-temporal dynamics. Existing trajectory data management studies mainly focus on analyzing the spatio-temporal properties of trajectories, while leaving the understanding of their activities largely untouched. In this paper, we incorporate the semantic analysis of the activity information embedded in trajectories into query modelling and processing, with the aim of providing end users more accurate and meaningful trip recommendations. To this end, we propose a novel trajectory query that not only considers the spatio-temporal closeness but also, more importantly, leverages probabilistic topic modelling to capture the semantic relevance of the activities between data and query. To support efficient query processing, we design a novel hybrid index structure, namely ST-tree, to organize the trajectory points hierarchically, which enables us to prune the search space in spatial and topic dimensions simultaneously. The experimental results on real datasets demonstrate the efficiency and scalability of the proposed index structure and search algorithms.

    AB - Nowadays, users of social networks like tweets and weibo have generated massive geo-tagged records, and these records reveal their activities in the physical world together with spatio-temporal dynamics. Existing trajectory data management studies mainly focus on analyzing the spatio-temporal properties of trajectories, while leaving the understanding of their activities largely untouched. In this paper, we incorporate the semantic analysis of the activity information embedded in trajectories into query modelling and processing, with the aim of providing end users more accurate and meaningful trip recommendations. To this end, we propose a novel trajectory query that not only considers the spatio-temporal closeness but also, more importantly, leverages probabilistic topic modelling to capture the semantic relevance of the activities between data and query. To support efficient query processing, we design a novel hybrid index structure, namely ST-tree, to organize the trajectory points hierarchically, which enables us to prune the search space in spatial and topic dimensions simultaneously. The experimental results on real datasets demonstrate the efficiency and scalability of the proposed index structure and search algorithms.

    KW - Activity trajectories query

    KW - Semantic relevance

    KW - Spatial keywords

    UR - http://www.scopus.com/inward/record.url?scp=85015263573&partnerID=8YFLogxK

    U2 - 10.1145/3018661.3018678

    DO - 10.1145/3018661.3018678

    M3 - Conference Paper

    SP - 283

    EP - 292

    BT - WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining

    A2 - Tomkins, Andrew

    A2 - Zhang, Min

    PB - Association for Computing Machinery (ACM)

    CY - New York, New York

    ER -

    Liu H, Xu J, Zheng K, Liu C, Du L, Wu X. Semantic-aware query processing for activity trajectories. In Tomkins A, Zhang M, editors, WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining: February 6–10, 2017, Cambridge, United Kingdom. New York, New York: Association for Computing Machinery (ACM). 2017. p. 283-292 https://doi.org/10.1145/3018661.3018678