内容

周晓方教授:Moving Object Linking Based on Historical Trace

阅读数:34    发布:2019-01-08 16:08    

题目: Moving Object Linking Based on Historical Trace

主讲人:周晓方

时间:2019年1月10日15:00

地点:科技楼1304

报告人简介:

image.png

周晓方博士,IEEE Fellow,澳大利亚昆士兰大学计算机科学教授、数据科学带头人,苏州大学特聘兼职教授、苏州大学先进数据分析研究中心主任,“863”主题项目首席科学家,IEEE数据工程技术委员会(TCDE)现任主席,中国计算机学会大数据专家委员会常务委员,中国中文信息学会网络空间大搜索专委会副主任。周晓方教授长期从事数据库,数据挖掘和人工智能,数据质量管理,智能搜索以及大数据管理和应用等领域的研究。曾任IEEE ICDE 2013, ACM CIKM 2016,VLDB 2020等国际一流学术会议的程序委员会主席, ACM Multimedia 2015和2017年中国大数据技术大会大会主席,WISE 2008, CIKM 2016和DEXA 2018大会主题报告人,和VLDB Journal、IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Cloud Computing等多个国际一流学术期刊编委。曾获WISE 2012,WISE 2013,ICDE 2015和DASFAA 2016等多个国际会议最佳论文奖。

Abstract—The prevalent adoption of GPS-enabled devices has witnessed a blooming of various location-based services which produce a huge amount of trajectories monitoring an individual’s movement. This triggers an interesting question: is the movement history sufficiently representative and distinctive to identify an individual? In this work, we study the problem of moving object linking based on their historical traces. However, it is non-trivial to extract effective patterns from moving history and meanwhile conduct object linking efficiently. To this end, we propose three representation strategies (i.e., sequential, temporal, and spatial) and two quantitative criteria (i.e., commonality and unicity) to construct the personalised signature from a trace. Moreover, we formalise the problem of moving object linking as a k-nearest neighbour (k-NN) search on the collection of signatures, and aim to improve efficiency considering the high dimensionality of the signature and the large cardinality of the candidate object set. A simple but effective dimension reduction strategy is introduced in this work, which empirically outperforms existing algorithms including PCA and LSH. We propose a novel indexing structure, Weighted R-tree (WR-tree), and corresponding pruning methods to further speed up k-NN search by combining both weight and spatial information contained in the signature. Our extensive experimental results on a real world dataset verify the superiority of our proposals, in terms of both accuracy and efficiency, over other state-of-the-art approaches.

 


深圳大学计算机与软件学院 2009-2016