A Probabilistic Method for Mining Sequential Rules from Sequences of LBS Cloaking Regions

Analyzing large-scale spatial-temporal anonymity sets can benefit many LBS applications. However, traditional spatial-temporal data mining algorithms cannot be used for anonymity datasets because the uncertainty of anonymity datasets renders those algorithms ineffective. In this paper, the authors a...

Full description

Saved in:
Bibliographic Details
Published in:International journal of data warehousing and mining 2017-01, Vol.13 (1), p.36-50
Main Authors: Zhang, Haitao, Chen, Zewei, Liu, Zhao, Zhu, Yunhong, Wu, Chenxue
Format: Article
Language:English
Subjects:
Algorithms
Data mining
Datasets
Probabilistic methods
Queries
Sequences
Series (mathematics)
Spatiotemporal data
Uncertainty
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Analyzing large-scale spatial-temporal anonymity sets can benefit many LBS applications. However, traditional spatial-temporal data mining algorithms cannot be used for anonymity datasets because the uncertainty of anonymity datasets renders those algorithms ineffective. In this paper, the authors adopt the uncertainty of anonymity datasets and propose a probabilistic method for mining sequence rules (PMSR) from sequences of LBS cloaking regions generated from a series of LBS continuous queries. The main concept of the method is that it designs a probabilistic measurement of a support value of a sequence rule, and the implementation principle of the method is to iteratively achieve sequence rules. Finally, the authors conduct extensive experiments, and the results show that, compared to the non-probabilistic method, their proposed method has a significant matching ratio when the mined sequence rules are used as predictors, while the average accuracy of the sequence rules is comparable and computing performance is only slightly decreased.
ISSN:1548-3924
1548-3932
DOI:10.4018/IJDWM.2017010102