Effective algorithms for vertical mining probabilistic frequent patterns in uncertain mobile environments
by Xiaomei Yu; Hong Wang; Xiangwei Zheng; Yilei Wang
International Journal of Ad Hoc and Ubiquitous Computing (IJAHUC), Vol. 23, No. 3/4, 2016

Abstract: Data uncertainty is inherent in mobile applications. The traditional methods of mining frequent patterns are confronted with enormous challenges in uncertain mobile environments. The present achievements have shown that vertical mining algorithms are promising in mining expected support-based frequent patterns from uncertain data, while they have not captured much attention in mining probabilistic frequent patterns. In this paper, we propose two vertical mining algorithms (UBEclat and NDUEclat) for probabilistic frequent patterns mining (FPM). The UBEclat algorithm is applied to discover exact probabilistic frequent patterns in uncertain environments, while the NDUEclat algorithm is suitable for mining probabilistic frequent patterns approximately in mobile environments with huge uncertain data. We test the two algorithms on real and synthetic datasets, and compare them with well-known FPM algorithms. The extensive evaluations show that the novel Eclat-based algorithms outperform the comparative ones in performance of efficiency and precision.

Online publication date: Mon, 26-Sep-2016

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Ad Hoc and Ubiquitous Computing (IJAHUC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com