Infrequent pattern mining in smart healthcare environment using data summarization

Mohiuddin Ahmed, Abu S.S.M. Barkat Ullah

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A summarization technique creates a concise version of large amount of data (big data!) which reduces the computational cost of analysis and decision-making. There are interesting data patterns, such as rare anomalies, which are more infrequent in nature than other data instances. For example, in smart healthcare environment, the proportion of infrequent patterns is very low in the underlying cyber physical system (CPS). Existing summarization techniques overlook the issue of representing such interesting infrequent patterns in a summary. In this paper, a novel clustering-based technique is proposed which uses an information theoretic measure to identify the infrequent frequent patterns for inclusion in a summary. The experiments conducted on seven benchmark CPS datasets show substantially good results in terms of including the infrequent patterns in summaries than existing techniques.

Original languageEnglish
Pages (from-to)5041-5059
Number of pages19
JournalJournal of Supercomputing
Volume74
Issue number10
DOIs
Publication statusPublished - 1 Oct 2018
Externally publishedYes

Fingerprint Dive into the research topics of 'Infrequent pattern mining in smart healthcare environment using data summarization'. Together they form a unique fingerprint.

Cite this