Uncovering High Average Utility Rare Itemsets in Uncertain Databases

Author:

S Nandhini S1,S Kannimuthu2

Affiliation:

1. Bannari Amman Institute of Technology

2. Karpagam College of Engineering

Abstract

Abstract High Utility Itemset Mining (HUIM) is very crucial mining process in the field of data mining because of its wide range applications apart from market analysis. But HUIM often mines lengthier itemsets as high utility itemset though it is not and the shorter valuable itemsets are left unidentified. High Average Utility Itemset Mining (HAUIM) overcomes the drawback of HUIM and mines the valuable itemsets based on their true values rather than getting affected because of the length or the number of items in the itemset. The proposed algorithm, mines High Average Utility Rare Itemset using the Multi-Objective Evolutionary Algorithm (HAURI-MOEA/D) based on the decomposition technique. Mining rate itemset holds an important insight in many applications like detecting anomalies, market differentiation, healthcare, scientific research and much more. This work aims at mining such unique rate itemsets with high average utility from the uncertain database. The uncertainty in the database here refers to the dynamic nature of the utility associated with each unique item in the dataset. In real world data, the utility of the items will vary time to time and the same has been considered as uncertainty in this work. The proposed algorithm is compared with other multi-objective algorithms to mine rare HAUIs and it is proved that the proposed algorithm performs well in terms of Hypervolume, Coverage and Generational Distance.

Publisher

Research Square Platform LLC

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3