文章基本信息

标题：Using Attribute Oriented Induction High Level Emerging Pattern (AOI-HEP) to Mine Frequent Patterns
其他标题：Using Attribute Oriented Induction High Level Emerging Pattern (AOI-HEP) to Mine Frequent Patterns
本地全文：下载
作者：Harco Leslie Hendric Spits Warnars
期刊名称：International Journal of Electrical and Computer Engineering
电子版ISSN：2088-8708
出版年度：2016
卷号：6
期号：6
页码：3037-3046
DOI：10.11591/ijece.v6i6.pp3037-3046
语种：English
出版社：Institute of Advanced Engineering and Science (IAES)
摘要：Frequent patterns in Attribute Oriented Induction High level Emerging Pattern (AOI-HEP), are recognized when have maximum subsumption target (superset) into contrasting (subset) datasets (contrasting ⊂ target) and having large High Emerging Pattern (HEP) growth rate and support in target dataset. HEP Frequent patterns had been successful mined with AOI-HEP upon 4 UCI machine learning datasets such as adult, breast cancer, census and IPUMS with the number of instances of 48842, 569, 2458285 and 256932 respectively and each dataset has concept hierarchies built from its five chosen attributes. There are 2 and 1 finding frequent patterns from adult and breast cancer datasets, while there is no frequent pattern from census and IPUMS datasets. The finding HEP frequent patterns from adult dataset are adult which have government workclass with an intermediate education (80.53%) and America as native country(33%). Meanwhile, the only 1 HEP frequent pattern from breast cancer dataset is breast cancer which have clump thickness type of AboutAverClump with cell size of VeryLargeSize(3.56%). Finding HEP frequent patterns with AOI-HEP are influenced by learning on high level concept in one of chosen attribute and extended experiment upon adult dataset where learn on marital-status attribute showed that there is no finding frequent pattern.
其他摘要：Frequent patterns in Attribute Oriented Induction High level Emerging Pattern (AOI-HEP), are recognized when have maximum subsumption target (superset) into contrasting (subset) datasets (contrasting ⊂ target) and having large High Emerging Pattern (HEP) growth rate and support in target dataset. HEP Frequent patterns had been successful mined with AOI-HEP upon 4 UCI machine learning datasets such as adult, breast cancer, census and IPUMS with the number of instances of 48842, 569, 2458285 and 256932 respectively and each dataset has concept hierarchies built from its five chosen attributes. There are 2 and 1 finding frequent patterns from adult and breast cancer datasets, while there is no frequent pattern from census and IPUMS datasets. The finding HEP frequent patterns from adult dataset are adult which have government workclass with an intermediate education (80.53%) and America as native country(33%). Meanwhile, the only 1 HEP frequent pattern from breast cancer dataset is breast cancer which have clump thickness type of AboutAverClump with cell size of VeryLargeSize(3.56%). Finding HEP frequent patterns with AOI-HEP are influenced by learning on high level concept in one of chosen attribute and extended experiment upon adult dataset where learn on marital-status attribute showed that there is no finding frequent pattern.
关键词：Computer Science; Information Technology;Data Mining; AOI-HEP; Attribute Oriented Induction; Emerging Pattern; High level Emerging Pattern; Frequent pattern; HEP Frequent pattern.