期刊名称:International Journal of Computer Science and Information Technologies
电子版ISSN:0975-9646
出版年度:2015
卷号:6
期号:6
页码:5552-5557
出版社:TechScience Publications
摘要:Pattern mining is a data mining method thatinvolves finding existing patterns in data. The main objectiveis to uncover the hidden regularities in the data. Until nowmost of the research in pattern mining has been exclusivelyfocused on frequent item set, however in some situation it isinteresting to find patterns that are rare instead of frequent orpatterns that reflect a negative co relation between items.These patterns are referred to as rare and negative patterns.For example in jewellery sales data, sales of diamond watchesare rare however patterns involving the selling of diamondwatches could be interesting. Rare items occur rarely but areof special interest as they may highlight exceptional behaviourin the data which is likely of interest. It tries to capturepatterns that involve events that are unusual in the data set.This research proposes that in some domain such as medicaldatabases, computer security, rare items are of higherimportance than frequent one. This research investigates otherkind of knowledge that is not usually discovered usingfrequent item-set mining i.e. rare item-sets and non-presentitem-sets. In order to mine rare and non-present item-sets, wemethodologically extract the principles behind Aprioriapproach, and then generalize it in such a way it can not onlybe applied to mine frequent item-sets but also to mine othercategories of patterns such as rare and non-present item-sets.Our goal is to apply the principle of the Apriori approach usedfor frequent item-set mining and apply it to rare and nonpresentitem-set mining. The proposed approach is able to findthe whole rare item set and at the same time pruning out thezero itemset.We will be using the concept of minimal rare itemset (MRI) to generate strong Rare Association rules with highconfidence and low support. The MRI will act as a generator,based on which valid rare association rule will be generated