A Bitmap Approach for Mining Erasable Itemsets

Abstract

Erasable-itemset mining is a useful method of pattern extraction for helping the manager of a factory analyze production planning. The erasable itemsets derived can be considered important production information regarding how to plan the production of a factory during an economic depression or financial shortage for the manager. After the erasable-itemset mining was proposed in 2009, several efficient mining approaches for finding erasable itemsets have been developed. However, these methods require a considerable amount of execution time when the amount of product data is large. Especially, manufacturing small amounts of versatile products has been a trend today, and it will generate a large product database. In this paper, we adopt a bitmap representation for itemsets in an erasable-itemset mining algorithm to speed up the execution. Different from the traditional bitmap meaning for frequent itemsets, a bitmap for erasableitemset mining here denotes the relationship that a product includes at least one material (item) in a specified itemset. Using the bitmap representation can easily find the desired products to check, thus being able to decrease the scans of a database. Experimental evaluation on real datasets was used to compare the proposed approach with the other two approaches under different parameter values for experimental conditions. The experimental results show that the proposed approach can make a good trade-off between execution time and memory usage.INDEX TERMS Data mining, Erasable itemset mining, Bitmap representation, Product database.

An analysis and literature review of algorithms for frequent itemset mining

“…Hong et al [28] proposed a bitmap representation for itemsets in an erasable-itemset mining algorithm to speed up execution.…”

“…Hong et al [28] proposed a mining approach based on erasable-itemset algorithm. It has been based on the execution time.…”

A Fast Algorithm for Mining Top-Rank-k Erasable Closed Patterns

“…In other words, we wish to find the sets of itemsets which can best be eliminated (erased) (called EPs) so that managers can then utilize this knowledge to create a new production plan that minimizes the profit reduction. Numerous algorithms have been proposed to solve the EP mining problem, such as META [12], MEI (mining erasable itemsets) [19], EIFDD (erasable itemsets for very dense datasets) [20], pMEI (parallel mining erasable itemsets) [21], and BREM (bitmap-representation erasable mining) [22]. Several variations have also been developed, such as mining EPs with constraints [23], mining erasable closed patterns [24], mining maximal EPs [25], mining top-rank-k EPs [26,27] mining erasable patterns in incremental database [28,29], and mining EPs in data streams [30][31][32][33].…”