Distributed mining of significant frequent colossal closed itemsets from long biological dataset

Abstract

Mining colossal itemsets have gained more attention in recent times. An extensive set of short and average sized itemsets do not confine complete and valuable information for decision making. But, the traditional itemset mining algorithms expend a gigantic measure of time in mining these little and average sized itemsets. Colossal itemsets are very significant for numerous applications including the field of bioinformatics and are influential during the decision making. The new mode of dataset known as long biological dataset was contributed by Bioinformatics. These datasets are high dimensional datasets, which are depicted by an expansive number of features (attributes) and a less number of rows (samples). Extracting huge amount of information and knowledge from high dimensional long biological dataset is a nontrivial task. The existing algorithms are computationally expensive and sequential in mining significant Frequent Colossal Closed itemsets (FCCI) from long biological dataset. Distributed computing is a good strategy to overcome the inefficiency of the existing sequential algorithm. The paper proposes a distributed computing approach for mining FCCI. The row enumerated mining search space is efficiently cut down by pruning strategy enclosed in Distributed Row Enumerated Frequent Colossal Closed Itemset Mining (DREFCCIM) algorithm. The proposed DREFCCIM algorithm is the first distributed algorithm to mine FCCI from long biological dataset. The experimental results demonstrate the efficient performance of the DREFCCIM algorithm in comparison to the current algorithms.