K. ANISH THEEBA AND J. ILAMCHEZHIAN
Abstract
In the area of Bioinformatics the explosion of genomic data is increasing day by day. During many years, efforts concentrated on sequencing the genome of organisms but extracting the meaningful information from the huge DNA micro array data is a crucial process. The Data Mining discovers hidden or desired pattern from such a large amount of DNA Micro array data. On the other hand discovering the hidden pattern in the big data is the most complex process. Mining frequent patterns plays an important role in the field of Data mining which deals with extraction of the desired information and knowledge from the huge size of the stored data. Association rule mining (ARM) has various techniques from extraction of data to mining. Among the existing techniques Apriori algorithm, FP (Frequent Pattern) Growth algorithm, RARM: Rapid Association Rule Mining, ECLAT algorithm, Direct Hashing and Pruning and AIS are prominent algorithms for DNA micro array data mining. These algorithms have like complexity like space and time complexity in which RARM algorithm avoids complex candidate generation process by using tree data structure and accelerates the mining process even at low support thresholds. This paper has been presented in the form of a comparative study with focus on algorithmâs weaknesses in finding Association rule.