Analysis of Improved TDTR Algorithm for Mining Frequent Itemsets using Dengue Virus Type 1 Dataset: A Combined Approach

摘要

Association rule mining is the recent data mining research. We have presented an approach for mining frequent itemsets using dengue virus type-1 data set. This paper proposes an Improved Two Dimensional Transaction Reduction (ITDTR) algorithm which is a combined approach of transaction reduction and sampling in bio data mining. This system produces the same frequent item sets as produced from Apriori algorithm and FP-Growth algorithm with the higher performance. This system reveals that Glycine(G), Leucine(L), Serine(S), Lysine(K), Phenylalanine(F) are the dominating amino acids in dengue virus type-1 data set with higher accuracy and efficiency. The efficiency of this algorithm is compared with Apriori algorithm, FP-Growth algorithm, Genetic algorithm and TDTR algorithm which we have implemented in our previous research work.