Title: Fuzzy improved firefly-based MapReduce for association rule mining
Authors: Lydia Nahla Driff; Habiba Drias
Addresses: Artificial Intelligence Laboratory (LRIA), Department of Computer Science, USTHB University, Algiers, Algeria ' Artificial Intelligence Laboratory (LRIA), Department of Computer Science, USTHB University, Algiers, Algeria
Abstract: In order to refine association rules based on frequent patterns, we advised an improved version of firefly algorithm called IFF. We had to eliminate blind mating from the design of GA and replaced it by mating between mature fireflies, while ensuring balanced convergence. The proposed approach uses advanced methods such as controlled genetic operations to manipulate frequent patterns, and the uses of fuzzy logic to control IFF parameters to assure convergence calibration, based on data size, algorithm iterations and temporary local optimum. Also, we executed IFF under Hadoop to get a MapReduce system and ensure the most optimal execution time. To analyse the quality of our proposal, we made simulations on MEDLINE dataset. Results indicate that the proposed approach is superior to existing algorithms with an accuracy of 10% to 50% and save execution time around 36%, while ensuring a good balance between the quality and variety of knowledge.
Keywords: swarm intelligence; firefly algorithm; genetic algorithm; fuzzy logic; association rules mining; ARM; frequent patterns; MapReduce; Hadoop; MEDLINE collection.
DOI: 10.1504/IJICA.2023.129376
International Journal of Innovative Computing and Applications, 2023 Vol.14 No.1/2, pp.104 - 123
Received: 02 Jan 2021
Accepted: 23 Aug 2021
Published online: 07 Mar 2023 *