Exploiting parallel graphics processing units to improve association rule mining in transactional databases using butterfly optimization algorithm

Extracting association rules from huge amounts of data is an essential method in data mining that can provide valuable knowledge from datasets for various applications. In addition to a variety of traditional and parallel association rule mining (ARM) methods, some studies have also been represented in the literature to extract association rules from datasets using multi-core processors combining GPU-CPU (graphics processing unit-central processing unit) and FPGA-CPU (field programmable gate array-central processing unit). These parallel methods have been utilized to speed up the process of ARM, including its major phase, frequent itemset mining (FIM). The use of multiple GPUs for ARM and FIM has been usually in the cluster form, and the simultaneous use of multiple GPUs on a single system has not been extensively used to extract the set of association rules. Due to the huge volume of big data, finding more efficient and faster ARM and FIM methods is still of interest to researchers. In this paper, the butterfly optimization algorithm (BOA), which has an acceptable accuracy and speed in solving optimization problems, is used for ARM. In this study, an efficient platform including a single CPU and three parallel GPUs are employed to parallelize ARM using BOA. The main feature of the proposed method is the use of parallel GPUs on a single computer, to speed up the process, and the use of the CPU as a synchronizer. Since the GPUs reduce the runtime by executing similar duplicate structures, the proposed model speeds up the mining process and prevents computing overload on the CPU. All three phases of the algorithm are implemented on the parallel graphics cards to increase the performance. The evaluation of the proposed method and its comparison with the BSO- and GBSO-Miner methods show its better performance in terms of accuracy and execution time.