parallelization

One of the most famous algorithms in the field of focused exploration of data mining correlation rules is the Apriori algorithm and its many developed versions. But what can be raised as a major challenge in this field is the proper application of this algorithm in the distributed environments of today's world. In this research, a parallelization-based approach is proposed to improve the performance of the Apriori algorithm in the process of exploring recurring patterns on network topologies. The proposed approach includes two major features: (1) combining the node centrality criterion and the Apriori algorithm to identify frequent patterns, (2) using the mapping/reduction method in order to create parallel processing and achieve optimal values in the shortest time. Also, this approach pursues three main goals: reducing the temporal and spatial complexity of the Apriori algorithm, improving the process of extracting dependency rules and identifying recurring patterns, comparing the performance of the proposed approach on different network topologies in order to determine the advantages and disadvantages of each topology. To prove the superiority of the proposed method, a comparison has been made between our approach and the basic Apriori algorithm. The evaluation results of the methods prove that the proposed approach provides an acceptable performance in terms of execution time criteria compared to other methods.

An ecient parallel strategy is presented for optimization of the aerodynamic shapes using Genetic Algorithm (GA). The method is a hybrid Parallel Genetic Algorithm (PGA) that combines a multi-population PGA and master-slave PGA using Message Passing Interface. GA parameters are rstly tuned according to the fact that subpopulations evolve independently. The e ect of the number of sub-population on the computational time is investigated. Finally, a new strategy is presented based on the load balancing that aims to decrease the idle time of the processors. The algorithm is used for optimization of a transonic airfoil. An unstructured grid nite volume ow solver is utilized for objective function evaluations. For the considered class of problems, the suggested Hierarchical Parallel Genetic Algorithm (HPGA) results in more than 30% reduction in optimization time in comparison to regular master-slave PGA. A semi-liner speed-up is also obtained which indicates that the model is suited for modern cluster work stations.