Efficient Parallel Memetic Algorithm to Rule Extraction in Data Mining

Abstract This is extension of my last publication [1] with more expermetation to explain how I choseed every variable in each algorithm and to present more clear results and discussions. we presents a parallel memetic algorithm (PMA) for solving the classification problem in the process of Data Mining. We focus our interest on accelerating the PMA. In most parallel algorithms, the tasks performed by different processors need access to shared data, this creates a need for communication, which in turn slows the performance of the PMA. In this work, the design of PMA with new replacement approach is presented.. This latter is a hybrid approach that uses both Lamarckian and Baldwinian approaches at the same time in order to reduce the quantity of information exchanged between processors and consequently to improve the speedup of the proposed algorithm. An extensive experimental study performed on the UCI Benchmarks proves the efficiency of the proposed PMA.