Improved Harmony Search Algorithm And Appliation In The Attribute Reduction Of Rough Set

Many scientific, engineering and economic problems need the optimization of a set of parameters with the aim of minimizing or maximizing the objective function. The traditional sequential optimization methods exhibited their weakness to deal with complex problems. They often fail in working upon many real-world problems that usually have a large search space, multi local optimum, and even are not well-defined. Therefore, effective optimization method, harmony search algorithm, has become one of the main objectives for scientific researchers.Rough set theory has been proved to be an excellent mathematical tool dealing with uncertain and vague description of objects after vague theory and evidence theory. Finding the minimal reduction is one of the most important works in the research of rough set theory, as an important part of soft computing, attribute reduction plays applications have played an important role, especially in the areas of knowledge acquisition, machine learning, pattern recognition, decision analysis, and modeling etc. However, it has been proved that finding the minimal reductions is a NP-hard problem. The thesis studies on the rough set attribute reduction algorithm based on improved global best harmony search algorithm.Firstly, the thesis reviews the theories and methods of rough set systematically, and analyzes the algorithms of attribute reduction based on discernibility matrix, attribute significance, dependability.Secondly, the basic theory, the algorithm steps and selection parameters of harmony search algorithm are described. In the improved harmony search algorithm, two important parameters are improved, which are associated to the iterative number. In the adaptive harmony search algorithm, the two important parameters are adaptive adjusted by information in the harmony storeroom. In global best harmony search algorithm, the global information is introduced in the harmony storeroom.Thirdly, the improved global best harmony search algorithm is proposed, which is the combination of adaptive harmony search algorithm and global best harmony search algorithm. In the improved global best harmony search algorithm, the new variable is adaptive adjusted by the information in the harmony storeroom in order to avoid overlap variable and keep diversity. Furthermore, in the new variable, the global information is introduced. From the kinds of test functions, five test functions are selected, which are multimodal and complex. The simulation results show that the solution variable is converged to the best solution gradually. The new algorithm is compared with other algorithms, the results show that the new algorithmLastly, the improved global best harmony search algorithm is applied in the attribute reduction of rough set. The rough set-improved global best harmony search attribute reduction algorithm is proposed, and reduce the car decision. Compared to other algorithms, the test results show the validity and feasibility of this method.