A Comparative Study of Space Search Algorithm

In this study, we propose a space search algorithm (SSA) and then introduce a hybrid optimization of ANFIS-based fuzzy  models  based  on  SSA  and  information  granulation  (IG).  In  comparison  with  conventional  evolutionary algorithms (such as PSO), SSA leads not only to better search performance to find global optimization but is also more computationally  effective.  In  the  hybrid optimization  of ANFIS-based  fuzzy  inference  system, SSA  is  exploited  to carry out the parametric optimization of the fuzzy model as well as to realize  its structural optimization. IG realized with  the  aid of C-Means  clustering helps  to determine  the  initial values of  the  apex parameters of  the membership function of  fuzzy model. The overall hybrid  identification of ANFIS-based  fuzzy models comes  in  the  form of  two optimization mechanisms: structure identification (such as the number of input variables to be used, a specific subset of input variables, the number of membership functions, and polynomial  type) and parameter identification (viz.  the apexes of membership function). The structure identification is developed by SSA and C-Means while the parameter estimation is realized via SSA and a standard least square method. The evaluation of the performance of the proposed model was carried out by using three representative numerical examples such as Non-linear function, gas furnace, and Mackey-Glass  time  series.  A  comparative  study  of  SSA  and  PSO  demonstrates  that  SSA  leads  to  improved performance both in terms of the quality of the model and the computing time required. The proposed model is also contrasted with the quality of some conventional fuzzy models already encountered in the literature.

Keywords:

en