Hybrid radial basis function network for classification problems

Abstract

The construction of a quality RBF Network for a specific application can be a time-consuming process as the modeler must select both a suitable set of inputs and a suitable RBF Network structure. This study proposes RBF Network hybrid learning with Particle Swarm Optimization (PSO) for better convergence, error rates and classification results. RBF Network hybrid learning involves two phases. The first phase is a structure identification. in which unsupervised learning is exploited to determine the RBF centers and widths. This is done by executing different algorithms such as k-mean clustering and standard derivation respectively. The second phase is parameters estimation. in which supervised learning is implemented to establish the connections weights between the hidden layer and the output layer. This is done by performing different algorithms such as Least Mean Squares (LMS) and gradient based methods. The results for training, testing and validation of four datasets (XOR, Balloon. Iris and Cancer) illustrate the effectiveness of PSO in enhancing RBF Network learning compared to conventional Backpropogation (BP). This study illustrates how a hybrid REF Network system can be constructed, and applies the system to a number of datasets. The utility of the resulting RBFNs on these classification problems is assessed and the results from the RFBN-PSO hybrids are shown to be competitive against the best performance on these datasets using BP.