A COMPARATIVE STUDY OF FUZZY LOGIC WITH ARTIFICIAL NEURAL NETWORKS ALGORITHMS IN CLUSTERING
G. M. Nasira, S. Ashok Kumar · 2008
Clustering technique challenges to find classes of patterns using some measure of similarity. Fuzzy clustering belongs to a group of soft computing techniques which includes Artificial Neural Networks (ANN) and Fuzzy Systems (FS). The Fuzzy K-means algorithm is one of the simplest unsupervised algorithms that solve a clustering problem. This procedure classifies a given data set through a certain number of cluster priorities. Neural network model attempts to emulate architecture and information representation scheme of the human brain. A class of NN, Self Organizing Feature Map (SOFM) is a clustering algorithm developed by Kohonen. Both Fuzzy Systems and Artificial Neural Networks have advantages when unclear or prior knowledge is required. A comparative study is proposed on clustering algorithm with FS and ANN. The various drawbacks with their performance are analyzed and therefore a combination of FS and ANN has been proposed. Thus this paper brings out the concept referred as Hybrid network or Fuzzy Artificial Neural Networks (FANN) which offers few new features to overcome the individual weakness of both the approaches.