AN IMPROVED FUZZY C-MEANS CLUSTERING ALGORITHM FOR RBF NETWORKS

Journal Title: Advance Research Journal of Multidisciplinary Discoveries - Year 2018, Vol 31, Issue 31

Abstract

In fuzzy C-means (FCM) clustering, each data point belongs to a cluster to a degree specified by a membership grade. FCM partitions a collection of vectors in c fuzzy groups and finds a cluster center in each group such that the dissimilarity measure is minimized. This paper presented a training algorithm for the radial basis function (RBF) network using improved Fuzzy C-means (IFCM) clustering method which is the modified version of FCM clustering method based on weight readjustment for each attributed.The training algorithm which uses IFCM clustering method to train the network gain better accuracy in predictions and reduced network architecture compared to the standard RBF networks. The proposed training algorithm was implemented with RBF networks in MATLAB, therefore the new network will undergo a hybrid learning process. The networks called improved Fuzzy C-means Clustering–Radial Basis Function Network (IFCM/RBF) was tested against the standard RBF network and the networks called standard Fuzzy C-means Clustering-RBF network (FCM/RBF) in predictions. The experimental models were tested on three real world application problems, particularly in Air pollutant problem, Biochemical Oxygen Demand (BOD) problem, and Phytoplankton problem, which yield promising results.

Authors and Affiliations

Dr. Lim Eng Aik, Tan Wei Hong, Ahmad Kadri Junoh

Keywords

Related Articles

EMMA BY JANE AUSTEN : A BEAUTIFUL PICTURE OF IMPERFECTION

Throughout history, different approaches dealing with the concept of beauty have been made and various aesthetic currents have occurred to analyze its manifestations. Some of these currents have defended the possibility...

Synthesis, Characterization, and Biological Activity of some Mixed-Ligands Vital Metal Complexes of Levofloxacin as Potential Medical Agents

Two series of mixed-ligands metal complexes of Fe(III), Ni(II), Cu(II) and Zr(IV) based on levofloxacin as primary ligand, 8-hydroxyquinolene and 1,10-phenanthroline as secondary ligands were prepared and characterized b...

Sacred Forests in the Western Highlands-Cameroon : Ethnobotany Role and Indigenous Conservation of Biodiversity.

Deforestation in tropic and sub-tropical regions can be attributed to the change in land use system from forests to agriculture and industrialization. The social and scientific role of Ethnobotany are becoming more consi...

Patient Satisfaction with the Facilities of Pre-Operative Anesthesia Evaluations Clinics

Objective: The aim of the study was to measure the satisfaction of patients with the facilities of pre-operative anesthesia evaluations clinics by using questionnaire. Methodology: This study is a descriptive analytical...

Control the movement of nodes for sensor networks and simulate the state of contract failure.

In sensor networks, the data is transmitted through a set of nodes spread over a specific area where the sensor is monitored and the specific state of the nodes is assembled to be in a fixed position. Because of the deve...

Download PDF file
  • EP ID EP424995
  • DOI -
  • Views 93
  • Downloads 0

How To Cite

Dr. Lim Eng Aik, Tan Wei Hong, Ahmad Kadri Junoh (2018). AN IMPROVED FUZZY C-MEANS CLUSTERING ALGORITHM FOR RBF NETWORKS. Advance Research Journal of Multidisciplinary Discoveries, 31(31), 1-5. https://europub.co.uk/articles/-A-424995