Learning Logic Programming in Radial Basis Function Network via Genetic Algorithm

2012 ◽  
Vol 12 (9) ◽  
pp. 840-847 ◽  
Author(s):  
Nawaf Hamadneh ◽  
Saratha Sathasivam ◽  
Surafel Luleseged Tilahun ◽  
Ong Hong Choon
Keyword(s):  
Genetic Algorithm ◽  
Radial Basis Function ◽  
Logic Programming ◽  
Basis Function ◽  
Radial Basis Function Network ◽  
Radial Basis ◽  
Function Network ◽  
Learning Logic

Modelling of plasma etching process using radial basis function network and genetic algorithm

Vacuum ◽  
2005 ◽  
Vol 79 (3-4) ◽  
pp. 140-147 ◽  
Author(s):  
Dongil Han ◽  
Seung Bin Moon ◽  
Kyungyoung Park ◽  
Byungwhan Kim ◽  
Kyeong Kyun Lee ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Radial Basis Function ◽  
Plasma Etching ◽  
Basis Function ◽  
Radial Basis Function Network ◽  
Etching Process ◽  
Plasma Etching Process ◽  
Radial Basis ◽  
Function Network

PROTEIN SUPERFAMILY CLASSIFICATION USING ADAPTIVE EVOLUTIONARY RADIAL BASIS FUNCTION NETWORK

2012 ◽  
Vol 11 (04) ◽  
pp. 1250026 ◽  
Author(s):  
SWATI VIPSITA ◽  
SANTANU KU. RATH
Keyword(s):  
Genetic Algorithm ◽  
Amino Acid ◽  
Radial Basis Function ◽  
Basis Function ◽  
Radial Basis Function Network ◽  
Amino Acid Sequences ◽  
Protein Superfamily ◽  
Multiobjective Genetic Algorithm ◽  
Radial Basis ◽  
Function Network

In this paper, the concept of adaptive multiobjective genetic algorithm (AMOGA) is applied for the structure optimization of radial basis function network (RBFN). The problem of finding the number of hidden centers remains a critical issue in the design of RBFN. The number of basis function controls the complexity and generalization ability of the network. The most parsimonious network obtained from the pareto front is applied in one of the challenging research area of proteomics and computational biology: Protein superfamily classification. The problem deals with predicting the family membership of a newly discovered amino acid sequence. The modification to the earlier approach of multiobjective genetic algorithm (MOGA) is done based on the two key controlling parameters such as probability of crossover and probability of mutation. These values are adaptively varied based on the performance of the algorithm i.e., based on the percentage of total population present in the best nondomination level. Principal component analysis (PCA) is used for dimension reduction and significant features are extracted from long feature vector of amino acid sequences. Numerical simulation results illustrates the efficiency of our approach in terms of faster convergence, optimal architecture and high level of classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document