| NUKLEONIKA 2011, 56(4):323-332
A REAL-VALUED GENETIC ALGORITHM TO OPTIMIZE
THE PARAMETERS OF SUPPORT VECTOR MACHINE
FOR CLASSIFICATION OF MULTIPLE FAULTS IN NPP
Fathy Z. Amer1, Ahmed M. El-Garhy1, Medhat H. Awadalla1, Samia M. Rashad2,
Asmaa K. Abdien2
1 Faculty of Engineering, Department of Electronics, Communications
and Computers,
Helwan University, Helwan Governerate, Helwan, Egypt
2 Emergency Control Center (ECC), 3 Ahmed el-Zomor, Nasr city, Cairo, Egypt
Two parameters, regularization parameter c, which determines the trade off cost between minimizing the training error and minimizing the complexity of the model and parameter sigma of the kernel function which defines the non-linear mapping from the input space to some high-dimensional feature space, which constructs a non-linear decision hyper surface in an input space, must be carefully predetermined in establishing an efficient support vector machine (SVM) model. Therefore, the purpose of this study is to develop a genetic-based SVM (GASVM) model that can automatically determine the optimal parameters, c and sigma, of SVM with the highest predictive accuracy and generalization ability simultaneously. The GASVM scheme is applied on observed monitored data of a pressurized water reactor nuclear power plant (PWRNPP) to classify its associated faults. Compared to the standard SVM model, simulation of GASVM indicates its superiority when applied on the dataset with unbalanced classes. GASVM scheme can gain higher classification with accurate and faster learning speed.
Close X |