Towards a hybrid optimization model for elemental content analysis in EDXRF

This paper presents a hybrid optimization model for predicting the elemental contents such as Ti, V and Fe in energy dispersive X-ray fluorescence (EDXRF) based on least square support vector machine (LS-SVM) and particle swarm optimization (PSO) methods. The model used PSO to optimize LS-SVM parameters. In order to assess the capability and effectiveness of the proposed model, several measurement methods such as SVM model and BP neural network model were compared. The results indicate that the proposed model is feasible for quantitative analysis of elemental contents in nondestructive nuclear measurement applications.