Nonlinear Calibration for Temperature Sensors Based on AGA-Least-square Support Vector Machines

The principle and the method for correcting the nonlinear errors of the sensor system with least square SVM (LS-SVM) are introduced. The basic principle of LS-SVM is presented. In order to get the optimal parameters of LS-SVM automatically, use adaptive genetic algorithm (AGA) to select parameters of LS-SVM, and use AGA-least square SVM to nonlinear calibration of temperature sensor. Experimental results show that this method has more accurate than CMAC and BP for nonlinear calibration of temperature sensor, and has parameter automatically obtain advantage. This method is very effective