Nonlinear multifunctional sensor signal reconstruction based on least squares support vector machines and total least squares algorithm

Least squares support vector machines （LS-SVMs） are modified support vector machines （SVMs） that involve equality constraints and work with a least squares cost function, which simplifies the optimization procedure. In this paper, a novel training algorithm based on total least squares （TLS） for an LS-SVM is presented and applied to multifunctional sensor signal reconstruction. For three different nonlinearities of a multifunctional sensor model, the reconstruction accuracies of input signals are 0.00136%, 0.03184% and 0.504 80%, respectively. The experimental results demonstrate the higher reliability and accuracy of the proposed method for multifunctional sensor signal reconstruction than the original LS-SVM training algorithm, and verify the feasibility and stability of the proposed method.