Skip to Main Content
Electrical capacitance tomography (ECT) is a typical small samples and nonlinear mapping problem. Support vector machine (SVM) is based on the special small samples theory with strong generalization ability, and is selected as an optimal theory for small samples classify problem. In this paper the ECT image reconstruction algorithms based on C-S VM is proposed and a novel training method is proposed to improve the efficiency of C-SVM classifier by selecting active penalty parameters. The simulation and experiment indicates this algorithm has the stronger space resolution and generalization ability.