Selection of kernel parameters for KNN

How to choose the optimal parameter is crucial for the kernel method, because kernel parameters perform significantly on the kernel method. In this paper, a novel approach is proposed to choose the kernel parameter for the kernel nearest-neighbor classifier (KNN). The values of the kernel parameter are computed through optimizing an object function designed for measuring the classification reliability of KNN. We test our approach on both artificial and real-word datasets, and the preliminary results demonstrate that our approach provides a practical solution.