The hybrid of semisupervised manifold learning and spectrum kernel for classification

Abstract

Manifold learning classification, as an advanced semisupervised learning algorithm in recent years, has gained great popularity in a variety of fields. Moreover, kernel methods are a group of algorithms for pattern analysis, the task of which is to find and study general types of relations in datasets. Thus, under the framework of kernel methods, manifold learning classifier has been introduced and explored to directly detect the intrinsic similarity by local and global information hidden in datasets. Two validation approaches were used to evaluate the performance of our models. Experiments indicate that the proposed model can be considered as an effective and alternative modeling algorithm, and it could be further applied to the areas of biochemical science, environmental analysis, clinical, etc.