一种新的支持向量分类方法及其在粮食安全预警系统中的应用(英文)

A New version of Support Vector Classification and Its Application to Early Warning of Food Security

本文提出了支持向量分类的一种新方法,它和标准的支持向量分类方法不同:标准的支持向量分类方法要求每一个输入点(模式)都确切地属于某一类,在本文中我们只要求输入点以某种概率属于某一类.同时,我们把这种方法应用于粮食安全预警问题中。

A new version of support vector classification (SVC) is proposed in this paper. Different from the standard SVC where every input must be exactly assigned to one of two classes without any uncertainty, it is allowed here that inputs belong to one class with some probabilities. Furthermore, the new method is applied to a real-world problem -early warning of food security. The numerical results obtained supports the reasonability of our new method and its wide field of applications.