基于粗糙理论的RBF网络及其遥感影像分类应用

RBFNN Representation Based on Rough Sets and Its Application to Remote Sensing Image Classification

将粗糙集合概念与模式分类过程相联系,构造粗糙集意义下的RBF网络表示形式,并利用遗传算法实现其粗糙逻辑机制。研究粗糙集意义下RBF映射理论在遥感影像分类应用中的具体算法和实现过程,以LandsatTM影像进行的土地覆盖分类实验为例,对分类过程和结果进行综合分析,认为该方法在网络结构、收敛性和分类精度等方面具有一定的优势。

Rough sets theory is a new tool for studying imprecision, vagueness, and uncertainty in data analysis. The artificial neural network has been applied widely to remote sensing data classification. This article combines artificial neural network with roughs sets, describes the semantic expression of rough sets under the meaning of setvalued measure and establishes a RBFNN modal based on rough sets. A rough logical learning mechanism of RBFNN based on rough sets is constructed. The survey and analysis of the RBFNN based on rough sets for the classification of remotelysensed multispectral image is presented. The proposed method was successfully applied in a classification of land cover with results confirming the flexibility and practicality of this rough approach.