多粒度的GIS數據不確定性粗集表達

Abstract

粗集是一種處理地理信息不確定性和不精確性的新型數學工具,在揭示和表達多層次(或粒度)的空間知識方面具有較大優勢。為此,從空間信息觀測或表達的粒度角度來探討空間數據所蘊含的不確定性。在此基礎上,運用粗集理論中的一些基本概念和方法來系統地描述和表達空間目標位置數據、屬性數據以及空間關系數據的不確定性,旨在建立一種多粒度的不確定性分析和表達方法。 Rough set is a novel mathematical tool for dealing with uncertainties and imprecision of geographic information,which can be used to represent uncertainties in multi-levels spatial knowledge.Based upon the fundamental concepts in rough set theory,this paper proposes rough set models to represent the uncertainties in position,attribute and topological relation of spatial objects.The changes of these uncertainties with the observation granularity are also investigated and represented by the rough set approach.It suggests that rough set is a very promising tool to integrate the representation of the uncertainties in measurement,classification and spatial relationships,and their changes with the observation granularity.