Fuzzy rule acquisition and assessment in spatial decision exploration

摘要

One of the tasks for an intelligent GIS is to emulate the spatial problem solving capabilities of the human expert. This study develops a novel methodology to acquire spatial knowledge for decision making. Our aim is using linguistic If-Then rules to instead of numerical values in the spatial decision models when uncertainty is involved in data. Such a method is expected to solve realistic problems in natural resources analysis and management. The paper presents an adaptive neural network based on fuzzy inference system that is able to leam the spatial knowledge in the form of fuzzy logical rules, and discusses the measures of uncertainty on extracted fuzzy rules for further interpretation. The extracted fuzzy rules by this approach can be very well interpreted to support spatial decision-making.