多源知识融合处理算法

多源知识融合可有效提高判决结果的可靠性和置信度.借鉴信息融合的思路,分析了知识融合方法和一般模型.重点讨论了基于Bayes准则、基于D-S(Dempster-Shafer)证据理论以及基于模糊集理论的知识融合算法,给出了基于3种知识融合算法的具体处理步骤,并从算法特点和适用性、实用性等方面对3种知识融合算法性能进行了对比分析.通过知识融合在合成孔径雷达(SAR,Synthetic Aperture Radar)图像融合中应用的仿真实验,验证了知识融合算法的有效性.

Multi-source knowledge fusion algorithm

Multiple source knowledge fusion can effectively enhance the reliability and credibility of the ruling result. In the light of information fusion, methods and general model of knowledge fusion were analyzed, with emphasis on knowledge fusion algorithms based on Bayes rule, Dempster-Shafer(D-S) proof theory and fuzzy sets theory. Explicit processing steps of the algorithms mentioned above were presented, and comparison between which from the perspectives of the characteristics, applicability wend practicability were drawn as well. Finally, the knowledge fusion algorithms based on Bayes theory was introduced into the field of synthetic aperture radar(SAR) image fusions. Simulation results show the effectiveness of the multiple source knowledge fusion algorithms.