基于属性粒计算的认知模型研究  

Research on Cognitive Model Based on Attribute Granular Computing

作　　者：周如旗[1] 冯嘉礼[2] 

机构地区：[1]广东第二师范学院计算机科学系,广州510303 [2]上海海事大学信息工程学院,上海200135

出　　处：《计算机科学》2014年第7期68-73,共6页Computer Science

基　　金：国家自然科学基金项目(60075016);广东省科技计划项目(2012B010100049)资助

摘　　要：属性粒计算可模拟人脑的粒化、组织和因果等认知功能,但推理过程缺乏一种形式化机制。Petri网具有的异步、并发和不确定性等特征与人脑思维过程中的某些认知活动类似。基于属性粒计算的基本概念和逻辑计算规则对Petri网进行了基于定性映射的适当扩充,使得Petri网以属性粒计算的形式在知识表示、知识推理、学习模式和记忆模式等方面初步体现出一个认知系统所需要具备的一些基本元素特征。这种方法能够在一定程度上体现具有不确定性识别和判断的思维认知过程,为研究Petri网应用于模拟人类的高级智能、形象思维能力提供了一种新的思路。Attribute granular computing can simulate the cognitive functions of human brain, such as granulation, orga- nization and causation, but it lacks of a formal mechanism for the reasoning process. Petri net has asynchronous, concur- rent and uncertainty characteristics, which is similar to the characteristics of some cognitive activities in human thinking process. The basic concept and logic calculation rules of attribute granular computing were put forward in this paper. The Petri net was properly extended based on qualitative mapping. Some basic elements of a cognitive system, such as knowledge representation, reasoning, learning and memory mode were initially showed in the extended Petri net. The re- sults show that this method can reflect the cognitive process of uncertainty identification and judgment in a certain ex- tent. This model provides a new convenient tool for Petri net in the study and stimulation of human＇s advanced intelli- gence and ima~：e thinking.

关 键 词：认知模型 粒计算 定性映射 模糊集 PETRI网 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]