本文概述了地震预报专家系统(Expert System for Earthquake Prediction).ESEP 包括3个子系统:中长期预报系统、年度预报系统和中短期预报系统.每一子系统均由7个模块组成:控制模块、数据库、专家知识库、方法库、事实准备模块、推理和...本文概述了地震预报专家系统(Expert System for Earthquake Prediction).ESEP 包括3个子系统:中长期预报系统、年度预报系统和中短期预报系统.每一子系统均由7个模块组成:控制模块、数据库、专家知识库、方法库、事实准备模块、推理和决策模块、绘图显示模块.ESEP 中建立了推理模型 ESEP/R 和知识表示模型 ESEP/K,并提出了限制(CON)、加权(W)和综合(SYN)等3种新的证据组合方式.ESEP 的特点有:(1)体系化;(2)能综合多种专家知识;(3)拥有大量数据和专家经验;(4)采用4种推理模型并作综合决策;(5)采用多种软件环境;(6)模块化;(7)具有友好的用户界面.展开更多
This paper deals with knowledge representation of ESEP (Expert System for Earthqauke Prediction). Attending the characteristics of the knowledge in earthquake prediction domain, production representation and procedura...This paper deals with knowledge representation of ESEP (Expert System for Earthqauke Prediction). Attending the characteristics of the knowledge in earthquake prediction domain, production representation and procedural representation are connected in the knowledge repesentation model of ESEP named ESEP/K, and three new ways of evidence conbination are proposed for production rules besides 'AND' and 'OR'.展开更多
In this paper,four pattern recognition methods are set forth.Based on plane projection of samples and analysis of typical samples along with the few pattern recognition methods,the PTR algorithm for recognizing variou...In this paper,four pattern recognition methods are set forth.Based on plane projection of samples and analysis of typical samples along with the few pattern recognition methods,the PTR algorithm for recognizing various structure samples is proposed.Also two examples are given and these show the PTR algorithm is effective.展开更多
文摘This paper deals with knowledge representation of ESEP (Expert System for Earthqauke Prediction). Attending the characteristics of the knowledge in earthquake prediction domain, production representation and procedural representation are connected in the knowledge repesentation model of ESEP named ESEP/K, and three new ways of evidence conbination are proposed for production rules besides 'AND' and 'OR'.
文摘In this paper,four pattern recognition methods are set forth.Based on plane projection of samples and analysis of typical samples along with the few pattern recognition methods,the PTR algorithm for recognizing various structure samples is proposed.Also two examples are given and these show the PTR algorithm is effective.