عربى
Claes Home Page
Objectives
Achievement
Organizational Structure
CLAES Projects
Expert Systems
online Expert Systems
Publications
Reasearch Staff
Worshops
Collaborating Institutions
intrnal Links
 
Titles
English : A Hybrid Analogical Learning System and Its Application in Employment Accidents Domain
Abstract Analogy is one of the central inference methods in human cognition. Several analogy methods have been developed, they were different in the technique used to establish the analogy, estimate the similarities, and transform the concepts and knowledge from the source situation to the target situation. All of these methods were used separately in different learning approaches. In this paper, we propose a learning system based on hybrid model of analogy, learning is done using different analogy strategies, according to the learning task. Using one model of analogy in a learning system will constrain the learning task, while the possibility of using multi-methods of analogy in one model will contain two main features. First, it will integrate different models of analogy in a hybrid learning system. Second, it will help in selecting and applying the suitable analogy method according to the given learning task and the given knowledge. The developed learning system consists of four main modules: Knowledge Base, User Interface, Retriever and Learning Modules. A set of real cases from the domain of employment accidents is used to demonstrate the learning capability of the system.
URL
Publication year 2003
Organization Name
    Central Laboratory for Agricultural Expert System (CLAES)
Country Egypt
City Cairo
serial title Scientific Bulletin, Faculty of Engineering, Ain Shams University, Part III: Electrical Engineering
Volume 38 . 2
Author(s) from ARC
External authors (outside ARC)
    Mohmmed Eid El-Sedeek
    Said El-Mabrouk
Agris Categories Documentation and information
Proposed Agrovoc Machine Learning; Learning by Analogy; Case-Based Learning.;
Publication Type Journal

 
Please email your suggestions to management@claes.sci.eg