Spatial analysis commonly uses statistics packages, fuzzy logic, cellular automata, neural-networks, and artificial intelligence (AI) techniques (such as knowledge-based systems) as analysis tools. The proposed approach is based on a rule-based expert system which it uses a simple, easy rule structure, and hence has been the most common technique in knowledge-based AI for developing hybrid systems with GIS. The rules can be programmed using a simple ‘if-then’ structure in a natural language such as Arabic or English. The proposed framework simplifies the interfaces to users by providing the necessary accessing and querying tools.
Previous rule-based expert systems in GIS applications have used an automatic procedure for land use/cover classification. In this paper, a rule-based expert system is presented that uses an interactive question-and-answer sequence. In this system, the knowledge (prolog, questions and answers, and rules) can be constructed easily by experts using Arabic or English. Using this system, users can determine a solution to a specific problem easily from the constructed rules through the interactive question and answer sequence. A rule-based engine using existing rules will generate the questions and solutions.
This rule-based expert system consists largely of a main window system (expert part, user part, and application part), rule-based engine, and a database. This system is applicable to any interactive interpretation of GIS applications. The development of the application part is independent of the other parts in order to create independent object oriented components rather than coherent ones. The proposed system interface is written in VB.NET.
Abid Al Ajeeli,
Management Information Systems Department,
College of Information Technology,
Bahrain University, Kingdom of Bahrain.