In this chapter, the authors present Intelligent Expert Decision Support Systems (IEDSSs) technology and conceptual models of Expert systems(ES) for Human-Operator (H-O) of different areas and Air Navigation System (ANS) too. The authors demonstrate some interesting applications of IEDSS. Intelligent Expert Decision Support Systems technology is a challenging field that has witnessed great advances in the last few years. Artificial intelligence (AI) theories and approaches receive increasing attention within this emerging technology .Researchers have been used the AI concepts and theories to develop a robust generation of IEDSSs. Moreover, the convergence of AI technologies and web technologies (WT) is enabling the creation of a new generation of web-based IEDSSs for all domains and tasks. This chapter discusses the AI methodologies and techniques for developing the IEDSSs. Two most popular paradigms are discussed namely; case-based reasoning and ontological engineering. Moreover, the chapter addresses the challenges faced by the application developers and knowledge engineers in developing and deploying AI-based expert decision support systems. In addition, the chapter presents some examples of ES by the author and colleagues at National Aviation University, Ukraine and some cases of IEDSSs developed by the author and his colleagues at Artificial intelligence and Knowledge Engineering Research Labs, Ain Shams University, AIKE Labs-ASU, Cairo, Egypt.
TopIntelligent Expert Decision Support Systems
Intelligent Expert Decision Support Systems (IEDSSs) represent a special kind of knowledge-based systems. Such systems permits the knowledge and experience of one or more experts to be captured and stored in its knowledge base. IEDSSs are based on many disciplines such as: cognitive science, computational neuroscience, philosophy, artificial intelligence, computer science and knowledge engineering . IEDSSs are smart systems that imitates the human mind. The main characteristics of such systems are the ability of inference, reasoning, perception, learning, non-algorithmic and knowledge-based systems . To a limited degree, AI concepts permits IEDSS to accept knowledge from human input, then use that knowledge through simulated thought and reasoning processes to solve problems. Many types of IEDSSs are in existence today and are applies to different domains, e.g., air navigation, geology, biological sciences, economy, medical sciences, health care, commerce, and education (Greer, 1995; Salem, 2011).
This paper is organized as follows; the second section introduces an overview of the knowledge representation and reasoning techniques and methodologies for developing the IEDSSs. In the third section we present the Case-Based intelligent expert decision support systems. Sections four, five and six describe the ontological engineering, data mining and agent-based approaches and methodologies for developing such respectively. The seventh section gives an overview of some applications of IEDSSs in healthcare domain developed by the author and his colleagues at AIEK Labs-ASU. The eighth section discusses the difficulties and challenges. The last section draws conclusion and perspectives.
Figure 1. General characteristics of IEDSSs
TopIntelligent Expert Decision Support System (Iedss)
An intelligent expert decision support system consists of three major components: a knowledge base, an inference engine, and a user interface. The knowledge base contains all the facts, ideas, relationships, and interactions of a narrow domain. The inference engine analyzes the knowledge and draws conclusions from it. This engine (software) uses search and pattern matching techniques on the knowledge base to answer questions, draw conclusions, gives recommendations or otherwise perform an intelligent function.
Figure 2. Intelligent Expert Systems Disciplines
The user interface software permits new knowledge to be entered into the knowledge base and implements communication with the user. The purpose of the system is not to replace the experts, but simply to make their knowledge and experience more widely available. Typically there are more problems to solve than there are experts available to handle them. The system permits others to increase their productivity, improve the quality of their decisions, or simply to solve problems when as expert is not available. The main challenge in developing IEDSS for any specific task is to build a “knowledge base” in that domain of interest. The knowledge of that domain must be collected, codified, organized and arranged in a systematic order. The process of collecting and organizing the knowledge is called knowledge engineering. It is the most difficult and time-consuming stage of any IEDSS development process. Figure 3 shows some of the static/Hierarchical techniques, e.g.; lists, trees, production rules, semantic networks, frames, scripts, cases, and ontologies. Figure 3 represents some of the stereotypical knowledge representation (KR) techniques. The key to the success of such systems is the selection of the appropriate technique that best fits the domain knowledge and the problem to be solved. That choice is depends on the experience of the knowledge engineer.