Success factors for expert systems

This paper has reviewed the objectives and success factors for developing expert systems, portraying the rapid prototyping cycles of expert systems against the framework of traditional life cycle management practices. 

Resource estimation is a critical factor influencing the success of expert system projects. It is important that the developer accurately estimates the time, staff, and financial resources required to complete the project. Another resource estimation factor is allowing for experimentation or exploration through prototyping, often both are necessary in the development of an expert system. 

Success factors associated with the target users of the system involve an understanding of the users needs and a specification of the content and level of complexity of expert system s outputs. Users of expert systems do not want it to build a clock for them, they just want to know what time it is. 

In spite of the emergence of ICT and their successful application by various manufacturing industries, communication in B C has a low success rate, due to its fragmented sector. Although B C has dynamic partnerships between various experts from different organizations, the reality is that each partner uses isolated systems that are mostly not interoperable and that cannot support data interface standards. Manual transfer of data is stiU largely the way to pass information. Tasks are therefore undertaken as isolated notes of a large network, in which communication procedures are primitive, slow and expensive. Interoperability is a prime factor for better control of quality and time and for cost reduction. 

To design a successful high speed fire protection system, an engineer must take many factors into consideration. In addition, each individual installation typically has characteristics that require special attention. Because of the nature of the hazard involved and the need for such extremely fast response, the design of the high speed detection system is best left to a skilled expert. 

This is a computerized system produced by DNA Systems Inc. of Flint, Michigan. Erley (1971) has compared the performances of S/RCH-I, S/RCH-III, and FIRST-1 using the ASTM infrared data file. He used a test group of 138 unknown spectra selected at random from the literature. Features introduced into the FIRST-1 system increased the accuracy and precision above those of the other systems. Also, a novice could obtain successful results about as well as an expert. The cost per performance (taking all the factors affecting the search into account) was lowest for the FIRST-1 system. 

---