Expert systems future

Hahn, GJ. (1985), More Intelligent Statistical Software and Statistical Expert Systems Future Directions, American Statistician, 39, 1-16. 

The appearance of expert systems to solve practical problems, also in chemistry, started in the eighties. During this period much experience has been acquired through the expected and unexpected problems that arose during such projects. Until now there are only a few commercially available expert systems and this is not likely to change in the near future. This implies that expert systems will be mostly in-house developments. The different steps to consider are ... 

Advances in computer science continue to serve as the basis for new extensions to software products. In particular, artificial intelligence techniques have begun to mature to the point at which they can play a role in scientific software. In the future, scientific software will incorporate expert systems technology in order to provide a new level of assistance to scientists in applying statistical and graphical techniques to data analysis. 

Analytical chemistry in the new millennium will continue to develop greater degrees of sophistication. The use of automation, especially involving robots, for routine work will increase and the role of ever more powerful computers and software, such as intelligent expert systems, will be a dominant factor. Extreme miniaturisation of techniques (the analytical laboratory on a chip ) and sensors designed for specific tasks will make a big impact. Despite such advances, the importance of, and the need for, trained analytical chemists is set to continue into the foreseeable future and it is vital that universities and colleges play a full part in the provision of relevant courses of study. 

Expert systems represent a branch of artificial intelligence that has received enormous publicity in the last two to three years. Many companies have been formed to produce computer software for what is predicted to be a substantial market. This paper describes what is meant by the term expert system and the kinds of problems that currently appear amenable to solution by such systems. The physical sciences and engineering disciplines are areas for application that are receiving considerable attention. The reasons for this and several examples of recent applications are discussed. The synergism of scientists and engineers with machines supporting expert systems has important implications for the conduct of chemical research in the future some of these implications are described. 

Rules in the expert system are structured to allow flexibility and future expansion. For speed of execution, the IF-THEN clauses are actually executable LISP code. Tables II and III contain examples of how rules are structured. The IF clauses contain functions, called predicates. Predicates have a value of either... 

Additionally, use of a commercial AI shell for expert system development has been demonstrated without the need to learn computer programming languages (C, Pascal, LISP or any of its variations), nor to have an intermediary knowledge engineer. Although this development effort of 4-5 man months was on a minicomputer, adaptation of EXMAT to the microcomputer version of TIMM is anticipated. The completed implementation of EXMAT will support the belief that AI combined with intelligent instrumentation can have a major impact on future analytical problem-solving. 

In general, it appears that expert systems which combine symbolic/numeric processing capabilities are necessary to effectively automate decision-making in applications involving analytical and process instrumentation/sensors. Furthermore, these integrated decision structures will likely be embedded (67-69) within the analytical or process units to provide fully automated pattern recognition/correlation systems for future intelligent instrumentation. 

Section 9.2 will review traditional statistical process control/statistical quality control (SPC/SQC) techniques used in quality control. Section 9.3 will follow this review with a discussion of techniques based primarily on an experiential rule base and expert system technology. Section 9.4 will discuss control strategies that use an on-line process model a variety of models can be used in such model predictive control. Section 9.5 will discuss this variety of models. Section 9.6 will summarize this chapter and discusses future trends in the field. 

Fig. 7 Screen images for the tablet formulation expert system as described by Rowe. (A) Shows user interface with windows for the formulation task tree, specification, formulation, and current task. Tasks are displayed in various formats—current task in highlighted or bold text, completed in italics, and future in standard text. (B) Shows the security of the system. The input of a password displays the user privileges. (From Ref...

The attempts that have been made to utilize true chemometric optimization of operating conditions in CEC are unclear in most of the studies done utilizing CEC. This has been done for many years in GC and HPLC, as well as in CE, but there are no obvious articles that have appeared which have utilized true chemometric software approaches to optimization in CEC [57-59]. It is not clear that any true method optimization has been performed or what analytical figures of merit were used to define an optimized set of conditions for biopolymer analysis by CEC. It is also unclear as to why a specific stationary phase (packing) was finally selected as the optimal support in these particular CEC applications for biopolymers. In the future, it is hoped that more sophisticated optimization routines, especially computerized chemometrics (expert systems, theoretical software, or simplex/optiplex routines) will be employed from start to finish. 

Stephanopoulos, G., The future of expert systems. Chem. Eng. Prog., September, p. 44 (1987). 

The computerized system which helps most in product development resembles more the so-called expert system, which is a set of relationships quantified by an experiment for the purpose of similar products. Such systems are increasingly more effective with the amount of data (information) increasing. Considering such need, this book will have in the future a companion CD-ROM containing a base of available data which will be periodically updated to build an incremental wealth of information serving two purposes material selection and data processing for the needs of the formulator. 

Even though technological advances might Improve the resolution of some of our Instrumentation, miniaturization itself will only complicate our ability to characterize devices In the future. Artificial intelligence and expert systems appear to have an excellent potential for enhancing our problem solving ability. It Is expected that with proper development, this tool could become an essential Item In the microanalyst s repertoire of techniques In tomorrow s technology. 

All of these critical considerations described melt down to a simple fact Expert systems — as well as other Al approaches — are dehnitely different from conventional software in the same way humans differ from expert systems. What is needed is a change in perception of these systems since they pose the beginning of a transition from nonintelligent to intelligent systems. We will better be off to see this transition as a matter of fact to be prepared for the future. 

The ESES expert system provides an explanation facility which justifies the recommendations given to the user (this is the HOW feature, also frequently referred to as the WHY feature in expert system literature). A comprehensive report of the session can be printed for future reference which includes the recommendations given, HOW explanations, a profile of the problem described by the... 

---