Applications of expert systems

It extends the usage of statistical methods and combines it with machine learning methods and the application of expert systems. The visualization of the results of data mining is an important task as it facilitates an interpretation of the results. Figure 9-32 plots the different disciplines which contribute to data mining. 

In chemistry and chemical engineering, expert systems are used for various tasks ranging from laboratory automation or reaction kinetics to the design of syntheses or the simulations of processes [24]. The application of expert systems in chemistry is described in more detail in Chapter IX, Section 2 of the Handbook,... 

Dolata, D. P., Carter, R. E. WIZARD applications of expert system techniques to conformational analysis. 1. The basic algorithms exemplified on simple hydrocarbons. J. Chem. Inf. Comp. Sci. 1987, 27, 36-47. 

The range of applications of expert systems in science is very wide, limited primarily by the considerable effort that is often needed to prepare one. Typical applications include the work of Pole, Ando, and Murphy on the prediction of the degradation of pharmaceuticals 1 Nuzillard and Emerenciano s work on structure elucidation from two-dimensional NMR data 2 the work of Patlewicz and co-authors on sensitization 3 and of Prine in another area connected to safety, that of MSDS data.4 The number of publications runs to several hundred per year, covering a great diversity of topics. 

In the real-time application of expert systems, a number of design considerations, beyond those usually considered in expert systems, become important. Execution efficiency is a prime consideration. 

Expert systems have been investigated for 20 years. The implementation of expert systems is now being undertaken on a widespread basis, due to the availability of hardware and software tools which alleviate the "knowledge-engineer bottleneck", allowing cost effective implementation. In a similar way, real-time applications of expert systems require tools to allow straightforward implementation. We have presented a software/hardware structure which supports knowledge-base capture and real-time inference for process applications. 

Conventional wisdom is to prepare exhaustive technical reports, either in hard copy or electronic form, that can be distributed as need requires. In the present environment, however, instant access to information, utilizing a user-friendly approach, is often demanded. One such approach that is gaining more attention in the pharmaceutical industry involves the application of expert systems. 

Murray, F.J. The application of expert systems to pharmaceutical processing. Pharm. Tech. 1989, 13 (3), 100-110. 

The following sections provide an overview on applications of expert system and related software in these fields. 

The objectives for the Concept Phase include problem definition, requirements and feasibility. These objectives define the approach to solve the information processing problem. The first objective of the Concept Phase is to confirm the existence of the information processing or knowledge-intensive problem. The second objective is to identify high level requirements for a solution to the problem. These requirements should focus on the nature of the problem and the user s needs. The third objective is to determine the feasibility of an expert system solution to the problem. This requires a study of the applicability of expert systems to the project and the capabilities of other information technologies in comparison to the choice of an expert system. 

Identifying the intended users of the expert system leads to a clear idea of the focus of the output and its level of sophistication. Users at an entry level position will require a different focus - one that pertains directly to their task - as well as a degree of sophistication. The output should be conveyed in terms they can understand. Advanced users, on the other hand, are often better served by succinct answers that they can use as guidance. For instance, in the case of a medical application of expert systems, the difference between an entry level and advanced user might be defined by the distinctions between a medical technician and a physician. 

Application of Expert Systems to Environmental Problems Cellular Metabolism An Approach Through Artifical Intelligence An Intelligent System for the Design of Biochemical Pathways... 

D. P. Dolata and R. Carter,/. Chem. Inf. Comput. Set., 27, 36 (1987). WIZARD Applications of Expert Systems Techniques to Conformational Analysis. 1. The Basic Algorithms Exemplified on Simple Hydrocarbons. 

Application of Expert System Cisoc-Ses to the Structure Elucidation of Complex Natural Products. 

One of the most popular applications of expert systems is an intelligent job aid (Harmon, 1987 Tieman Markle, 1984). A job aid is any structured information device that an individual consults to help perform some task. Job aids are often used in place of instruction when the task performance is simple enough and non-recurrent. Job aids use linear, algorithmic logic to ensure that the performer is able to complete the task correctly. Expert systems can perform as job aids more effectively than traditional, print, linear job aids because they can represent more complex problems and because they do not use a linear procedure to solve the problem, like most job aids. The reasoning pattern of an expert system is more flexible. Welsh and Wilson (1987) have identified characteristics of expert systems as intelligent job aids ... 

Many applications of expert systems in analytical science have to cope with and manage situations... 

The value of an expert system depends on the quality (both accmacy and completeness) of the data it contains, as well as the sophistication of the shell or inference engine. As computer power grows and instrumentation becomes more automated, the development of larger and better knowledge bases will continue and the application of expert systems will become more evident. 

One of the earliest applications of expert systems in the field of QSAR was the development of calculation schemes for octanol/water partition coefficients. Although the early work with n constants had shown that they were more or less additive, a number of anomalies had been identified. In addition, in order to calculate log P values from n constants it is necessary to have a measured log P for the parent and this, of course, is often unavailable. One approach to the question of how to calculate log P from chemical structure is to analyse a large number of measured log P values so as to determine the average contribution of particular chemical fragments (Nys and Rekker 1973). The fragment contributions constitute the rules of the expert system, extra rules being supplied in the form of correction factors. Operation of this expert system consists of the following few simple steps. 

Martland, C.D., McNeil, S., Acharya, D, Mishalani, R., 1990. Applications of expert systems in railroad maintenance scheduling rail relays. 

Basden, A., On the Applications of Expert Systems, International Journal of Man Machine Studies, 19 461-472 (1983). 

The first application of expert system technology in chemistry was the development of DENDRAL by Nobel award winner J. Lederberg and co-workers at Stanford University. The program supported chonists in analyzing the molecular structure of unknown chemical substances. The decision process took into account data from mass spectrometry and other experimental information. One simple rule taken from DENDRAL will explain the type of knowledge base. 

---