Expert systems developing, model

General. We have studied the characterization of multicomponent materials by combining modem analytical instrumentation with a commercially available AI expert system development tool. Information generated from selected analytical databases may be accessed using TIMM, ( The Intelligent Machine Model, ) available from General Research Corp., McLean, VA. This Fortran expert system shell has enabled development of EXMAT, a heuristically-1inked network of expert systems for materials analysis. 

MOLGEN is an expert system developed to model the experimental design activity of scientists in molecnlar genetics. 

Peroxide hazard classification expert systems development at FM/Norwood is presently on hold until some of the resources noted become available. We have a way to go before a fully validated classification model is complete. At the same time, we are continuing to explore the possibility of using chemical database programs such as those available from Molecular Design Inc. and the University of Santiago, Chile (ARIUSA) as components of our chemical hazard expert systems. We are also looking at chemical databases on optical disc such as those available from DuPont, Aldrich, Micromedix and the Canadian Center for Occupational Safety and Health as components of future systems. 

The definition of this model will be used to design the best higher grade Knowledge Base structure. If this structure matchs with a commercial expert system developing tool characteristics, it can be selected and used allowing a minor effort to build the final system. 

As a precursor to developing the final predictive expert systems, metabonomic models were constructed for urine from control rats and mice, enabling identifica-... 

At the start of the development, it had been intended use an expert system shell to implement this tool, however, after careful consideration, it was concluded that this was not the optimum strategy. An examination procedure can be considered as consisting of two parts fixed documentary information and variable parameters. For the fixed documentary information, a hypertext-like browser can be incorporated to provide point-and-click navigation through the standard. For the variable parameters, such as probe scanning paths, the decisions involved are too complex to be easily specified in a set of rules. Therefore a software module was developed to perfonn calculations on 3D geometric models, created fi om templates scaled by the user. 

Foxboro developed a self-tuning PID controller that is based on a so-called expert system approach for adjustment of the controller parameters. The on-line tuning of K, Xi, and Xo is based on the closed-loop transient response to a step change in set point. By evaluating the salient characteristics of the response (e.g., the decay ratio, overshoot, and closed-loop period), the controller parameters can be updated without actually finding a new process model. The details of the algorithm, however, are proprietary... 

In the first stages of the development of an Action plan all control options are considered. In the case of lakes, this process is aided by a PC-based expert system , PACGAP, which looks at the physical and chemical characteristics of the lake to determine the most likely option for control. Once further, more detailed information has been collected on the lake s nutrient inputs and other controlling factors, amore complex interactive model can be used (Phytoplankton Response To Environmental CHange, PROTECH-2) to define the efficacy of proposed control options more accurately. This model is able to predict the development of phytoplankton species populations under different nutrient and stratification regimes. 

The computer has become an accepted part of our daily lives. Computer applications in applied polymer science now are focussing on modelling, simulation, robotics, and expert systems rather than on the traditional subject of laboratory instrument automation and data reduction. The availability of inexpensive computing power and of package software for many applications has allowed the scientist to develop sophisticated applications in many areas without the need for extensive program development. 

A large variety of techniques are available to develop predictive models for toxicity. These range from relatively simple techniques to relate quantitative levels of potency with one or more descriptors to more multivariate techniques and ultimately the so-called expert systems that lead the user directly from an input of structure to a prediction. These are outlined briefly below. 

In Chapter 43 the incorporation of expertise and experience in data analysis by means of expert systems is described. The knowledge acquisition bottleneck and the brittleness of domain expertise are, however, the major drawbacks in the development of expert systems. This has stimulated research on alternative techniques. Artificial neural networks (ANN) were first developed as a model of the human brain structure. The computerized version turned out to be suitable for performing tasks that are considered to be difficult to solve by classical techniques. 

Fuzzy logic is often referred to as a way of "reasoning with uncertainty." It provides a well-defined mechanism to deal with uncertain and incompletely defined data, so that one can make precise deductions from imprecise data. The incorporation of fuzzy ideas into expert systems allows the development of software that can reason in roughly the same way that people think when confronted with information that is ragged around the edges. Fuzzy logic is also convenient in that it can operate on not just imprecise data, but inaccurate data, or data about which we have doubts. It does not require that some underlying mathematical model be constructed before we start to assess the data. 

This paper describes a new approach to building molecular models using methods of expert systems. We are applying symbolic reasoning to a problem previously only approached numerically. The goals of this project were to develop a rapid model builder that mimicked the manual process used by chemists. A further aim was to provide a justification for the model as a chemist would justify a particular conformation. The AIMS algorithm reported here is extremely fast and has a complexity that increases linearly with the number of atoms in the model. 

We have not attempted to make the computer do the job of auto-r matically finding the fundamental laws of chemistry from a compilation of individual facts. Rather, we have explicitly built into the computer specific models that we believe can represent the structure of chemical information. We were guided in this endeavor by concepts derived by the chemist and have tried to develop models and procedures that quantify these concepts. In doing so we have put more emphasis on the acquisition and representation of knowledge than on problem-solving techniques. In any expert system the quality of the knowledge base is of primary and desicive importance. 

The WHO/IPCS international workshop on skin sensitization in chemical risk assessment (WHO/IPCS 2007) concluded (Q)SARs and expert systems for identification of sensitizing capacity have not been vahdated to date, but may be used as part of a weight of evidence approach for identifying the sensitizing capacity of chemicals. There are certain local (Q)SARs that can be used for a small range of chemicals. However, these are currently insufficient to cover the full range of chemicals. The Workshop recommended that QSAR models need to be further developed, and the apphcabihty domain of each model needs to be established. ... 

The chapter is divided into a section on development of process cycles or plans and a section on in-process control. The tools to be discussed include design of experiments, expert systems, models, neural networks, and a variety of combinations of these techniques. The processes to be discussed include injection molding, resin transfer molding, autoclave curing, and prepreg manufacturing. The relative cost and difficulty of developing tools for these applications will be discussed where data is available. 

Reaction to these trends is then governed by some sort of expert system. The Shrinking Horizon Process Model developed by Joseph and Thomas (Chap. 9) uses similar concepts, but recognizes that control options decrease as the run progresses. 

---