Computerized expert systems

The relationship between chemical structure and activity has been recognized from early on, as the examples in Sec. 10.3.2 illustrate. Tbday, computerized expert systems allow the virtual screening of millions of possible structures with the objective to find the best candidates for development. However, the accuracy of such in-silico predictions is still low and it will take time before they can replace experimental discovery methods. 

Such complex information is known by experts in each analytical area. The problem for most practitioners is to obtain the needed information or knowledge and proceed with an analytical scheme. The extent to which this knowledge becomes available in computerized "expert systems" the easier and more efficient this task will become. This creates more freedom for the art, or the intuitive/oreative side of analysis. The critical role of the analyst is then the building of scientifically consistent mental picture, a concept or a model, to fit the accumulated data. 

The escape rate coefllcients of the iodine and noble gas isotopes identified in one PWR or BWR plant can be directly applied to other plants of the same type, provided that the essential conditions, for example, fuel rod linear heat ratings, are comparable or can be corrected for. By this means it became possible to evaluate the number of failed fuel rods in the core of an operating reactor on the basis of the fission product activity concentrations measured in the coolant early attempts in this area were reported by Schuster et al. (1977). Although these estimates were based only on empirical data, they permitted a rather trustworthy prediction, as can be seen from Fig. 4.6., where the predicted numbers of failed fuel rods are compared with those detected in the course of post-cycle examinations. These techniques have been considerably improved, on the basis of experimental results as well as of model development and calculations. Because of the great number of parameters influencing the escape of fission products from defective fuel rods, evaluation of the number and type of defects from the measured activity concentration of fission products in the primary coolant is a difficult task which can be performed reliably only by specialists with considerable experience in this field. Attempts were, therefore, imdertaken to develop computerized expert systems that could be applied routinely. Lewis et al. (1992) described the development of such a system by means of which information can be obtained on the number of defects and their... 

There are two major approaches to de novo sequencing by mass spectrometry. The first one is based on a number of empirical rules obtained by observing typical peptide fragmentation schemes [20]. Current versions of this approach rely on computerized expert systems that are built on the dozens of empirical rules and factors. These include general observations on the prevalence of certain fragments in spectra produced by the used fragmentation methods and in typical instruments. For example, CAD is known to produce predominantly y- and fc-type ions. There... 

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. 

Today, analytical evaluation is done on a large scale in a computerized way by means of data bases and expert systems (Sect. 8.3.6). In particular, a library search is a useful tool to identify pure compounds, confirm them and characterize constituents in mixtures. Additionally, unknown new substances may be classified by similarity analysis (Zupan [1986], Hippe [1991], Warr [1993], Hobert [1995]). The library search has its main application in such fields where a large number of components has to be related with large sets of data such as environmental and toxicological analysis (Scott [1995], Pellizarri et al. [1985]). 

The book s first section, on expert systems, is a collection of expert-system applications. Expert systems can simplistically be thought of as computerized clones of an expert in a particular specialty. Various schemes are used to capture the expert s knowledge of the specialty in a manner that the computer can use to solve problems in that field. Expert-systems technology is the most heavily commercialized area in AI as shown by the wide variety of applications that use this technology. These applications help show the breadth of problems to which AI has been applied. Much of the work from other sections of the book also uses expert-system techniques in some manner. 

Raman, and nmr spectra. An extensive bibliography of older hard-copy ir spectra is given in The Coblent Sodety Desk Book of Infrared Spectra (62). Since the mid-1980s, comprehensive databases have been available in computerized form where the spectra themselves, not merely the bibliographic references, are searchable and displayable. The search algorithms vary considerably among the available systems no algorithm standard exists (ca 1994), but several are under development (63,64). Expert systems, which assist in the automatic interpretation and identification of spectra, have existed for many years but are not commonly used (65). Computerized spectral databases are either local, PC-based, or public. 

Probably the most common representation for all kind of spectra used in computerized information and expert systems is the peak table. This very simple representation consists of a table containing all (or a certain number of the most significant) peaks appearing in the spectrum. Each peak is usually described by its position and intensity, but more information (half width, multiplicity, shape type, etc.) can be added if needed. 

Information from these sensors and data from conventional sensors that monitor are gathered and sent to a computerized decision making system. This decision-maker includes an expert system and a mathematical model of the process. The system then makes any changes necessary in the production process to ensure the material s structure is forming properly. These might include changing temperature or pressure profiles, or altering other variables that will lead to a defect-free fabricated product. 

Lun A, Ivandic M, Priem F, Filler G, Kirschstein M, EhrichJH, Guder WG. Evaluation of pediatric nephropathies by a computerized Urine Protein Expert System (UPES). Ped Nephrol 1999 13 900-906. 

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. 

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. 

EPA has undertaken the development of computerized information systems, decision support systems, and "smart" advisors to provide access to the specialized knowledge of experts and confront... 

The Defense Priority Model (DPM) is designed to provide an estimate of the relative potential risk to human health and the environment from sites containing hazardous materials. The DPM evolved from a model called the Hazard Assessment Risk Model (HARM) developed by Oak Ridge National Laboratory from 1984-1986 for the Air Force. The automation of DPM was done first in KES(r) and then in Arity Prolog(r) for use on an IBM-PC/AT class machine. The computerized model has already become more sophisticated than the paper model and as development continues, it is possible to take advantage of additional expert system features. This paper is designed as a case study of DPM development and presents the reasons for the choice of expert system environment and its evolution, the current scope of the model, and planned additions that will increase the functionality of model in the future. The methodology used to evaluate this expert system is also described. 

The Air Force determined that the model needed to be computerized to be maximally useful. They initially considered using dBase or Lotus software for implementing the model, but then decided that expert systems technology could provide some definite advantages such as the ability to ... 

Computerizing the information on zeolite catalysts have been attempted successfully and different databases concentrate on specific properties[25-28]. The information in several databases are shown in Table 3. Our approach[29] involves retrieval of information from the database and additionally an expert system approach is followed to derive a set of conditions to achieve one s goal in the synthesis of zeolites. The structure of the system is designed to perform three salient fiinctions as shown in Fig. 7. The first function is to provide access to a large database of physico-chemical properties and crystallographic information of all reported zeolite[30]. The second function provides for the synthesis of zeolites - the most logical route for the synthesis of a desired zeolite structure is provided. The third function is a graphic tool application to simulate X-ray powder diffraction patterns for zeolite phases with different amount and nature of purity. 

Hutchinson TA, Dawid AP, Spiegelhalter D, Cowell RG, Roden S (1991b) Computerized aids for probabilistic assessment of drug safety 11 an expert system. Drug Information Journal 25 41—48. 

The Chemical Data Summary Sheet (CDSS) is a part of a larger INEEL Chemical Management System (ICMS) — a computerized tracking system for chemical products, chemicals, or hazardous agents (CPCHA). INEEL developed the CDSS as a tool to aid in hazard identification. Chemical safety experts evaluated every CPCHA at INEEL and developed a CDSS for each. Information on the CDSS includes the National Fire Protection Association (NFPA) diamond a listing of all hazards and a compatibility classification, time-sensitive classification, and building code classification for the identified CPCHA. While the CDSS is not a replacement for an MSDS, it does contain site-specific safety information that cannot be found in an MSDS and that information is presented in a standardized format... 

The iterative schedules given before can be easily computerized. The modular scheduling is much more complicated and involves using a rule-based expert system in the computer program, but the modular system is easy to do manually. 

An expert system is an intelligent, computerized, knowledge-based system that uses symbolic processes and inference procedures to simulate the decision-making process that an expert performs to solve a problan. 

The second component of the computerized system is an expert system called GlovEs, which, given a set of initial conditions or parameters, screens the information in the data base and makes recommendations based on the needs as defined by the user of the system. The system allows considerable flexibility in seeking information and quickly provides the data in a useful form. The program runs on a standard IBM or compatible PC. 

Expert systems in solid-liquid separation have now gone out of fashion somewhat and the pre-selection of equipment now tends to be built into much larger design software. In any case, computerized advice, although helpful to complete beginners as a first approach, is no substitute for experience and in-depth knowledge of the subject. 

---