Simple Expert System Research Articles

Sonar recognition of targets embedded in sediment

Dolphins have biological sonar abilities that exceed those of any man-made system in an aquatic environment. One problem of particular importance, and for which only limited capabilities exist, is the detection and recognition of targets buried under sediment. This paper reviews dolphin echolocation capabilities and describes a system that uses a dolphin-like signal and biomimetic signal processing mechanisms to emulate the performance of the dolpin on such targets. The system employed a digitized dolphin click with a center frequency of 120 kHz and a 3dB bandwidth of 39 kHz, 50 μs duration. This signal was transmitted through seawater into mud and the echoes reflected from the objects were recorded and digitized. Two spectral estimators were used to extract a time-frequency representation of the echo. One was based on short-time fast Fourier transforms, and the other was based on an autoregressive estimator. The time-frequency representation was then processed by a separate backpropagation neural network for each estimator, designed to derive independent identifications of the targets. These identifications were then combined in a modified probabilistic neural network that used a linear transfer function rather than a binary function for its output. Finally the output of the probabilistic network was processed symbolically by a simple expert system. Three experiments are described in which the system was used to discriminate a small stainless-steel cylinder from cyliners of the same size made of hollow aluminium, foam-filled aluminium, or coral rock embedded in resin. Each of the targets was presented buried in mud at a depth of several centimeters. The system proved highly effectively at recognizing these buried targets.

Macrozonation Methodology for Landslide Hazard Determination

This is a simple expert system designed to allow a fast, low cost “a priori” classification of landslide hazards in seismically active tropical areas. It has been created to guide decision making where further and more detailed geotechnical investigations should be performed. The input consists of 5 factors. A combination of three of them (slope, lithology and soil humidity) define the “intrinsic landslide susceptibility indicator.” Meanwhile, the “triggering indicator” results from a combination of rainfall and seismic intensity factors. This system provides a data framework which can be adapted to local and regional trends. The zonation serves as a guide in determining the general trend and spatial distribution of potentially unstable slopes.

Design and Implementation of an Expert System for Controlling Health Care Costs

Many firms with self-funded medical insurance administered by outside parties fail to review the administrators' performance effectively. Often the firms do not know the extent of overpayments because they lack the expert knowledge to evaluate the paid claims. We examine the use of a simple expert system in conjunction with optimization methods for identifying claims payment errors. The knowledge base is constructed using expertise from the areas of claims processing, auditing, medical diagnosis, and procedure coding practices. Once potential errors are identified, a mathematical program is used to select claims for audit based on maximizing expected benefits subject to various firm-specific processing limitations. We use an efficient Lagrangian relaxation to solve instances of this pure binary programming problem with as many as 150,000 variables. We report on our experience in the use of this system on behalf of a Fortune 100 firm's claims data base.

Computerized Interactive Morphometry and the Diagnosis of Lymphoid-Rich Effusions

An experimental computerized interactive morphometry system for the classification of lymphoid-rich effusions is presented. The relatively inexpensive microcomputer-based system was assembled in our laboratory with commercially available hardware and software. One hundred twenty-two effusions (86 benign lymphocytoses, 26 lymphomas, and 10 chronic lymphocytic leukemias) were studied. Lymphoid cells were selected randomly by the system from real-time images of Papanicolaou-fixed and stained cytospin smears of pleural, peritoneal, and pericardial effusions. Parameters of nuclear shape, area, and optical density were measured automatically. Multiparameter statistical procedures of discriminant classificatory analysis analyzed the distribution of lymphoid nuclear profile integrated optical density to yield three groups of effusions, each with a predictive value of diagnosis of 100%. Neither these statistical procedures nor a simple rule-based expert system accurately classified chronic lymphocytic leukemia effusions based on the distribution of lymphoid nuclear profile area. When chronic lymphocytic leukemia effusions were excluded, however, the predictive values of a diagnosis of lymphoma by statistical analysis and by rule-based expert system were 92.3% and 88.9%, respectively, whereas the predictive values of a diagnosis of benign lymphocytosis were 97.7% and 91.3%, respectively. Potential applications and limitations of this technology for the diagnosis of lymphoid-rich effusions are discussed.

エキスパートシステムによる水田の水管理

This paper describes an expert system for controlling water temperature of rice field and results of its field test. We developed a simple expert system for controlling water temperature of rice field that can be used in determining how best to control the water depth under changing weather conditions, particularly cool summer weather conditions.To test its applicability to rice field, field experiments were made at two plots with the area of 110m2, respectively in 1990 and 1991. The water depth of an experiment plot was controlled by this expert system and the water depth of a control plot was maintained at a water height of 3cm (1990) or 4cm (1991) during the rice growing reriod.Field experiments showed that brown rice yield and perfect rice grain yield were higher for the experiment than those for the control plot. This results indicate evidently that water temperature environment of rice fields was improved using the expert system for controlling water temperature, resulting increase in rice yield.

Expert systems and finite element structural analysis — a review

Finite element analysis of many engineering systems is practised more as an art than as a science. It involves high level expertise (analytical as well as heuristic) regarding problem modelling (e.g. problem specification, choosing the appropriate type of elements etc.), optical mesh design for achieving the specified accuracy (e.g. initial mesh selection, adaptive mesh refinement), selection of the appropriate type of analysis and solution routines and, finally, diagnosis of the finite element solutions. Very often such expertise is highly dispersed and is not available at a single place with a single expert. The design of an expert system, such that the necessary expertise is available to a novice to perform the same job even in the absence of trained experts, becomes an attractive proposition. In this paper, the areas of finite element structural analysis which require experience and decision-making capabilities are explored. A simple expert system, with a feasible knowledge base for problem modelling, optimal mesh design, type of analysis and solution routines, and diagnosis, is outlined. Several efforts in these directions, reported in the open literature, are also reviewed in this paper.

Expert system for estimates of molecular weights of volatile organic compounds from low-resolution mass spectra

MAXMASS, the highest mass with an intensity of 5% of the base peak in a low-resolution mass spectrum, has been found to be linearly correlated with the true molecular weights of 400 randomly selected spectra, yielding a family of parallel lines. A simple expert system using MAXMASS has been developed to estimate molecular weights of unknown volatile compounds from their mass spectra. This is an empirical rule-based system which will run on a personal computer. It consists of a classification module chained to separate molecular weight prediction modules for six classes. These are benzenes, chlorobenzenes, bromoalkanes/alkenes, mono- and dichloroalkanes/alkenes, tri-, tetra- and pentachloroalkanes/alkenes, and unknown (other) classes. The rules were derived from National Institute of Standards and Technology (NIST) reference spectra of 75 target toxic compounds from the first five classes and 32 from the unknown class. Performance tests of molecular weight predictions were made with the expert system and the self training interpretive and retrieval system (STIRS) on NIST reference spectra of the 107 training compounds; on a set of 32 test NIST reference spectra of other compounds found in air samples; on a set of 100 randomly selected NIST reference spectra; and on 30 spectra taken from actual field gas chromatography-mass spectrometry (GC-MS) samples. The expert system performed much better than STIRS on training spectra, STIRS performed better on test and random spectra, and the expert system performed better with field data. The median absolute value deviation from the true results for the expert system was 1 and 3 mass units for training and field GC-MS spectra, respectively. Moreover, the expert system is much faster than STIRS.

Global view of optical design space

The optical design space of some simple lenses is investigated systematically. Typical space topographies are visualized with 3-D graphics, where the complete set of available solutions is clearly identified. The space characteristics are then studied and compared through the use of several merit functions with differing degrees of complexity. A two-phase search algorithm, based on global optimization techniques, is proposed here. In the first phase, using a coarse sampling approach, the program finds the favorable regions that correspond to potentially promising configurations. In the second phase, conventional optimization routines are used to find the solutions in each region. Then an optimum solution is determined according to the application at hand. The proposed algorithm is analyzed and compared to more conventional design approaches. A further refinement of the algorithm excludes from the systematic search some unfavorable configuration regions through the use of a simple expert system. Search times are further reduced through parallel-processing methods. The algorithm provides overall information about a given design space and offers a selection of best solutions to choose from. As an example, it is applied to a triplet objective.

Development and application of a simple expert system for the interpretation of the antepartum fetal heart rate tracings (version 88/2.29)

A simple expert system is developed for the interpretation of antepartum fetal heart rate tracings. The perinatal expert chose to use the phrase ‘Fetal Reserve’ to describe what the cardiotocogram is indirectly measuring. Our analysis program gives numerical values to each CTG such as 5, 4, 3, 2.5, 2 and 1 corresponding to the fetal reserve conditions of good, satisfactory, probably satisfactory with uncertainity, borderline, decreased, and critical respectively. This study consists of 33 normal pregnancies with normal outcome. Each patient is followed by our computerized system biweekly from the 28th to the 38th gestational week and weekly there after. The expert system's decision for 28th, 30th, 32th, 34th, 36th, 38th, 39th and 40th gestational weeks were 3.3 ± 1.0, 3.8 ± 0.7, 3.8 ± 1.0, 4.1 ± 0.9, 4.1 ± 0.7, 3.6 ± 1.0, 4.2 ± 1.0, 3.8 ± 0.9 and 3.4 ± 1.2, respectively. In this study, we have used confusion matrix to determine the normal, security, and danger zones according to the perinatal expert and the expert system and the discriminatory power of the system is found to be highly significant statistically (Q = 221). We also showed that the passive test (non-stress test) in normal pregnancies has demonstrated false positive results in 4.2 and 9.3% of the cases according to the evaluations of the perinatal expert and the expert system, respectively.

Expert Systems in Forensic Science

Abstract Expert systems provide a means for experienced experts to make their expertise available to others. The workings of a simple expert system shell are described using several small knowledge bases for examples. Several types of materials are described which would appear to be excellent candidates around which to develop knowledge bases to assist in the identification, evaluation, or interpretation of evidence involving such materials. The knowledge bases could be used in practice by forensic scientists or for educational purposes.

A simple expert system for identifying plants in a local area

Over the last five years educationalists have recognized the potential of expert systems for instructing students. They can explain and tutor students, they can allow exploration of alterations and, to a lesser extent, they can offer a natural dialogue with the student. In this paper, we describe the adaption of a simple expert system to the task of identifying the eucalypt species present in a small Nature Reserve used by teachers for instructions. The knowledge base consists of nine hypotheses (species), 22 rules and 28 explanatory items (including drawings). The system operates on a cheap, handheld computer designed for fieldwork. Preliminary tests showed that, except for its slowness, it was suited for the task. The speed limitation is likely to be overcome with the next generation of handheld computers. This work has shown that is now becoming possible to use this technology for simple education purposes.

A simple expert system shell for microcomputer-aided radiographic diagnosis

A simple microcomputer-based expert system shell for radiographic diagnosis is described. The system interrogates the user by means of a simple question--and-answer approach on the radiographic findings in a given case and proffers a differential diagnosis from a database. The system also allows listing of both the radiographic findings pertinent to a specific diagnosis and all diagnoses in which a particular finding or combination of findings occur. The system database can be easily updated or modified by the user. The demonstration application for the expert system shell is the plain film diagnosis of osseous dysplasia.

Reliability and performance evaluation of systems containing embedded rule-based expert systems

A method for evaluating the reliability of real-time systems containing embedded rule-based expert systems is proposed and investigated. It is a three stage technique that addresses the impact of knowledge-base uncertainties on the performance of expert systems. In the first stage, a Markov reliability model of the system is developed which identifies the key performance parameters of the expert system. In the second stage, the evaluation method is used to determine the values of the expert system's key performance parameters. The performance parameters can be evaluated directly by using a probabilistic model of uncertainties in the knowledge-base or by using sensitivity analyses. In the third and final state, the performance parameters of the expert system are combined with performance parameters for other system components and subsystems to evaluate the reliability and performance of the complete system. The evaluation method is demonstrated in the context of a simple expert system used to supervise the performances of an FDI algorithm associated with an aircraft longitudinal flight-control system.

Sedrule: A rule-based system for interpreting some major sedimentary environments

SEDRULE is a simple expert system for identification of major sedimentary environments from good outcrops. Although rudimentary, the program, written in muLISP, illustrates the forward-chaining search method. Initially designed as a teaching aid for the novice field sedimentologist, it also can be used to teach some basic principles of LISP programming within sedimentology. Furthermore, this program helps analyze the basic tenets of interpreting depositional environments, thereby helping to examine expert reasoning, which is a goal of AI research. Finally, the program expands its knowledge base as the student's own abilities grow, so it provides a lifelong tool for field work.

How much does the end user need an intermediary?

INSEAD, the European Institute for Business Administration, at Fontainebleau, near Paris, offers advanced management education for over 400 students a year, mainly through the MBA course. The Library first set up online access in 1984, and now has extensive online training facilities for students, as well as services for professors, researchers and administrative staff. As demand for online training from students has increased, some professors have encouraged Library online specialists to give brief presentations at the start of courses, helping students to aim their information searching directly towards project needs. In 1987, with pressure on the present three online specialists, we started to explore ways of increasing the participation of staff and student end users in their own searching. More attention was given to existing online menu‐driven systems like Textline, while the growth of professional datafiles on France's Minitel videotex system made it worthwhile to explore their potential as subsidiary search options. In 1988, to develop direct end user searching further, two CD‐ROM workstations were installed, which now offer six disc databases on free access. There has also been an exploration of the role of databases issued on floppy disk as offline alternatives. To help campus users understand the range of database options available, a booklet listing by subject major databases accessible on campus, on both online and offline media, was recently issued. Currently, a prototype simple expert system is being developed from this to help users to move between offline and online searching more easily. The present efforts are aimed at a more user‐oriented information access as the Library prepares to transfer next year to a new building.

Development of an expert system for preoperative assessment of female urinary incontinence

We developed a simple expert system for preoperative assessment of women complaining of involuntary loss of urine and scheduled to undergo surgery for incontinence. The aim of the system was to use the parameters obtained at urodynamic investigation to arrive at the correct diagnosis. We used an IBM-PC with two disk drives and 256k RAM, and the expert system shell EXSYS, a rule based system with the possibility of assigning probabilities to the different solutions. To write the rules forming the knowledge base we used a two-fold approach: we constructed tree diagrams for each diagnosis and calculated the corresponding predictive values (statistical approach), and we added rules based on our experience (heuristic approach). The expert system has been found reliable in a clinical setting and is useful for teaching purposes.

A simple expert system

Expert systems are one field of artificial intelligence (AI) that has received considerable recent attention. These systems generally are written in Lisp or Prolog -- languages that are interpretive, have flexible data accessing mechanisms, and use powerful string manipulation tools. This raises two questions: what are expert systems, and can they be implemented using MUMPS? Some answers are presented in this paper.

A simple expert system for a mask shop : S. N. Gupta and K. I. Arshak. Microelectron. J.18(4), 35 (1987)

A simple expert system for a mask shop : S. N. Gupta and K. I. Arshak. Microelectron. J.18(4), 35 (1987)

PCNDT-an electromagnetic finite element package for personal computers

An integrated finite element package for the solution of magnetostatic and eddy current problems, suitable for use on personal computers, is presented. It can handle general field problems but is particularly applicable to nondestructive-evaluation modelling problems including moving probes. The package consists of an interactive preprocessor, routines for adaptive and nonadaptive mesh generation, bandwidth reduction algorithms, iterative and direct linear solvers, and a postprocessor. A simple expert system shell is used in conjunction with the user input. The main emphasis throughout the package is on useful options, simplification of user input, and minimization of the time needed to define correctly a geometry for finite element analysis. Extensive graphics editing capabilities are provided. >

An expert system for the optimal mesh design in the hp‐version of the finite element method

AbstractThis paper suggests a simple expert system frame and provides the domain knowledge for the optimal mesh design and the prediction of the error in the energy norm for the problem of plane elasticity using the hp‐extension in the finite element method. The expert system monitors the progress of the analysis, guides the user through the various steps and is able to reason about its own advice. In an example the user–expert communication is shown and the superiority of the results is demonstrated.