scholarly journals Designing Optimal Knowledge Base for Neural Expert Systems

2017 ◽  
Vol 10 (6) ◽  
pp. 137 ◽  
Author(s):  
Dat-Dao Nguyen
Keyword(s):  
Expert Systems ◽  
Knowledge Base ◽  
Decision Problem ◽  
Integrated System ◽  
Problem Domain ◽  
Training Set ◽  
Large Pool ◽  
Artificial Neural Network Ann ◽  
Optimal Set ◽  
Initial Knowledge

One of the limitations of conventional expert systems and traditional machine induction methods in capturing human expertise is in their requirement of a large pool of structured samples from a multi-criteria decision problem domain. Then the experts may have difficulty in expressing explicitly the rules on how each decision was reached. To overcome these shortcomings, this paper reports on the design of an optimal knowledge base for machine induction with the integration of Artificial Neural Network (ANN) and Expert Systems (ES). In this framework, an orthogonal plan is used to define an optimal set of examples to be taken. Then holistic judgments of experts on these examples will provide a training set for an ANN to serve as an initial knowledge base for the integrated system. Any counter-examples in generalization over new cases will be added to the training set to retrain the network to enlarge its knowledge base.

Knowledge Acquisition for Large-Scale Expert Systems in Transportation

1998 ◽  
Vol 1651 (1) ◽  
pp. 59-65
Author(s):  
Jeffrey L. Adler ◽  
Eknauth Persaud
Keyword(s):  
Expert System ◽  
Expert Systems ◽  
Knowledge Acquisition ◽  
Knowledge Base ◽  
Traditional Knowledge ◽  
Large Scale ◽  
Knowledge Engineering ◽  
Problem Domain ◽  
Client Server ◽  
Server Application

One of the greatest challenges in building an expert system is obtaining, representing, and programming the knowledge base. As the size and scope of the problem domain increases, knowledge acquisition and knowledge engineering become more challenging. Methods for knowledge acquisition and engineering for large-scale projects are investigated in this paper. The objective is to provide new insights as to how knowledge engineers play a role in defining the scope and purpose of expert systems and how traditional knowledge acquisition and engineering methods might be recast in cases where the expert system is a component within a larger scale client-server application targeting multiple users.

A Desktop Expert System as a Human Factors Work Aid

1987 ◽  
Vol 31 (10) ◽  
pp. 1087-1090 ◽  
Author(s):  
Craig S. Hartley ◽  
John R. Rice
Keyword(s):  
Expert System ◽  
Human Factors ◽  
Expert Systems ◽  
Knowledge Base ◽  
System Development ◽  
Scientific Publication ◽  
Problem Area ◽  
Video Display ◽  
Problem Domain ◽  
Topic Area

The advent of increasingly powerful microcomputers, coupled with the development of small, feature-packed expert systems now makes it cost effective to provide workers with relatively inexpensive desktop expert systems. In order to evaluate the value of such systems as work aids for human factors engineers, we developed a small demonstration system using a commercially available expert system development tool, NEXPERTTM, released in 1985 by Neuron Data, Inc. of Palo Alto, CA. We selected a candidate problem area based on four criteria: 1) the problem domain had to be small enough to be covered comprehensively by a relatively small knowledge base; 2) the problem domain had to be potentially useful to video display terminal (VDT) screen designers; 3) appropriate information had to be readily available in human factors guidelines, published reports, and journal articles; and 4) the problem should provide the opportunity to exercise as many of the features of NEXPERT as possible. The topic area we selected was “video display screen color”. Our goal was to produce a job performance aid (JPA) that non-human factors VDT screen designers could use to select appropriate colors for screen features. Because the system users typically have little or no formal training in human factors, the JPA has to supply color recommendations in the form of clearly stated requirements, but with the decision rationale and additional references also immediately available for users wanting more information. Using the expert system shell provided by NEXPERT, we constructed a knowledge base containing more than one hundred IF …, THEN … rules representing knowledge gained from a detailed literature review. We initially validated our expert system by posing a wide variety of hypothetical design problems and assessing its conclusions against our expectations. Based on our work so far, we have concluded that small expert systems can be useful in providing human factors expertise to system designers. We believe that increasing use of expert systems may soon lead to changes in the typical current scientific publication format to include knowledge base rules provided by the author(s).

CONSTRUCTING MODULAR HYBRID RULE BASES FOR EXPERT SYSTEMS

2001 ◽  
Vol 10 (01n02) ◽  
pp. 87-105 ◽  
Author(s):  
I. HATZILYGEROUDIS ◽  
J. PRENTZAS
Keyword(s):  
Expert Systems ◽  
Knowledge Base ◽  
Empirical Data ◽  
Knowledge Bases ◽  
Initial Training ◽  
Production Rules ◽  
Training Set ◽  
Natural Knowledge ◽  
Training Examples ◽  
Rule Bases

Neurules are a kind of hybrid rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding neurule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural knowledge base is constructed, in contrast to existing connectionist knowledge bases. In this paper, we present a method for generating neurules from empirical data. To overcome the difficulty of the adaline unit to classify non-separable training examples, the notion of 'closeness' between training examples is introduced. In case of a training failure, two subsets of 'close' examples are produced from the initial training set and a copy of the neurule for each subset is trained. Failure of training any copy, leads to production of further subsets as far as success is achieved.

scholarly journals A Game Theoretic Look at Life Insurance Underwriting

1980 ◽  
Vol 11 (1) ◽  
pp. 1-16 ◽  
Author(s):  
Jean Lemaire
Keyword(s):  
Cooperative Game ◽  
Life Insurance ◽  
Decision Problem ◽  
Optimal Strategies ◽  
Minimax Criterion ◽  
Game Theoretic ◽  
Optimal Set

The decision problem of acceptance or rejection of life insurance proposals is formulated as a two-person non cooperative game between the insurer and the set of the proposers. Using the minimax criterion or the Bayes criterion, it is shown how the value and the optimal strategies can be computed, and how an optimal set of medical informations can be selected and utilized.

An Integrated System for Design of Mechanisms by an Expert System—DOMES: Theory

1990 ◽  
Vol 112 (4) ◽  
pp. 488-493 ◽  
Author(s):  
B. Yang ◽  
P. Datseris ◽  
U. Datta ◽  
J. Kowalski
Keyword(s):  
Expert System ◽  
Knowledge Base ◽  
Design Problem ◽  
Integrated System ◽  
Structural Constraints ◽  
Design Engineers ◽  
Engine Design ◽  
Synthesis Of Mechanisms ◽  
System 2 ◽  
Human Designer

Methodologies have been developed and implemented in LISP and OPS-5 languages which address type synthesis of mechanisms. Graph theory and separation of structure from function concepts have been integrated into an expert system called DOMES (Design Of Mechanism by an Expert System) to effectively implement the following three activities: (1) enumeration of all nonisomorphic labelled graphs; (2) identification of those graphs which satisfy structural constraints; (3) sketching of a mechanism corresponding to a given graph. Developed theories and algorithms are applied to a Robot Gripper design [19] and a Variable Stroke Piston Engine design [16]. The results from these two applications indicate that the automated techniques effectively identify all previously obtained solutions via manual techniques. Additional solutions are also identified and several errors of the manual process are detected. The developed methodologies and software appear to perform a complete and unbiased search of all possible candidate designs and are not prone to the errors of the manual process. Other important features of DOMES are: (1) it can learn and reason, by analogy, about a new design problem based on its experience of the problems previously solved by the system; (2) it has the capability to incrementally expand its knowledge base of rejection criteria by converting into LISP code information obtained through a query-based interactive session with a human designer; (3) it can select the set of rejection criteria relevant to a design problem from its knowledge base of rejection criteria. These procedures could become a powerful tool for design engineers, especially at the conceptual stage of design.

On techniques of expert systems on the example of the Akinator program

2020 ◽  
Vol 25 (2) ◽  
pp. 7-13
Author(s):  
Zhangozha A.R. ◽  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Expert Systems ◽  
Knowledge Base ◽  
Hybrid Systems ◽  
Online Game ◽  
Basic Principles ◽  
The Moment ◽  
Definition Of

On the example of the online game Akinator, the basic principles on which programs of this type are built are considered. Effective technics have been proposed by which artificial intelligence systems can build logical inferences that allow to identify an unknown subject from its description (predicate). To confirm the considered hypotheses, the terminological analysis of definition of the program "Akinator" offered by the author is carried out. Starting from the assumptions given by the author's definition, the article complements their definitions presented by other researchers and analyzes their constituent theses. Finally, some proposals are made for the next steps in improving the program. The Akinator program, at one time, became one of the most famous online games using artificial intelligence. And although this was not directly stated, it was clear to the experts in the field of artificial intelligence that the program uses the techniques of expert systems and is built on inference rules. At the moment, expert systems have lost their positions in comparison with the direction of neural networks in the field of artificial intelligence, however, in the case considered in the article, we are talking about techniques using both directions – hybrid systems. Games for filling semantics interact with the user, expanding their semantic base (knowledge base) and use certain strategies to achieve the best result. The playful form of such semantics filling programs is beneficial for researchers by involving a large number of players. The article examines the techniques used by the Akinator program, and also suggests possible modifications to it in the future. This study, first of all, focuses on how the knowledge base of the Akinator program is built, it consists of incomplete sets, which can be filled and adjusted as a result of further iterations of the program launches. It is important to note our assumption that the order of questions used by the program during the game plays a key role, because it determines its strategy. It was identified that the program is guided by the principles of nonmonotonic logic – the assumptions constructed by the program are not final and can be rejected by it during the game. The three main approaches to acquisite semantics proposed by Jakub Šimko and Mária Bieliková are considered, namely, expert work, crowdsourcing and machine learning. Paying attention to machine learning, the Akinator program using machine learning to build an effective strategy in the game presents a class of hybrid systems that combine the principles of two main areas in artificial intelligence programs – expert systems and neural networks.

Computer-aided homœopathy

1991 ◽  
Vol 80 (01) ◽  
pp. 34-38 ◽  
Author(s):  
J. Fichefet
Keyword(s):  
Expert Systems ◽  
Knowledge Base ◽  
Clinical Data ◽  
Turning Point ◽  
Computer Aided ◽  
The Future

AbstractHomœopathy has now come to a turning point. Thanks to Knowledge Base Expert Systems, which appeared recently and are orientated towards drug diagnosis, homœopaths have been made aware of the enormous possibilities that computers can offer them. This applies particularly to the gathering of clinical data and analysis of a collection of clinical files. The purpose of this paper is to summarize what has already been done and suggest what can be done in the future.

scholarly journals Personal knowledge base designer: Software for expert systems prototyping

SoftwareX ◽  
2020 ◽  
Vol 11 ◽  
pp. 100411 ◽  
Author(s):  
Aleksandr Yu. Yurin ◽  
Nikita O. Dorodnykh
Keyword(s):  
Expert Systems ◽  
Knowledge Base ◽  
Personal Knowledge

scholarly journals Modeling of a CPV/T-ORC Combined System Adopted for an Industrial User

Energies ◽  
2020 ◽  
Vol 13 (13) ◽  
pp. 3476 ◽  
Author(s):  
Carlo Renno ◽  
Fabio Petito ◽  
Diana D’Agostino ◽  
Francesco Minichiello
Keyword(s):  
Energy Demand ◽  
Peak Power ◽  
Organic Rankine Cycle ◽  
Rankine Cycle ◽  
Point Of View ◽  
Integrated System ◽  
Electrical Heating ◽  
Combined System ◽  
Artificial Neural Network Ann ◽  
T System

The increasing energy demand encourages the use of photovoltaic solar systems coupled to organic rankine cycle (ORC) systems. This paper presents a model of an ORC system coupled with a concentrating photovoltaic and thermal (CPV/T) system. The CPV/T-ORC combined system, described and modeled in this paper, is sized to match the electrical load of a medium industrial user located in the South of Italy. A line-focus configuration of the CPV/T system, constituted by 16 modules with 500 triple-junction cells, is adopted. Different simulations have been realized evaluating also the direct normal irradiance (DNI) by means of the artificial neural network (ANN) and considering three input condition scenarios: Summer, winter, and middle season. Hence, the energy performances of the CPV/T-ORC system have been determined to evaluate if this integrated system can satisfy the industrial user energy loads. In particular, the peak power considered for the industrial machines is about 42 kW while other electrical, heating or cooling loads require a total peak power of 15 kW; a total electric average production of 7500 kWh/month is required. The annual analysis shows that the CPV/T-ORC system allows satisfying 100% of the electric loads from April to September; moreover, in these months the overproduction can be sold to the network or stored for a future use. The covering rates of the electrical loads are equal to 73%, 77%, and 83%, respectively for January, February, and March and 86%, 93%, and 100%, respectively for October, November, and December. Finally, the CPV/T-ORC combined system represents an ideal solution for an industrial user from the energy point of view.

Sign in / Sign up

Export Citation Format

Share Document