Expert System Interface Research Articles

Design of An Expert System for Early Diagnosis of Intestinal Tuberculosis

<p class="Abstract">WHO in 2013 released data in the Global Tuberculosis Report that 8.6 million more people were positive for TB, and 15.12% of them died. One of the causes of death due to tuberculosis is too late to know when it is infected and too late to get treatment. For an initial diagnosis of whether someone has TB, they can immediately go to a hospital or use a computer application that has an expert's ability. This study aims to design an expert system for the early diagnosis of intestinal tuberculosis using the Forward Chaining method. Expert System is one part of Artificial Intelligence that can create a computer program to provide decisions and analysis like an expert or expert in a particular field. The research method used in this study is the Research and Development method with the ADDIE approach. The expert system for early diagnosis of intestinal tuberculosis is designed by making a decision tree diagram to find out the rules needed to diagnose whether a person has intestinal tuberculosis from the symptoms experienced. The formulation of the problem or the rules needed for the initial diagnosis of intestinal tuberculosis in this study was built using the Forward Chaining method. The output of this research is an Expert System in the form of a Stand-Alone application that is built with the Visual Basic Programming Language, which can provide diagnostic results whether a person suffers from intestinal tuberculosis from the symptoms entered into the Expert System Interface.</p>

Development of Expert System for Dental and Oral Diseases Diagnose in Certainty Condition

Expert systems are used to solve problems based on the view of an expert. Expert systems are widely used in various fields, such as health. This study aims to create a web-based expert system that is used for the early diagnosis of dental and oral diseases through the initial symptoms that appear from the patient. In its implementation, this research used a descriptive qualitative method completed by collecting data and observation. While the development of expert systems using the prototype development method and the model of the expert system created using the Dempster Shafer method. The acquisition of knowledge about the symptoms of dental and oral diseases from experts is stored in a repository. The implementation of expert system models uses an object-oriented approach. In this study, the results to be achieved are a prototype design of an expert system application used as an initial diagnosis for ordinary users (patient) regarding dental and oral diseases in certain conditions. The initial symptoms suffered are feed-in into the expert system interface. Knowledge in the expert system is prepared and store into the system by a specialist in dental and oral disease.

XDSAPP2.0

XDSAPPis an expert system and graphical user interface (GUI) for the automated processing of diffraction images using theXDSprogram suite and other programs. The latest major update and the extension of the program are presented here. The update includes new features, as well as improvements in the GUI and the underlying decision-making system.XDSAPPis freely available for academic users.

A Demonstration Model of a Mobile Expert System with Augmented Reality User Interface Supporting M-28 Aircraft Maintenace / Prototyp Przenośnego - Ekspertowego Systemu Z Rzeczywistoścą Rozszerzoną Do Obsługi Samolotu M-28

Abstract The paper discusses the problem of supporting aircraft diagnostic and maintenance processes. A possibility of usage of modern technologies, that could facilitate aircraft’s maintenance procedures and increase safety of their service, is presented. A usage of a mobile device, with implemented expert system and user interface based on augmented reality technology, is suggested. Proposed system structure is presented in the paper. Also, a possibility of usage of such a system is demonstrated on M-28 aircraft simulator

A developed model of expert system interface (DMESI)

Cognitive compatibility plays an important role in the development of the human–computer interface. A good user interface will lead to better user/expert system interaction and task performance. In this study, we examined what and how cognitive types affect problem-solving and analyzed the theoretical development of the relationship between human cognition and the use of intelligent machines in the domain of maintenance. The implementation of the knowledge acquisition (KA) presented the development process of the maintenance protocol which derived from using ICAM DEFinition0 (IDEF0) and Data Flow Diagram (DFD). From the maintenance process modeling, the formal representation of what the user does with the resulting interface can be defined. The knowledge base of the system is represented by a fault decision tree diagram, and is incorporated to communicate between the maintainers and the computer. Furthermore, we also evaluated and compared the effectiveness of expert system interface with the traditional maintenance handbook. As a case study, a fault recovery expert system for the Maintenance Department of the diesel engine bus system of Taipei City has been developed. Findings of the study have important implications in expert system interface design, including the specific features of changeability, traceability, plenitude, and qualitative description in this maintenance area.

The Influence of an Expert System for Test Ordering and Interpretation on Laboratory Investigations

The Laboratory Advisory System (LAS) is an expert system interface that works interactively with clinicians to assist them with test selection and result interpretation throughout the laboratory investigation of a patient. To study the influence of the LAS on laboratory investigations, a repeated-measures experiment using clinical vignettes was conducted. To collect baseline data on how laboratory investigations are currently conducted, clinicians investigated one-half of the vignettes using a conventional (noncomputer) approach. To determine the influence of the LAS on clinicians' behavior, the other half of the vignettes were investigated using the LAS. Clinicians using the LAS (compared with conventional practice) ordered fewer laboratory tests during the diagnostic process (mean, 17.8 vs 32.7), completed the diagnostic workup with fewer sample collections (mean, 5.8 vs 7.5), generated lower laboratory costs (mean, $194 vs $232), shortened the time required to reach a diagnosis (mean, 1 day vs 3.2 days), showed closer adherence to established clinical practice guidelines, and exhibited a more uniform and diagnostically successful investigation. The LAS enhances the outcome of the investigation and improves laboratory utilization.

3D Hydrogeological Modelling with an Expert GIS Interface

Geographical Information Systems provide a powerful tool for creating three-dimensional (3D) datasets for sophisticated hydrogeological models. The article describes a GIS with an expert system interface developed for generating 3D hydrogeological frameworks. The system integrates 2D images of elevation and geology and vertical profile data. Application of the expert GIS to a complex aquifer in South Eastern Sweden is described.

Material Specifications of Advanced Ceramics and Other Issues in the Use of Property Databases with Corrosion Analysis Models

Abstract The growing interest in linking analysis models with distributed materials property databases gives rise to new database design requirements. This paper discusses the conditions encountered in the modeling of the corrosion of a ceramic material as a time-dependent phenomenon. In the corrosion of ceramics, numerous distinct contributing processes occur in different regions of the specimen simultaneously. These different regions usually have different compositions, native microstructures, and environmentally intrusive agents. Both predictive modeling efforts and post-test diagnostic analyses, therefore, require chemical and physical property data that are related to the specific material substructures. There are significant problems in the practice of representing such information in general-purpose materials property databases. The essential issues pertain to the form of the representation, the accessibility of the data, and the uniqueness of the value set. This paper addresses these issues in the context of a multipurpose database into which access is needed by an automated, external, analysis program. The corrosion of silicon carbide is used as a prototypic case in discussing the standards for the database, the expectations of the user, and the implications of the practical design of the property database. It is concluded that the required analysis tools include the model with constraints on the material and the environment, a property database that distinguishes the material's substructure types and locations, a reactions database for all significantly reacting species in the system, and an expert system interface to assess the performance level options available by means of the property data.

Results of Egyptian unified grid hourly load forecasting using an artificial neural network with expert system interface

This paper presents the hourly load forecasting results of the Egyptian unified grid (EUG). The technique is based on a generalized model combining the features of ANN and an expert system. The above methodology makes the technique robust, updatable and provides for operator intervention when necessary. This property makes it especially suitable for the EUG where the load patterns are influenced mostly because of social activities, and weather contributes very little to load forecast. For example, many social occasions depend on religious preferences which cannot be decided well in advance. This technique has been tested with one year data of EUG during 1993. The results clearly demonstrate the advantage of the above methodology over statistical based techniques. The average absolute forecast errors for the proposed methodology is 2.63% with a standard deviation of 2.62% whereas, the conventional multiple regression method scores an average absolute error of 4.69% with a standard deviation of 4.03%.

Real-time expert systems interfaces, cognitive processes, and task performance: an empirical assessment.

In this experiment we investigated the effect of different real-time expert system interfaces on operators' cognitive processes and performance. The results supported the principle that a real-time expert system's interface should focus operators' attention on where it is required most. However following this principle resulted in unanticipated consequences. In particular, it led to inferior performance for less critical, yet important cases requiring operators' attention. For such cases operators performed better with an interface that let them select where they wanted to focus their attention. Having a rule generation capability improved performance with all interfaces but did so less than hypothesized. In all cases performance with different interfaces and a rule generation capability was explained by the effect of the interfaces on cognitive process measures.

Human cognition and the expert system interface: mental models and inference explanations

Variables affecting user/expert system interaction are evaluated empirically, and theoretical development of the relationship between human cognition and the use of intelligent machines is addressed. The hypotheses are that a good mental model will lead to increased user/computer interaction and performance and that graphic inference explanations will lead to higher performance than textual explanation. The examination of these hypotheses, as well as the cognitive processing underlying them, contributes directly to expert system interface design principles, as well as to theoretical development of the role of mental models in the understanding and use of dynamic, complex systems. Based on Newell and Simon's (1972) theory of problem solving and the concept occurring in a problem space, human interaction with expert systems is quantified, relevant search strategies and directions are identified, and a theory of mental models of complex, dynamic systems is developed. The basic findings are that the user must have a good understanding (i.e., good mental model) of the expert system's reasoning process, and that the user must effectively understand the information present in the expert system's inference explanations.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

An expert system interface for an identification program

This paper describes an expert system interface, named (ihs), for the interactive data analysis and system identification program Idpac. The interface works as an intelligent help system. The system is completely noninvasive and uses the previous command history to understand what the user is doing and gives help according to this. This way of monitoring the user's activities is called the command spy strategy. Scripts are used for representing procedural knowledge, and production rules for diagnostic knowledge. The system has been implemented and a knowledge database handling system identification with the maximum-likelihood method has been developed. An example run with the system is included.

ISI - An environment for the engineering use of general purpose simulation languages

Present day approaches to discrete event simulation can be broadly classified as using either special purpose data-driven simula tion systems or general purpose simulation languages. Although the latter embrace a far wider range of applications and offer much greater flexibility in modeling for a particu lar application, their user base is restricted by the high level of expertise required. An Expert System interface to general purpose simulation languages, ISI (the Intelligent Simulation Interface), is pre sented here. Models are constructed and simulation runs are performed in an integrated environment comprising interactive menu-driven graphics, a knowledge base system and a general purpose simulation language. The features of ISI include hierarchical model construc tion, interactive experiment specification, automatic code generation, run-time animation and interactive graphical post- processing of results. An example case study is presented illustrating the main aspects of ISI. The ISI interface is shown to extend a general purpose language into an intelligent simulation environment.

Expert system interface to hazard prediction models

Information available at an accident scene involving the release of hazardous materials is generally insufficient and sometimes conflicting. Many times even the names of chemicals are not available to the emergency response personnel. In such cases, hazardous material behavior models alone are of little help. What is needed is a knowledge-based system which can determine with limited data from accident locations the specific chemical released (or at least the class of chemicals involved) and then exercise the appropriate hazard prediction models. A rule based system is being developed by TMS as an add-on to the hazard assessment software system. This Expert System is expected to be used for chemical accident planning and analysis. It contains facts and rules about hazardous chemicals and their physical and chemical characteristics and possible scenarios of behavior dependent on the release and environmental conditions. The system uses this information and the responses to a set of interactively entered data to identify the chemical by eliminating chemicals which do not match the released substance. Then, behavior scenarios for the chemical are identified and applicable models are executed. This paper describes our overall approach to the development of this expert system interface. The procedure is illustrated with a specific example.

The Knowledge Database used in an Expert System Interface for IDPAC

This paper describes an expert system interface for a program for system identification. It works as an intelligent help system for the CAD program Idpac. The knowledge database is built with scripts and rules. Scripts are used for representing procedural knowledge and production rules for diagnostic knowledge. The current version of the database can perform system identification with the maximum-likelihood method.

The second generation intelligent user interface for the crustal dynamics data information system

The National Space Science Data Center (NSSDC) has initiated an Intelligent Data Management (IDM) research effort which has as one of its components the development of an Intelligent User Interface (IUI). The intent of the IUI effort is to develop a friendly and intelligent user interface service that is based on database management system (DBMS), expert systems, natural language processing, and graphics technologies. This article presents the results of the project on the second generation interface to NASA's crustal dynamics database. In general, the system spans a local Sun 3/260 scientific workstation connected to the VAX 11/780 central system. Instead of using a database query language, the user uses the expert system to advise the user in the construction of English queries, which are then sent to either a local or a central natural language front-end to the database. On a systems level, the expert system interface is written in the Automated Reasoning Tool (ART), Lisp, C, and Fortran and resides on the Sun 3/260. Also, the Natural Language components are written using the THEMIS natural language front-end and the NLI DataTalker and are connected to the ORACLE and the Sybase DBMS, respectively. Lastly, the crustal dynamics database and THEMIS reside on the VAX 11/780.