Fuzzy logic in medical expert systems

30 Years after its introduction, fuzzy logic remains an area of active research. As can be seen from the examples given here, in most instances there is no single generalization from binary logic to fuzzy logic that is clearly best or correct. Many self-consistent systems have been developed which reduce to 2-valued logic if all parameters are crisp. The choice of a model depends at this point on how well each functions in practice. For medical expert systems, the theoretical framework of fuzzy logic provides a rich environment from which to choose. The adequacy of each approach is born out by the success of the model in practice     

Evaluation of diagnostic results by Bayes' theorem

Application of Bayes' theorem for the evaluation of diagnostic results of electric facilities is described. A concept of risk assessment method based on the diagnosis results is proposed and the effects of various parameters on the risk are clarified. Based on these results, a rational renewal scheme using diagnostic results is proposed. In addition, the prior probability based on the data of actual facilities is investigated and it is found that the data available so far is insufficient and more data are required for the detailed analysis. © 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Using the algebraic sum method in medical expert systems

In the development of a medical expert system, the choice of algorithms is an important consideration. According to 1979 statistics, some 60% of medical expert systems were based on the Bayes method, 30% were based on a linear discriminant function, matching handle and criterion tree, and 10% were based on other algorithms. Overall diagnostic accuracy rates were generally about 90%. Although the Bayes method has been used very widely, it has some limitations. Its two assumptions are difficult to satisfy in computer-assisted diagnostic systems, and it does not do well in solving the contradiction between the low frequency of a disease manifestation and the high specificity of the manifestation. A weighted summation method can better solve this problem, since the diagnostic value can be adjusted according to the real importance of each item of diagnostic information. The weighted summation method has been widely used in the development of many medical expert systems, such as the earliest expert system of traditional Chinese medicine: “The Computer Program for the Diagnosis and Treatment of Liver Disease Based on the Principle of Dialectical Treatment”. It is concluded that the algebraic sum method is an efficient, simple, and convenient mathematical model for the development of medical expert systems     

Adaptation problems in expert systems

Expert system (ES) theory problems have been traditionally considered without any essential connection with common control problems. However, nowadays, because of progress in ES theory development in practice and because of its wide use for solving complex control problems, new items in this field of research are being stressed, many of which are connected with traditional automation control. The combined study of adaptation and ES problems makes it possible to draw significant practical conclusions for systems of both types. In this work an analysis of general problems and of possible approaches to solving them in some special types of ESs based on Bayes inference is carried out. The main attention is focused on such ES characteristics as: (i) inference stability (with respect to variations in probabilistic approximation measures of rule truth); (ii) knowledge base adaptation (rule modification and new rule creation or approximation measure rule tranformation); (iii) knowledge base consistency maintenance.     

Applying multimedia to medical imaging

We present the architecture of MediaStation 5000 and its applications in medical imaging. As a medical imaging workstation, MediaStation 5000 satisfies the basic requirement of fast image display and processing. All the important image display, manipulation, and processing functions can be executed in real time on 512×512 images, providing instant feedback to the user     

Applying static excitation systems

Many power generation plants in the pulp and paper industry are faced with high maintenance and downtime due to the excitation system. DC field breakers, motor driven rheostats, rotating exciter failures, commutator deterioration, and replacement parts for the automatic voltage regulator (AVR) are just a few of the problems typical of these aged power plants. The result is high overhead and potentially long down time of the generator system. The replacement of the rotating exciter and associated equipment for static excitation systems provides the positive solutions to these problems. The static exciter offers the design flexibility of easy retrofit for both small and larger rotating exciter systems. Additionally, it eliminates the maintenance overhead common to the brush type exciter. This article discusses the static exciter system that includes the power control devices (SCRs, also called thyristors), power transformer and automatic voltage regulator. The elimination of the DC field breaker can offer substantial cost savings. Solid state fast de-excitation circuits and its benefits are discussed. Lastly, selection criteria and application considerations are reviewed regarding types of static exciters     

Obscuring the human costs of expert systems

The growing number of artificial-intelligence applications in industry creates a tension between the hopeful perspective that the white-collar workforce will fill the increasing need for knowledge, and the reality that experts will increasingly be displaced by expert systems. The rhetoric of those who promote expert systems obscures the tension between the social programs of training and education, on the one hand, and technical fixes, on the other. To make this tension explicit, we look more closely at the criteria that applied researchers, sales engineers, marketing managers and corporate staff use to justify knowledge based system development. Examining their rationale emphasizes their attempts to advance, in whatever way they can, the technology that they identify so thoroughly with continuing research funding and growing sales orders     

Promoting the application of expert systems in short-term unitcommitment

A heuristic approach to the short-term unit commitment problem is presented. The generating unit's capacities are divided into thee categories, and then a rough 24 h-generation schedule is established. The global optimization is performed as an inference process. A prototype system is developed and tested on an IBM-386 personal computer using the C language. The ToolBook software is used to enhance the graphics capability of the package. The primary advantage of the proposed method is its short processing time for each schedule, as it schedules the generation unit commitment for a typical system in less than 2 s. The same system is examined by dynamic programming with an average running time of 20 min on an IBM 386 personal computer     

Applying sensors to automatic assembly systems

The author describes the classes of sensors that are available to the automatic assembly machine designer. Examples of each class of sensor along with a discussion of their specific benefits and problems are included. Guidelines that will aid a machine designer in the selection and application of sensors for automatic assembly systems are provided. The necessity of providing methods in the automation for verifying the sensors' accuracy is discussed     

Applying low-voltage circuit breakers in direct current systems

Low-voltage, direct current equipment in electric utility control systems, uninterruptible power systems (UPS), telecommunication systems, and elsewhere has received increasing attention in recent years. Power conditioning needs are one reason. Closer attention by regulatory agencies is another. This paper is intended to help fill a gap in available material on ratings and application characteristics of low-voltage circuit breakers in DC power systems     

Impact of expert systems: the technique dimension

Techniques used in expert system development and techniques used in the problem domain are examined. Three stages are distinguished and discussed: predevelopment, during development, and postdevelopment. Consequences of expert systems for education are considered. It is concluded that examining the social impact of expert systems by examining the technology related to expert system development is vital     

Applying a PC accelerator board for medical imaging

An AT-compatible computer was used to expand X-ray images that had been compressed and stored on optical data cards. Initially, execution time for expansion of a single X-ray image was 25 min. The requirements were for an expansion time of under 10 s and costs of under $1000 for computing hardware. This meant a computational speed increase of over 150 times was needed. Tests showed that incorporating an 80287 coprocessor would only give a speed increase of five times. The DSP32-PC-160 floating-point accelerator board was selected as a cost-effective solution to the need for more computing power. This board provided adequate processor speed, onboard memory, and data bus width; floating-point math precision; and a high-level language compiler for code development.     

Potential applications of expert systems to power system protection

Working Group D10 Applications of Expert Systems to Power System Protection of the Line Protection Subcommittee, Power System Relaying Committee, was organized in 1989 with the following assignment as finally adopted: “Survey expert system technology to identify suitable and significant applications to power system protection. Write a technical paper that introduces protection engineers to expert systems and describes several potential applications”. This paper represents the work performed by the Working Group in fulfilling its assignment. The paper is divided into sections that describe a number of potential applications thought to be significant by the members of the Working Group     

混合型电力专家系统的快速开发方法

提出一种混合型电力专家系统快速开发方法.混合型电力专家系统兼有大量数值计算和复杂逻辑推理.基于该方法,详细展示了继电保护整定计算专家系统的快速开发过程.系统分为四大模块,其中:短路计算模块包含大量的数值计算,采用Matlab语言编写;整定计算模块具有复杂逻辑推理功能,采用Clips语言编写.运用混合编程技术,嵌入以C#为宿主语言的系统主体.系统开发过程表明:该方法能显著提高混合型电力专家系统的开发效率,大大缩短其开发周期.     

混合型电力专家系统的快速开发方法

提出一种混合型电力专家系统快速开发方法。混合型电力专家系统兼有大量数值计算和复杂逻辑推理。基于该方法,详细展示了继电保护整定计算专家系统的快速开发过程。系统分为四大模块,其中:短路计算模块包含大量的数值计算,采用Matlab语言编写;整定计算模块具有复杂逻辑推理功能,采用Clips语言编写。运用混合编程技术,嵌入以C#为宿主语言的系统主体。系统开发过程表明:该方法能显著提高混合型电力专家系统的开发效率,大大缩短其开发周期。     

专家系统改进模型及其在电机声学设计中的应用

针对电机振动和噪声问题的复杂性,分析出基于规则的专家系统应用于电机声学设计具有优势;进而,考虑到现有规则库知识结构模型应用于电机声学设计存在的不足,提出了一种相对完善的改进模型。该模型采用"IF THEN SO THAT"闭环结构,引入模糊集理论与概率理论,融合了定性知识与定量知识,可以实现正向或逆向、全闭环或部分推理。在此基础上,详细论述了专家系统改进模型在电机声学设计中的应用,包括电机声学设计智能系统的功能和构成、规则库知识模型的建立、系统配置、声学设计及实验数据管理等关键技术。最后,利用电机声学设计智能系统进行声学设计。结果表明,专家系统改进模型具有先进性和实用性。     

Augmented reality systems for medical applications

Augmented reality (AR) is a technology in which a computer-generated image is superimposed onto the user's vision of the real world, giving the user additional information generated from the computer model. This technology is different from virtual reality, in which the user is immersed in a virtual world generated by the computer. Rather, the AR system brings the computer into the “world” of the user by augmenting the real environment with virtual objects. Using an AR system, the user's view of the real world is enhanced. This enhancement may be in the form of labels, 3D rendered models, or shaded modifications. In this article, the authors review some of the research involving AR systems, basic system configurations, image-registration approaches, and technical problems involved with AR technology. They also touch upon the requirements for an interventive AR system, which can help guide surgeons in executing a surgical plan