专家系统在生产制造系统（MES）中的应用

介绍了生产制造系统(MES)。对MES工程最核心的生产计划模块选用了专家系统来实现其功能。引进了STEELPIA平台的专家系统模型。通过搜索知识库的专家知识最终出钢,轧钢的作业指示。对补充到专家系统的知识库中的部分浇铸的调度策略的优化过程作了详细地描述。     

Medical expert assessment in civil and criminal law--stand for evaluating medical expert assessment

The standard for the assessment of the medical expert opinion is defined by the high demands expected from the judgement of a high court: Objectiveness, solid knowledge, self-criticism, in contestability in diction and firmness in the argumentation. From the legal point of view, the knowledge of the medical expert witness has to clearly go beyond the knowledge of his profession. The obligation for objectiveness is the basis of expert witness' activity. From the medical point of view, the physician has to take into account during the preparation of his expert assessment that structural deficiency of the personnel and surgical equipment of a department for surgery frequently plays a role due to the development of surgery to high tech medicine and the hospital physician cannot affect this. It is necessary for a physician as an expert witness to have basic knowledge about the evidence law and the medical liability process. On the other hand, judges and lawyers should basically know the medical way of thinking.     

Application of a case-based expert system to orthodontic diagnosis and treatment planning: a review of the literature

Computer expert systems are being utilised increasingly in medical fields to assist diagnosis and treatment planning. Traditional rule-based expert systems have some limitations when applied to orthodontic diagnosis and treatment planning. These limitations may be avoided by using a case-based system which is a particular type of expert system that uses a stored data bank of previously-treated cases to provide the knowledge for solving new treatment problems. This article reviews the use of expert systems for orthodontic diagnosis and treatment planning, outlines the rationale, processes and advantages of case-based systems, and gives examples of the application of this technology in medical fields.     

Acquiring background knowledge for machine learning using function decomposition: a case study in rheumatology

Domain or background knowledge is often needed in order to solve difficult problems of learning medical diagnostic rules. Earlier experiments have demonstrated the utility of background knowledge when learning rules for early diagnosis of rheumatic diseases. A particular form of background knowledge comprising typical co-occurrences of several groups of attributes was provided by a medical expert. This paper explores the possibility of automating the process of acquiring background knowledge of this kind and studies the utility of such methods in the problem domain of rheumatic diseases. A method based on function decomposition is proposed that identifies typical co-occurrences for a given set of attributes. The method is evaluated by comparing the typical co-occurrences it identifies as well as their contribution to the performance of machine learning algorithms, to the ones provided by a medical expert.     

Computer-assisted diagnosis of postmenopausal osteoporosis using a fuzzy expert system shell

This paper shows how the AMDIS (Automated Medical Diagnosis with Intelligent Systems) integrated system can be employed to build a fuzzy medical expert system in the domain of postmenopausal osteoporosis. The fundamental aims of the expert system are to standardize knowledge and support physicians in the early detection of postmenopausal osteoporosis. A wide range of diagnostic situations has been considered for both categories of the disease, with judgments that range from disease is excluded to disease is definite. The salient aspects of the approach are the use of fuzzy logic as an analytic language for the representation and manipulation of knowledge and strategies and the integration of structured interview techniques and learning-by-example to address the knowledge acquisition task.     

Rheumatic chorea

Medicoeconomic standards (MES) became very popular in many regions of Russia as a unit for assessing the monetary relationships between hospitals and insurance companies within the framework of obligatory medical insurance. However, rather often the standards are introduced by voluntary solutions without due consideration for the specific features of a territory, this involving the risk of a formalistic approach to the use of MES. Regulations have been designed for the experiment on comparison of the medical standards which have been approved and the actual treatment technology in the hospitals of Moscow (actual volumes, bed-days, and cost of treatment). Such an experiment will help assess the current MES as far as it concerns their correspondence to practical medical care and will be conducive to their improvement and to the creation of new models of MES.     

Quality assurance and risk management in gynecology and obstetrics]

The predominance of medical experts in hearings on so-called professional malpractice has frequently been bemoaned, but is indispensable since lawyers lack the necessary knowledge and requisite expertise. Court decisions are therefore essentially dependent on the quality of expert medical opinions, which in turn are dependent on the professional competence of the expert and on whether the expert is aware of the judicial demands made of him, i.e. whether the expert correctly understands his status and function within the scope of the civil or criminal proceedings. For example,the fact that court practice allows for differing standards (i.e. that medical standards can vary within limits) is important for the expert's appraisal, as is also knowing to what extent he is bound by the assignment and which requirements apply for proving causality (i.e. of an error leading up to damage) in civil and criminal proceedings. Strict objectivity, comprehensible language, restriction to one's own special field, preparation of the report within a reasonable time, intellectual integrity, no dealing with legal issues, ex ante assessment of the case and personal responsibility for the opinion are other important precepts that must be adhered to in order to avoid a miscarriage of justice. Quality control as exercised by specialised experts is therefore of vital significance.     

Maintenance of cardiovascular risk factor changes among middle-aged women in a lifestyle intervention trial

This paper proposes and defends the small worlds hypothesis, which states that expert physicians organize diagnostic knowledge on the basis of similarities between disease categories, forming 'small worlds' consisting of small subsets of diseases and their distinguishing features. Examining existing data from several previous studies, the authors provide support for the small worlds hypothesis and for a characterization of the process of expert medical diagnostic reasoning as a succession of limited comparisons involving related diagnostic hypotheses. In one study, subjects were presented clinical endocrine cases one statement at a time and were prompted to think aloud after presentation of each statement. A combination of discourse and protocol analysis techniques were used to investigate hypothesis generation and evaluation. In another study, dialogues from doctor-patient interviews were examined. It was found that expert subjects rapidly select relatively small sets of plausible diagnostic hypotheses (small worlds) and focus on the most relevant medical findings that distinguish among the diseases in such small worlds. Results from both studies indicate that expert physicians use efficient strategies for discriminating among these alternative hypotheses in a stepwise process. In contrast, non-experts often generate large numbers of possible diagnostic hypotheses, belonging to widely differing disease categories. The results provide empirical support for the theoretical basis of small worlds. The implications of these results for the study of medical expertise and knowledge engineering are discussed, as well as considerations for the development of decision support systems.     

新钢三期工程MES系统冶炼-连铸-轧制一体化计划编制分析

进行冶炼-连铸-热轧一体化计划问题编制,必须对炼钢、连铸、热轧三个阶段的生产约束因素进行系统分析.作者根据在建立、实施热轧MES系统计划管理模块时的心得,对设计计划管理模块分阶段进行了业务分析,对同类型企业进行一体化计划编制或对MES系统计划模块的规划有一定参考作用.     

Intracellular distribution of ampicillin in murine macrophages infected with Salmonella typhimurium and treated with (3H)ampicillin-loaded nanoparticles

A performance evaluation of the DIABETES rule-based expert system prototype for clinical decision making is presented. The system facilitates multiple insulin regimen and dose adjustment of insulin dependent Type I or II diabetic patients. The study was performed on 600 subjects from two diabetological centres and three diabetological offices of Greek hospitals. The responses of the attendant medical doctors were compared with those of the DIABETES system, with the aid of a specifically devised valuation range (0-5 degrees, 0 indicating full agreement and 5 full disagreement). The capabilities and the weakness of the system in terms of its practicality for decision support in assisting therapy of diabetes mellitus by blood glucose monitoring and subsequent insulin dose adjustment are discussed. The potential benefits of decision support systems for diabetic patient management are seen to be the cost saving they provide in terms of man-hours of verbal instruction by medical experts, the support in terms of objective and consistent decision making, as well as the recording of medical knowledge in the ill-defined field of insulin administration, thus aiding the education and training of medical personnel.     

Clinically silent microemboli in patients with artificial prosthetic aortic valves are predominantly gaseous and not solid

BACKGROUND AND PURPOSE: Microembolic signals (MES) are frequently observed by transcranial Doppler ultrasound after prosthetic heart valve implantation. Whether these MES are due to solid or gaseous particles is uncertain. We hypothesized that MES are gaseous and that if they are due to cavitation effects, their occurrence should respond to changes of dissolved oxygen concentration in the blood. METHODS: Transcranial monitoring of MES was performed in five patients with prosthetic aortic valves, who inspired 100% oxygen through a facial mask. In one patient 100% oxygen was administered under hyperbaric (2.5 kPa) conditions in a hyperbaric chamber. RESULTS: Inspiration of 100% oxygen reduced the total number of MES from 96/30 min to 2/30 min. Increasing the concentration of dissolved oxygen in the hyperbaric chamber led to an increase from 0.3 MES per minute (1.0 kPa) to 0.9 MES per minute (2.5 kPa). CONCLUSIONS: The dependence of occurrence of MES in patients with prosthetic cardiac valves on the oxygen partial pressure in blood provides strong evidence that these microemboli are gaseous.     

低成本高效益高炉专家系统开发的理念与实践

当前,中国钢铁工业面临的难题是既要多用低价矿,又要维持高炉操作的平稳性和安全性,又要维持甚至降低炼铁的焦比和燃料比。大力开发应用高炉专家系统可以帮助钢铁厂解决这些难题。提出了适合中国国情的低成本高效益高炉专家系统的开发理念,即依靠国内力量,以企业最关注的高炉炉温和顺行状况的准确监测与预报为核心功能,以建议模式运行,主? 捎媚：评砑际踅⑹Ｐ停哂泻侠淼淖匝肮δ埽ü隡ES等网络技术的结合实现系统的长期稳定运行。该理念已成功应用于韶钢3200m38号高炉智能专家系统。两年多来该专家系统一直运行正常,在稳定炉温、减少炉况失常、提高作业率、降低燃料比、扩大喷煤比、提高生铁产量等方面发挥了重要作用。     

Replication of clinical innovations in multiple medical practices

BACKGROUND: Many clinical innovations had been successfully developed and piloted in individual medical practice units of Kaiser Permanente in North Carolina during 1995 and 1996. Difficulty in replicating these clinical innovations consistently throughout all 21 medical practice units led to development of the interdisciplinary Clinical Innovation Implementation Team, which was formed by using existing resources from various departments across the region. REPLICATION MODEL: Based on a model of transfer of best practices, the implementation team developed a process and tools (master schedule and activity matrix) to quickly replicate successful pilot projects throughout all medical practice units. The process involved the following steps: identifying a practice and delineating its characteristics and measures (source identification); identifying a team to receive the (new) practice; piloting the practice; and standardizing, including the incorporation of learnings. The model includes the following components for each innovation: sending and receiving teams, an innovation coordinator role, an innovation expert role, a location expert role, a master schedule, and a project activity matrix. Communication depended on a partnership among the location experts (local knowledge and credibility), the innovation coordinator (process expertise), and the innovation experts (content expertise). RESULTS: Results after 12 months of working with the 21 medical practice units include integration of diabetes care team services into the practices, training of more than 120 providers in the use of personal computers and an icon-based clinical information system, and integration of a planwide self-care program into the medical practices--all with measurable improved outcomes. CONCLUSION: The model for sequential replication and the implementation team structure and function should be successful in other organizational settings.     

Medical legal aspects of clinical monitoring

Modern laboratory technology has spawned a plethora of techniques for measuring and monitoring drug concentrations and body constituents; but the availability and frequent over-use of these determinations, some of which are exotic and require specialized personnel and expensive apparatus have further escalated the already high cost of medical care in several ways. The specter of medical malpractice suits has compelled the physician to practice defensive medicine including ordering unnecessary monitoring procedures, particularly for drug levels. Further impetus has been superadded by the courts and state legislatures; for example, phenylketonuria (PKU) determinations are mandatory in almost all states. Court rulings have held that "common knowledge" not expert testimony, may be all that is necessary to hold the doctor culpable for not ordering a test; nor is expert testimony necessarily required if the Physicians Desk Reference (PDR) or drug company insert recommends that certain tests or monitoring procedures be performed and the doctor fails to comply. (PSRO) programs will force further conformity, leave less to the discretion of the physician and place the government in an ever more regulatory role. Professional societies should take cognizance of the impropriety and danger of the government dictating diagnosis and treatment and should launch a vigorous program to scrutinize pending regulatory legislation and to make official and informed representations to appropriate legislators.     

八钢中厚板MES系统设计与实践

以八钢中厚板MES系统为研究对象,阐述了八钢中厚板MES系统的功能,对系统的软件结构及作业流程进行了详细论述.阐明了八钢中厚板MES系统的设计实施,解析了中厚板MES系统对制造执行所起作用.     

人工智能在高炉控制中的应用

应用于高炉控制的人工智能模型主要有：高炉专家系统，神经网络模型及神经网络专家系统。高炉专家系统虽然具有知识推理的透明性，但却不具备学习功能；神经网络模型虽然具有很强的自学习功能，但又不具备知识推理的透明性；神经网络专家系统则同时具备两者的优点。     

MEDUSA: a fuzzy expert system for medical diagnosis of acute abdominal pain

Even today, the diagnosis of acute abdominal pain represents a serious clinical problem. The medical knowledge in this field is characterized by uncertainty, imprecision and vagueness. This situation lends itself especially to be solved by the application of fuzzy logic. A fuzzy logic-based expert system for diagnostic decision support is presented (MEDUSA). The representation and application of uncertain and imprecise knowledge is realized by fuzzy sets and fuzzy relations. The hybrid concept of the system enables the integration of rule-based, heuristic and case-based reasoning on the basis of imprecise information. The central idea of the integration is to use case-based reasoning for the management of special cases, and rule-based reasoning for the representation of normal cases. The heuristic principle is ideally suited for making uncertain, hypothetical inferences on the basis of fuzzy data and fuzzy relations.     

Expert Systems for Construction Project Monitoring

Potential applications of knowledge based expert systems in the area of construction project monitoring and control are described. Originally developed from research in artificial intelligence, these systems are computer programs that can undertake intelligent tasks currently performed by highly skilled people. While some project monitoring can be accomplished by algorithmic procedures, the capability of knowledge based expert systems to deal with illstructured problems and to be extensively modified over time make them desirable for application in this area. Sample applications and heuristic rules in scheduling and inventory control are provided.     

高炉冶炼专家系统知识库的建立

阐明了知识库是高炉冶炼专家系统的核心和基础,介绍了高炉冶炼专家系统知识库的知识获取方法、知识表示方式和知识存储结构,探讨了高炉冶炼专家系统知识库的建立方法。     

Mortality in employees of a Scottish paper mill

The complexity of the monitored data available in modern intensive care units suggests that they may be best processed, for presentation to medical staff, by expert system techniques. However, standard expert system shells are ill-fitted to either the basic sequential monitoring tasks of data acquisition and storage, or to handling the temporal considerations inherent in monitoring and in the recognition and processing of sporadic alarm signals. A solution to this dilemma is described: an expert system that has an appropriately designed inference engine and manages data acquisition via a medical information bus (MIB). Use of this MIB standard allows great flexibility as regards the monitoring apparatuses employed; in particular, the connection or disconnection of any apparatus is recognised and triggers the automatic reconfiguration of the network.