A belief maintenance scheme for hierarchical knowledge-based image analysis systems

A variety of belief maintenance schemes for image analysis have been suggested and used to date. In the recent past, several researchers have suggested the use of the Dempster-Shafer theory of evidence for representation of belief. This approach appears to be particularly suited for knowledge-based image analysis systems because of its intuitively convincing ways of representing beliefs, support, plausibility, ignorance, dubiety, and a host of other measures that can be used for the purpose of decision making. It also provides a very attractive technique to combine these measures obtained from disparate knowledge sources. In this article, we show how the Dempster-Shafer theoretic concepts of refinement and coarsening can be used to aggregate and propagate evidence in a multi-resolution image analysis system based on a hierarchical knowledge base.     

A fuzzy set theoretic framework for knowledge-based simulation

Complex systems such as an industrial enterprise operating in a physical, biological, socioeconomic environments generally have many ill defined or imprecisely known parameters which are typically approximated by exact numbers or represented with random variables. Fuzzy set theory is a promising alternative for explicitly treating these aspects of a system. This paper describes a fuzzy set theoretic formalism for knowledge-based simulations. A prototype system is being implemented in Mathematica.     

A knowledge-based environment for modeling and simulating softwareengineering processes

The design and representation schemes used in constructing a prototype computational environment for modeling and simulating multiagent software engineering processes are described. This environment is called the articulator. An overview of the articulator's architecture identifying five principal components is provided. Three of the components, the knowledge metamodel, the software process behavior simulator, and a knowledge base querying mechanism, are detailed and examples are included. The conclusion reiterates what is unique to this approach in applying knowledge engineering techniques to the problems of understanding the statics and dynamics of complex software engineering processes     

Structure adaptation of hierarchical knowledge-based classifiers

This paper introduces a new method to identify the qualified rule-relevant nodes to construct hierarchical neuro-fuzzy systems (HNFSs). After learning, the proposed method analyzes the entire history of activities and behaviors of all rule nodes, which reflects their levels of involvement or contribution during the process. The less qualified rule-relevant nodes can then be identified and removed, reducing the size and complexity of the HNFS. Upon the repetitive learning process, the method may be repetitively applied until a satisfactory result is obtained, simultaneously improving the performance and reducing the size and complexity. Incorporated with the method is a new HNFS architecture which addresses both the scalability problem experienced in rule based systems and the restriction of the “overcrowded defuzzification” problem found in hierarchical designs. In order to verify the performance, the proposed method has been successfully tested against five well-known classification problems whose results are provided and then discussed in the concluding remarks.     

A knowledge-based prototyping environment for construction of scientific modeling software

Over the past 30 years, scientific software models have played an increasingly prominent role in the conduct of science. Unfortunately, scientific models can be difficult and time-consuming to implement, and there is little software engineering support specifically available for constructing scientific models. Because these models are not easily specified to scientifically-naive programmers, and because the scientist requires intimate knowledge of the code to conduct experiments, many scientists implement their own models. This coding activity takes valuable time away from their primary scientific mission. We have developed a knowledge-based software development tool that assists scientists in prototyping scientific models. With a specialized graphical user interface, the scientist constructs a high-level visual specification that captures the essential computational dependencies in the desired model. The system uses its scientific domain knowledge to ensure that the model being built is consistent and coherent. The final product is an executable prototype of a scientific model. Our tool accelerates the model-building process and eliminates the scientist's need to program in a formal language. Furthermore, the models developed with this tool are easier to understand and reuse than typical low-level scientific modeling code. At present, models developed with our system are restricted to those involving non-coupled algebraic and first order ordinary differential equations. Research is ongoing to lessen this restriction and support models with simultaneous equations.     

A simulation environment for multimodeling

Large-scale systems are typically quite difficult to model. Hierarchical decomposition has proven to be one successful method in managing model complexity, by refining model components into models of the same type as the lumped model. Many systems, however, cannot be modeled using this approach since each abstraction level is best defined using a different modeling technique. We present amultimodel approach which overcomes this limitation, and we illustrate the technique using a fairly simple scenario: boiling water. State and phase trajectories are presented along with an implementation using theSimPack simulation toolkit. Multimodeling has provided us with a mechanism for building models that are capable of producing answers over a wide range of fidelity. The author is grateful for partial funding of this research through a grant from the Florida High Technology Council.     

A knowledge-based computer environment for the conceptual design ofsmall electromechanical appliances

A knowledge-based computer environment that supports the concurrent engineering of small electromechanical appliances such as kitchen appliances and lighting is described. The environment integrates and provides active assistance for the following engineering activities: specification acquisition, conceptual design and redesign, and qualitative simulation. The design environment is examined by reviewing the steps in a redesign sequence that transforms a manual juicer into an electric juicer     

ASPIS: a knowledge-based CASE environment

The authors report on ESPRIT Project 401, building the Application Software Prototype Implementation System (ASPIS) for computer-aided software engineering (CASE). ASPIS uses artificial intelligence techniques in a software-development environment. The goal is to encourage a more flexible and effective software-development life cycle, smoothing the transition between user needs, analysis, and design. The focus is on a knowledge-based assistant called the analysis assistant, the primary goal of which is to provide the user with domain-dependent suggestions and advice during a particular method phase     

Granularity issues in a knowledge-based programming environment

Marvel is a knowledge-based programming environment that assists software development teams in performing and coordinating their activities. While designing Marvel, several granularity issues were discovered that have a strong impact on the degree of intelligence that can be exhibited, as well as on the friendliness and performance of the environment. The most significant granularity issues include the refinement of software entities in the software database and decomposition of the software tools that process the entities and report their results to the human users. This paper describes the many alternative granularities and explains the choices made for Marvel.     

A lexicon for knowledge-based MT

In knowledge-based machine translation (KBMT), the lexicon can be specified and acquired only in close connection with the specification and acquisition of the world model (ontology) and the specification of the text meaning representation (interlingua) language. The former supplies the atoms for the specification of text meaning and provides world knowledge to support the inference processes necessary for a variety of disambiguation and meaning assignment operations. The latter is necessary for the formulation of the semantic zone of the lexicon entries, which can be viewed as containing the static building blocks of the text meaning representation. This is the view taken in the Mikrokosmos KBMT project.     

A framework for knowledge-based control

A framework for knowledge-based control is proposed. The approach presented is suitable for control systems and control support of systems which have no adequate mathematical models. Thus, the control is performed by using knowledge engineering methods rather than pure mathematical control methods. The domain expert's knowledge is assumed to be encoded in the form of simple statements (facts) and special reasoning rules, which form the core of the Knowledge-Based Control System (KBCS). The control system reads the input information, and on the basis of the current state of its knowledge base, together with the application of supplied inference rules updates the knowledge base and performs the required control actions. Moreover, some inference control knowledge, reflecting the expert's way of reasoning, is to be incorporated in the KBCS. The main idea of the system consists of selecting an appropriate set of actions to be executed, with regard to the current state specification and the control goal given. An abstract mathematical model of the control process is formulated and a suitable language for knowledge representation is proposed. The reasoning scheme is discussed and the structure of the control system is outlined. A representative application example is provided.     

An interface for hierarchical modeling in object-oriented simulation

A graphical interface for a new simulation development environment is presented. This interface is described in relation to information hiding and visual layers. In the simulation development environment distinct types of entities may easily be modeled. This results in simulation models which are good representations of real world systems. We introduce two nodes which facilitate discrete event simulation modeling. Sequences of tasks may be assigned to various entities in a queue/server node. A multi-queues/multi-servers node permits the modeler to formulate server selection rules and queue selection rules for each type of entity. Servers may also have a queue selection rule.     

面向对象开发DeltaV系统仿真支撑环境

DeltaV是一种管理FFCS(Foundation Fieldbus Control System)的软件系统,用面向对象技术开发其仿真支撑环境,建立了流程图组态类库,包括设备类、仪表类、物流类等等,每一类都定义有如类型、种类、方向、位置、颜色、标记等属性,同时定义了对象的建立、标记、移动和缩放等方法,可灵活地增减类库成员和改变属性和方法。     

Negotiation in a knowledge-based concurrent engineering design environment

Abstract: Computational support for concurrent engineering design presents a number of issues in the design of knowledge-based systems. A fundamental concern is the need to provide the life-cycle perspective in recommending design alternatives. It is argued that such a complex knowledge-based system should be distributed, due to the inherent problems with large knowledge bases and the maintenance of consistency. Inconsistent local views of a problem and different priorities on design issues are expected between different knowledge-based design perspectives. These inconsistencies and different priorities will lead inherently to conflict which has to be resolved. This paper addresses the issues and key variables in conflict resolution and presents a strategy that can be applied for managing the conflict resolution process. We propose negotiation as the method of analysing a conflict situation, applying an appropriate conflict resolution strategy and monitoring its performance. We present an overview of the nature of conflict and some conflict resolution strategies, and see in what situations certain strategies are appropriate.     

Reconstruction of three-dimensional objects using a knowledge-based environment

This paper presents a knowledge-based technique forunderstanding and reconstructing a class of three-dimensional objects from their two-dimensional orthographic views commonly found in machine drawings and blueprints. The reconstruction procedure uses a volume-oriented approach and views a complex part as composed of a number of primitive subobjects. These subobjects are recognized using a model-guided recognition scheme, utilizing characteristic patterns of the primitives in different views. Features such as protrusions and cavities are recognized and the composite part is transferred to a CAD data base.     

A knowledge-based system for disk-drive diagnostics

A frame-based, backward-chaining knowledge-based system was developed to help the diagnostic process in the manufacture of computer high-end disk drives. The nature of the diagnostic and testing process is presented and the methodology used to develop the knowledge-based system is explained. The development and consultation environments are introduced and the final system is described. The improvements and results obtained with the utilization of this knowledge-based system in a factory environment are also included.