A Common Knowledge Representation for Plan Generation and Reactive Execution

<div> <p>Non-destructive testing (NDT) data in civil engineering is regularly used for scientific analysis. However, there is no uniform representation of the data yet. An analysis of distributed data sets across different test objects is therefore too difficult in most cases.</p> <p>To overcome this, we present an approach for an integrated data management of distributed data sets based on Semantic Web technologies. The cornerstone of this approach is an ontology, a semantic knowledge representation of our domain. This NDT-CE ontology is later populated with the data sources. Using the properties and the relationships between concepts that the ontology contains, we make these data sets meaningful also for machines. Furthermore, the ontology can be used as a central interface for database access. Non-domain data sources can be integrated by linking them with the NDT ontology, making them directly available for generic use in terms of digitization. Based on an extensive literature research, we outline the possibilities that result for NDT in civil engineering, such as computer-aided sorting and analysis of measurement data, and the recognition and explanation of correlations.</p> <p>A common knowledge representation and data access allows the scientific exploitation of existing data sources with data-based methods (such as image recognition, measurement uncertainty calculations, factor analysis or material characterization) and simplifies bidirectional knowledge and data transfer between engineers and NDT specialists.</p> </div>

Download Full-text

A GENERAL FRAMEWORK FOR KNOWLEDGE-BASED PATTERN RECOGNITION

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s021800148700014x ◽

1987 ◽

Vol 01 (02) ◽

pp. 189-205 ◽

Cited By ~ 1

Author(s):

F. BERGADANO ◽

L. SAITTA

Keyword(s):

Pattern Recognition ◽

Expert System ◽

Knowledge Representation ◽

General Framework ◽

Common Knowledge ◽

Learning Module ◽

Knowledge Based ◽

Recognition Phase ◽

Representation Scheme

This paper surveys a long term project, aimed at providing a general methodology for building up and maintaining an expert system oriented to Pattern Recognition problems. The methodology makes use of an integrated set of modules, performing different functions but sharing a common knowledge representation scheme. In particular, a learning module allows to acquire the knowledge automatically from a set of examples and another module performs sophisticated reasoning, on the basis of the available knowledge, during the recognition phase.

Download Full-text

Knowledge Representation and Conversion for Hybrid Expert Systems

Volume 1: 21st Design Automation Conference ◽

10.1115/detc1995-0002 ◽

1995 ◽

Author(s):

Terrence L. Chambers ◽

Alan R. Parkinson

Keyword(s):

Knowledge Representation ◽

Rapid Prototyping ◽

Expert Systems ◽

Decision Trees ◽

Common Knowledge ◽

Knowledge Engineer ◽

Knowledge Representations ◽

Functional Logic ◽

Decision Tables

Abstract Many different knowledge representations, such as rules and frames, have been proposed for use with engineering expert systems. Every knowledge representation has certain inherent strengths and weaknesses. A knowledge engineer can exploit the advantages, and avoid the pitfalls, of different common knowledge representations if the knowledge can be mapped from one representation to another as needed. This paper derives the mappings between rules, logic diagrams, frames, decision tables and decision trees using the calculus of truth-functional logic. The logical mappings between these representations are illustrated through a simple example, the limitations of the technique are discussed, and the utility of the technique for the rapid-prototyping and validation of engineering expert systems is introduced.

Download Full-text

Client-Server Approach for Managing Visual Attention, Integrated in a Cognitive Architecture for a Social Robot

Frontiers in Neurorobotics ◽

10.3389/fnbot.2021.630386 ◽

2021 ◽

Vol 15 ◽

Author(s):

Francisco Martín ◽

Jonatan Ginés ◽

Francisco J. Rodríguez-Lera ◽

Angel M. Guerrero-Higueras ◽

Vicente Matellán Olivera

Keyword(s):

Visual Attention ◽

Knowledge Representation ◽

Common Knowledge ◽

Cognitive Architecture ◽

Social Robot ◽

Knowledge Graph ◽

Distributed Knowledge ◽

Client Server ◽

The Core ◽

The Common

This paper proposes a novel system for managing visual attention in social robots. This system is based on a client/server approach that allows integration with a cognitive architecture controlling the robot. The core of this architecture is a distributed knowledge graph, in which the perceptual needs are expressed by the presence of arcs to stimuli that need to be perceived. The attention server sends motion commands to the actuators of the robot, while the attention clients send requests through the common knowledge representation. The common knowledge graph is shared by all levels of the architecture. This system has been implemented on ROS and tested on a social robot to verify the validity of the approach and was used to solve the tests proposed in RoboCup @ Home and SciROc robotic competitions. The tests have been used to quantitatively compare the proposal to traditional visual attention mechanisms.

Download Full-text

The Application of Knowledge Representation on the Design of Loading Device of Garbage Truck

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.121-126.3568 ◽

2011 ◽

Vol 121-126 ◽

pp. 3568-3572

Author(s):

Bin Wang ◽

Jie Tao ◽

Hong Pan Wu

Keyword(s):

Knowledge Representation ◽

Mass Customization ◽

Knowledge Engineering ◽

Semantic Network ◽

Common Knowledge ◽

Engineering Application ◽

Object Oriented ◽

Space Representation ◽

Loading Device ◽

Production Knowledge

To meet the requirement of mass customization of garbage truck, knowledge engineering plays an important part in modern garbage truck design. As the basis of knowledge engineering application, the principles of common knowledge representation methods were analyzed in detail, and the application places of different knowledge representation methods were presented in the paper. Finally, examples of production knowledge representation, sate space representation, object-oriented knowledge representation, and semantic network-based knowledge representation were introduced independently to show the feasibility of applying these methods on the design of loading device of garbage truck.

Download Full-text

Knowledge Representation and Conversion for Hybrid Expert Systems

Journal of Mechanical Design ◽

10.1115/1.2829175 ◽

1998 ◽

Vol 120 (3) ◽

pp. 468-474 ◽

Cited By ~ 1

Author(s):

T. L. Chambers ◽

A. R. Parkinson

Keyword(s):

Knowledge Representation ◽

Rapid Prototyping ◽

Expert Systems ◽

Knowledge Base ◽

Decision Trees ◽

Common Knowledge ◽

Knowledge Engineer ◽

Knowledge Representations ◽

Functional Logic ◽

Decision Tables

Many different knowledge representations, such as rules and frames, have been proposed for use with engineering expert systems. Every knowledge representation has certain inherent strengths and weaknesses. A knowledge engineer can exploit the advantages, and avoid the pitfalls, of different common knowledge representations if the knowledge can be mapped from one representation to another as needed. This paper derives the mappings between rules, logic diagrams, decision tables and decision trees using the calculus of truth-functional logic. The mappings for frames have also been derived by Chambers and Parkinson (1995). The logical mappings between these representations are illustrated through a simple example, the limitations of the technique are discussed, and the utility of the technique for the rapid-prototyping and validation of engineering expert systems is introduced. The technique is then applied to three engineering applications, showing great improvements in the resulting knowledge base.

Download Full-text

Ultrastructural features of prognostic significance in human oral cancer

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100123490 ◽

1992 ◽

Vol 50 (1) ◽

pp. 618-619

Author(s):

Karvita B. Ahluwalia ◽

Nidhi Sharma

Keyword(s):

Oral Cancer ◽

Squamous Cell ◽

Common Knowledge ◽

Prognostic Significance ◽

Growth Control ◽

Terminal Differentiation ◽

Squamous Cell Carcinomas ◽

Effective Therapy ◽

Invasive Potential ◽

Biological Behaviour

It is common knowledge that apparently similar tumors often show different responses to therapy. This experience has generated the idea that histologically similar tumors could have biologically distinct behaviour. The development of effective therapy therefore, has the explicit challenge of understanding biological behaviour of a tumor. The question is which parameters in a tumor could relate to its biological behaviour ? It is now recognised that the development of malignancy requires an alteration in the program of terminal differentiation in addition to aberrant growth control. In this study therefore, ultrastructural markers that relate to defective terminal differentiation and possibly invasive potential of cells have been identified in human oral leukoplakias, erythroleukoplakias and squamous cell carcinomas of the tongue.

Download Full-text