Welcome
Digital library of construction informatics
and information technology in civil engineering and construction
 

Works 

Search Results

Facilitated by the SciX project

Hits 1 to 6 of 6

Colajanni B, Fornarelli A, Giretti A, Naticchia B, Pellitteri G

ASA, An interactive assistant to architectural designers

Abstract: In the management of information for the design case reasoning seems the best fit for simulating the real designer s behaviour. In order to construct a plausible interactive assistant to architectural designers three main problems are to be solved: the way of encoding and indexing technical knowledge in order to easily recover the best starting case; the way of giving semantics to sketches; the way of coming to terms with inconsistencies generated during the process. An interactive architectural assistant is proposed based on case reasoning, managing architectural information encoded in a memory of real instances of the architectural type of reference and technical information encoded according the SfB system. Its architecture is made of two main parts. The first includes case memory, case recovery engine, abstraction engine and the design board. It manages the general and specific case knowledge in its abstract and semantics given form. The second includes the tools to generate single objects composing the architectural organism both directly and in parametric form, constraint management and consistency checking. The representation of the state of the object is twofold as a drawing in the drafting board, as a symbolic representation in the design board in which all the attributes of the object are recorded together with their relationships. The graphics of the assistant is implemented in AutoCAD environment while the alphanumeric knowledge is implemented in Kappa. The general architecture of ASA and the single modules are described, followed by a simulation of a session of work.

Keywords: case reasoning; architectural assistant; knowledge engineering

DOI:

Full text: content.pdf (825,405 bytes) (available to registered users only)

Series: w78:1993 (browse)
Cluster:
Class:
Similar papers:
Sound: read aloud.

Permission to reproduce these papers has been graciously provided by the National University of Singapore. The assistance of the editors, particularly Prof. Martin Betts, is gratefully appreciated.


Drogemuller R, Woodbury R, Crawford J

Extracting representation from structured text: initial steps

Abstract: A great deal of work has been done in the past on natural language recognition within the field of artificial intelligence. The aim of this work was to allow natural language text to be read in by a computer and structured in a format that would allow automatic interpretation of the text. This was intended to reduce the "knowledge engineering bottleneck" that has been a significant constraint on the use of artificial intelligence techniques within many fields. Some similar work has also been done within the AEC industry concentrating mainly on building codes. The research project described in this paper aims to simplify the analysis of structured text and its conversion into computer interpretable forms by providing support with computer software. The work is built around two documents - a glossary of building terms used in Australia and the Building Code of Australia. The various issues concerned with "noise" in the source data, the structure and content of documents to be analysed and the desired computer interpretable result will be presented. This work is motivated by: the need to maintain BCAider, a knowledge based system that assists in checking building designs for compliance with the Building Code of Australia; continuing work in encoding of regulations in computer interpretable form; and the need for international glossaries to support information harmonisation efforts such as the IAI and STEP. The software suite under development assists people with some understanding of language structure and knowledge engineering in converting structured text into computer interpretable form using a visual user interface. The current state of the design and development of this software suite will be described and the results of its use presented.

Keywords:

DOI:

Full text: content.pdf (262,275 bytes) (available to registered users only)

Series: w78:2000 (browse)
Cluster: papers of the same cluster (result of machine made clusters)
Class: class.retrieve (0.070694) class.analysis (0.045357) class.man-software (0.038615)
Similar papers:
Sound: read aloud.

Permission to reproduce these documents have been graciously provided by Icelandic Building Research Institute. The assistance of the editor, Mr. Gudni Gudnason, is gratefully appreciated


Drogemuller R

Modelling static and dynamic knowledge during design

Abstract: The IS0 STEP standards for product data modelling and exchange are based on the use of Express. Express has acknowledged limitations. Modifications have been suggested to extend Express (Express-E) into a more object-oriented language and to add rules as a means of encoding knowledge. The EDM group have presented solutions to many of these limitations for the modelling of buildings. This paper discusses BDeCS (Building Design and Construction System), an interactive system that supports building design and construction. BDeCS uses ideas from Express, EDM and the various knowledge representation formalisms developed in AI research. The initial development of BDeCS concentrated on the representation of knowledge within the system. The user interface was then developed around methods of interacting with the howledge in as "natural" a way as possible. Limitations of both knowledge representation formalisms from the AI field and traditional software development have been identified. The needs for extensibility and sharing of information among all of the members of the building design and construction team have lead to a software architecture that is unique. Methods of organising teams of people to work concurrently on the one project, while maintaining consistency of the data have also been developed.

Keywords:

DOI:

Full text: content.pdf (1,246,710 bytes) (available to registered users only)

Series: w78:1995 (browse)
Cluster: papers of the same cluster (result of machine made clusters)
Class: class.man-software (0.070743) class.software development (0.024602) class.represent (0.021522)
Similar papers:
Sound: read aloud.

Permission to reproduce these papers has been graciously provided by the Stanford University, USA. The support of the editors, particularly Prof. Fischer is gratefully appreciated.


J Dimyadi, C Clifton, M Spearpoint, R Amor

Regulatory Knowledge Encoding Guidelines for Automated Compliance Audit of Building Engineering Design

Abstract:

Keywords:

DOI:

Full text: content.pdf (150,637 bytes) (available to registered users only)

Series: w78:2014 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.


Maher M L, Li H

Learning empirical knowledge to assist preliminary design

Abstract: The reuse of the experience of design and construction of a major project is ad hoc and depends on the individuals involved in the project being present on a similar project in the future. At the same time, the development of knowledge-based systems to support the design process requires the encoding of previous experience in a form that can be applied to future design projects. Machine learning techniques can be applied to automate the reuse of design experience and to facilitate the development of design knowledge bases. The application of machine learning techniques in a design domain requires the consideration of the representation of the learned design knowledge, that is, a target representation, as well as the content and form of the training data, or design examples. This paper proposes a target representation called a design concept and presents a methodology for learning design concepls from design examples. The method is illustrated by applying it to examples of bridge designs.

Keywords: machine learning; design; conceptual clustering; knowledge-based design

DOI:

Full text: content.pdf (713,018 bytes) (available to registered users only)

Series: w78:1993 (browse)
Cluster:
Class:
Similar papers:
Sound: read aloud.

Permission to reproduce these papers has been graciously provided by the National University of Singapore. The assistance of the editors, particularly Prof. Martin Betts, is gratefully appreciated.


Thomas J R, Worling J

SGML and Office Document Management Systems: Tools for Building Code Writers

Abstract: In conjunction with research being conducted into providing computer based tools to support code users the National Research Council of Canada has also undertaken a research and development program to support the Authors of Code documents. Support for the Code Writers has been based upon the adoption of the Standard Generalized Markup Language (SGML) as a mechanism for supporting the management, publication, and information enrichment of the code development and delivery process.All of the current National Building Code documents have been converted to SGML and an Office Document Management System (ODMS) has been implemented to support this process. In addition, a number of prototype authoring tools have been developed to both hide the code authors fromthe SGML encoding of their text and at the same time ensure that the text of the code articles are consistent with the rest of the document.

Keywords:

DOI:

Full text: content.pdf (957,324 bytes) (available to registered users only)

Series: w78:1992 (browse)
Cluster: papers of the same cluster (result of machine made clusters)
Class: class.synthesis (0.046660) class.store (0.041598) class.software development (0.011293)
Similar papers:
Sound: read aloud.

Permission to reproduce these papers has been graciously provided by Research Press of the National Research Council of Canada. The support of the editor, Dr. Dana Vanier, is gratefully appreciated.


No more hits.

 

hosted by University of Ljubljana



includes

W78




© itc.scix.net 2003
Home page of this database login Powered by SciX Open Publishing Services 1.002 February 16, 2003