Conceptual Architectural Design Research Articles

ORCHID: building linguistic resources in Thai

ORCHID (Open linguistic Resources CHanelled toward InterDisciplinary research) is a project aimed at building linguistic resources to support research in, but not limited to, natural language processing. Based on the concept of an open architecture design, the resources must be fully compatible with those which already exist, and software tools must also be made available. This paper describes the construction of a Thai part-of-speech (POS) tagged corpus, a preliminary stage in the construction of a Thai speech corpus. The paper also details the development of a POS tagger to be used in the construction of the POS-tagged corpus. Additionally, we describe a proposal for a new tagset, based on the results of a prior multilingual machine translation project. The corpus is annotated on three levels: paragraph, sentence, and word. Text information is maintained in the form of the text information lines and the number lines, which are both utilized in data retrieval. Finally, we describe a POS neuro tagger, which consists of a three-layer perceptron with elastic input. Computer experiments show that the neuro tagger has an accuracy of 94.4 per cent for tagging ambiguous words when tested on a small Thai training corpus containing 22,311 ambiguous words. A series of comparative experiments further show that the neuro tagger is superior to the statistical models including the frequency model (a baseline model), local n-gram model, and HMM (Hidden Markov Model).

Building a Thai part-of-speech tagged corpus (ORCHID).

ORCHID (Open linguistic Resources CHanelled toward InterDisciplinary research) is an initiative project aimed at building linguistic resources to support research in, but not limited to, natural language processing. Based on the concept of an open architecture design, the resources must be fully compatible with similar resources, and software tools must also be made available. This paper presents one result of the project, the construction of a Thai part-of-speech (POS) tagged corpus, which is a preliminary stage in the construction of a Thai speech corpus. The POS-tagged corpus is the result of collaborative research between the Communications Research Laboratory (CRL) in Japan and the National Electronics and Computer Technology Center (NECTEC) in Thailand, with technical support from the Electrotechnical Laboratory (ETL) in Japan. In this paper, we propose a new tagset, based on the results of a prior multilingual machine translation project. The corpus is annotated on three levels: the paragraph, sentence, and word levels. Text information is maintained in the form of the text information lines and the number lines, which are both utilized in data retrieval. Both word segmentation and POS tagging were carried out by way of a probabilistic trigram model. Rules for syllable demarkation were additionally used to reduce the number of candidates in computing tagging probabilities

Collaborative Distributed Building Engineering

This article presents a software environment for collaborative distributed building design and construction planning called CIFE WORLD. Its test domain and demonstration include conceptual architectural design, structural design, and construction planning of office buildings. CIFE WORLD provides eight design and engineering applications that can be used by five project participants to collaborate on building design and construction in a geographically dispersed environment. The project forms a design group and a construction group, whose applications are organized based on a federated agent architecture. In this architecture, CIFE WORLD's applications are viewed as software agents, and their communication is mediated by a network of two facilitators. This article describes the CIFE WORLD environment, examines the use of federated agent architecture for building design and construction planning, and reports on the experience gained from this development.

Calculation and measurement of acoustic factors for the Kirishima International Concert Hall

The Kirishima International Concert Hall was designed by architect F. Maki with Ando’s acoustic design theory. It opened on July 22, 1994. The 770 seat main hall which has a volume of 8475 m3 was primarily designed for chamber music. Computer simulations made it clear that the acoustical design of the main hall would be an optimum solution with a plan like a leaf shape and a cross section like a bottom of a ship. These were solutions which satisfied requirements for both acoustical and architectural design concepts of the main hall. Getting a low IACC sound field at the front seat was most important. In order to get a low IACC, sound reflections from the stage to the audience floor were examined and studied in the early design processes. Calculation and measurement of acoustic factors of the sound fields in the main hall show: (1) the calculated and the measured IACCs are good in agreement, (2) IACCs tended lower values of about 0.1 than the calculated ones throughout the seats, and (3) the number of reflections needed for predicting IACC is recommended to be about 40 for the practical method of IACC calculation at the design stage of a hall.

A tapestry in the landscape

A concise report about the landform, architectural, and detail design concepts for the recently completed modernisation of the Bishopsfield Housing Estate in Harlow, Essex. The objective was to develop proposals for new interventions which are directly based on, and give emphasis and new life in a contemporary way to the architectural and urban design conceptions of the original architects and town planner.

Precedents in design: a computational model for the organization of precedent knowledge

A computational model for the organization of design precedent knowledge is developed. The model is composed of distinct chunks of knowledge called design stories. A formalism for the design story is proposed which represents the linkage between design issue, concept and form in designs. Stories are structured in memory according to a semantic network. The lexicon of the semantic network acts as a memory index. The memory structure and indexing system are demonstrated to enhance search and to support cross-contextual browsing and exploration in the precedent library. The approach is demonstrated in a pilot design aid system in the task domain of early conceptual design in architecture.

Using the points of large cases

We believe that case-based reasoning (CBR) will prove applicable to design, at least in part, as we have seen designers making extensive use of past cases. Construction of useful systems, however, requires the resolution of many open issues. In this paper we consider three issues in particular: (1) What sort of content should be captured in a design case? (2) How should the content of a complex case be segmented into chunks for use? (3) How should the resulting chunks be indexed for retrieval? These are among the issues we are seeking to address through construction of Archie-II, a case-based aid for conceptual design in architecture. In addition to our approaches to these issues, this paper also discusses our strategic choice to build a design aiding system as opposed to a system that generates designs on its own.