Summary: |
"Rapid advances in parallel processing technologies gave essential impetus to intelligent information processing, which became the driving source of an emerging technology known as soft computing. This calls for intelligent systems that are able to process information which may be complex, uncertain even incomplete or contradictory. In this context, neural networks and fuzzy logic are the essential tools. Considering the merits of each approach separately, most suitable computational intelligence method can be used for a specific application. Additionally, the combination of these methods can provide enhanced information processing for decision-making with enhanced reliability. For building design, the computational intelligence system use a knowledge base formed by means of neural network and fuzzy logic (neuro-fuzzy) techniques, from a building design database. The application of such a system to a building design task was preliminarily demonstrated earlier [1]. The present research describes a systematic neural fuzzy modelling of data that form a knowledge base in a hierarchical form (s.figure below). Each sub-knowledge base represents a local expert, being level-one expert and the association of local experts forms a more comprehensive expert that becomes a global domain expert as level-two. The association of the experts is accomplished by means of fuzzy-logic-driven gating network that performs, the information handling as required. Although, the present paper describes two-level hierarchical experts as local and global, the associations can be done in more subtle form, i.e., in more than two steps so that the level of experts can be categorised in multi-level form. In such more complex structures, multi-level experts require related gating network that could similarly be designed. The building design support system with the expert network developed, as a whole, is generic enough for decision-makings with a novel systematic approach concept using appropriate database. Accordingly, the research deals with a particular architectural building design with efficiency and consistency features using the hierarchical expert network system described[1] Ciftcioglu O, Sariyildiz S. and Veer P. v.d., 1998 , Information Ordering for decision support in building design, D and DSS, Design and Decision Support Systems 4th International Conference on Design and Decision Support Systems in Architecture and Urban Planning, Castle Vaeshartelt, Maastricht, July 26-29, The Netherlands" |