Modelling perceptions of building quality—A neural network approach

Abstract

The conceptual framework for this study was based on the premise that there are lifestyle groups within a culture which commonly share attitudes and perceptions which are reflected in the form and design of their buildings. This study focussed on a particular lifestyle group of people from the same ethnic background, i.e. Caucasian of European ancestry who owned and lived in detached houses. The sample of participants were homogenous in terms of their ethnic background and houses. The setting of this study was a residential estate in Townsville, Queensland, Australia, a hot-humid environment. This study used the ethnographic approach of case study methodology; hence, data were gathered from questionnaires, interviews, observations, building plans, notes and photographs. The attitudes and perceptions of the selected group of homeowners on the quality of their houses in six areas of building performance: spatial, thermal, acoustical, visual, building integrity and indoor air quality, were investigated. The data were qualitatively analysed, assembled and manipulated in a computer-based model. In developing the computer-based model, the capabilities of the programming paradigms—conventional programs, knowledge-based systems and learning systems, were investigated. A neural network learning system was chosen for developing the computer-based model. The neural network model was tested and validated on example cases of houses to verify its prediction capability.