An approach to the development of commonsense knowledge modelling systems for land selection

Abstract

The land use methods which are ergonomically and environmentally appropriate are determined first and foremost by characteristics and location. For instance, land selection in architectural construction domain is considered as an area in land use methods, which involves commonsense knowledge of architects. This is because land selection criteria are very personal and there is no theory behind how it should be done. Sometime, there are too many redundancies in the process selection of lands. In this paper we present an approach to modeling commonsense knowledge in a sub field of architecture domain of land selection to come up with land classifications as psychological, physical and social events. This gives three-phase knowledge modeling approach for modeling commonsense knowledge in, which enables holistic approach for land selection. At the initial stage commonsense knowledge is converted into a questionnaire. Removing dependencies among the questions are modeled using principal component analysis. Classification of the knowledge is processed through fuzzy logic module, which is constructed on the basis of principal components. Further explanations for classified knowledge are derived by expert system technology. This paper describes one such approach using classification of human constituents in Ayurvedic medicine. Evaluation of the system has shown 77% accuracy.