Affiliations: Center of Real Time Computer Systems, Kaunas University of Technology, K. Barsausko, Kaunas, LT, Lithuania
Correspondence:
[*]
Corresponding author. Vytautas Petrauskas, Center of Real Time Computer Systems, Kaunas University of Technology, K. Barsausko 59-A314, Kaunas, LT 51423, Lithuania. Tel.: +370 37 300 390; Fax: +370 610 03933; [email protected]
Abstract: A substantial amount of scientific research and publications in the smart home domain deal with different aspects of fuzzy logic application. However, we feel there is a general lack of complex modelling done of the whole smart home environment. So, the main goal of this paper is threefold: 1) to present a virtual model of a smart home environment to be intellectualized, 2) to demonstrate the efficiency of Mamdani type inference procedure in modelling of intellectual behaviour of the environment and 3) to show that it is possible to minimize the quantity of fuzzy rules by taking the hierarchical approach and adding the Takagi-Sugeno inference procedure to empower it. The results of computerized modelling and simulation are delivered in the paper demonstrating the practical viability and efficiency of the theoretical approach. The model of the intelligent home environment was used in two projects. Since a formalized analytical method for evaluating the sensitivity of system parameters still does not exist, the experimental sensitivity simulation in our case is performed and presented in this paper. Characteristics obtained in the modelled virtual environment can be easily expanded and used in a real home environment by changing pixels into real coordinates and the light intensity into other real variables.
Keywords: Functional organization, fuzzy rules, intellectualized home environment, hierarchical approach, virtual model
