Considering the complexity of the building design process, a systematic approach using the presently possible information processing possibilities is very desirable. By means of this, effective and efficient decisions can be acquired yielding substantial savings in design efforts. Soft computing is one of the emerging technologies with a high potential, in this context. In the present approach, soft computing is introduced into building design in the form of knowledge base formation for inductive decision-makings in place of traditional data acquisition and processing methods. By means of soft computing based approach a compact and affordable case-based decision support system with enhanced reliability of decisions about optimal solutions is obtained. The paper describes the method together with application to a case study based on actual building data.
[1]
Shang-Liang Chen,et al.
Orthogonal least squares learning algorithm for radial basis function networks
,
1991,
IEEE Trans. Neural Networks.
[2]
Lotfi A. Zadeh,et al.
Fuzzy Sets
,
1996,
Inf. Control..
[3]
D. Broomhead,et al.
Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks
,
1988
.
[4]
Chuen-Tsai Sun,et al.
Functional equivalence between radial basis function networks and fuzzy inference systems
,
1993,
IEEE Trans. Neural Networks.
[5]
Roderick Murray-Smith,et al.
Extending the functional equivalence of radial basis function networks and fuzzy inference systems
,
1996,
IEEE Trans. Neural Networks.
[6]
Simon Haykin,et al.
Neural Networks: A Comprehensive Foundation
,
1998
.