Application of PCA-based data compression in the ANN-supported conceptual cost estimation of residential buildings
Michał Juszczyk · AIP conference proceedings · 2016
The paper presents concisely some research results on the application of principal component analysis for the data compression and the use of compressed data as the variables describing the model in the issue of conceptual cost estimation of residential buildings. The goal of the research was to investigate the possibility of use of compressed input data of the model in neural modelling - the basic information about residential buildings available in the early stage of design and construction cost. The results for chosen neural networks that were trained with use of the compressed input data are presented in the paper. In the summary the results obtained for the neural networks with PCA-based data compression are compared with the results obtained in the previous stage of the research for the network committees.