In order to construct a novel design method for interior tiles, the relationship between image words (sensory evaluation) and total evaluation for interior tiles was studied. At first, the model for estimation of the total evaluation from image words was constructed using a fuzzy neural network (FNN) and MRA (multi regression analysis). The FNN model could estimate the total evaluation more correctly than the MRA model. Secondly, a FNN model for the estimation of the total evaluation from analytical data for interior tiles was constructed. This model was less accurate than the FNN model from image words, but could estimate within 10% errors. Lastly, in order to improve accuracy of the estimation, a FNN model for estimation of the total evaluation from both analytical data and image words was constructed. This model showed the highest accuracy among all models. "<I>Jyouhinna-gehinna</I>", "<I>shareta-yabona</I>" among image words and "average value of green color", "arithmetical mean deviation", "peak count" among analytical data were needed to construct the model for estimation of the total evaluation.
|Translated title of the contribution||Modeling of Sensory Evaluation for Interior Tiles Using a Fuzzy Neural Network|
|Number of pages||6|
|Journal||Kagaku Kogaku Ronbunshu|
|Publication status||Published - Jan 10 1998|