Abstract
In this paper, an attempt to quantify hands of fabrics for Korean folk clothes has been made based on mechanical properties and the sensory test using artificial intelligence systems. In order to classify the primary hand values, four neural networks with three-layered structure were constructed and one neural network was constructed to classify the total hand value. The learning algorithm was selected with the error back propagation algorithm and, in order to reduce errors and to speed up learning, the moment method was selected. From the analysis of the primary and total hands using a self-constructed artificial intelligence system, the error rates of silky, sleekness, roughness, and stiffness compared with the judgements of expert panels were found to be 4.9%, 4.9%, 4.9%, and 1.6%, respectively, while that of the total hand was 9.83%.