Prediction of fabric end-use using a neural network technique

A neural network computing technique was proposed to predict fabric end-use. One hundred samples of apparel fabrics were selected and measured using the Kawabata KES-FB instruments. Instrumental data of the fabric properties and information on fabric end-uses, suitings, shirts, and blouses, were input into a neural network software to train a multilayer perceptron model. The prediction error rate from the established neural network model was estimated by using a cross-validation method.