Get access

An Input Variable Selection Method for the Artificial Neural Network of Shear Stiffness of Worsted Fabrics

Authors


Abstract

The relationship between yarn properties, fabric parameters, and shear stiffness of worsted fabrics is modeled using the soft computing technique. Because of the small number of samples, the artificial neural network model to be established must be a small-scale one. Therefore, this soft computing approach includes two stages. First, the yarn properties and fabric parameters are selected by utilizing an input variable selection method, so as to find the most relevant yarn properties and fabric parameters as the input variables to fit the small-scale artificial neural network model. The first part of this method takes the human knowledge on the shear stiffness of fabrics into account. The second part utilizes a data sensitivity criterion based on a distance method. Second, the artificial neural network model of the relationship between yarn properties, fabric parameters, and shear stiffness of fabrics is established. The results show that the artificial neural network model yields accurate prediction and a reasonably good artificial neural network model can be achieved with relatively few data points by integrating with the input variable selecting method developed in this research. The results also show that there is great potential for this research in the field of computer-assisted design in textile technology. Copyright © 2009 Wiley Periodicals, Inc. Statistical Analysis and Data Mining 1: 000-000, 2009

Get access to the full text of this article

Ancillary