Intelligent Techniques for Modeling the Relationships between Sensory Attributes and Instrumental Measurements of Knitted Fabrics

The present investigation provides a promising tool for engineering industrial products design. In fact, two soft computing approaches, namely artificial neural network (ANN) and fuzzy inference system (FIS), have been applied to model the relationship between sensory properties and instrumental measurements of knitted fabrics. The prediction performance of these models was evaluated using the root mean square error (RMSE). The obtained results show the models’ ability to predict tactile sensory attributes from the measured surface and compression properties. These neural and fuzzy models may help textile industrialists to satisfy the specific needs of consumers.