Forecasting of Cotton Yarn Properties Using Intelligent Machines

An intelligence machine is a computer program that can learn from experience, i.e. modifies its processing on the basis of newly acquired information and thereafter makes decisions in a rightfully sensible manner when presented with inputs. Examples of such machine learning systems are artificial neural networks (ANNs), support vector machines (SVMs), fuzzy logic, evolutionary computation, etc. The prediction of cotton yarn properties from constituent fibre properties is quite significant from a technological point of view. Regardless of the relentless efforts made by researchers, the exact relationship between fibre and yarn properties has not yet been decisively recognized. The intelligence machine, which is a potent data-modeling tool in capturing complex input-output relationships, seems to be the right approach to decipher the fibre-to-yarn relationship. In this work, various cotton yarns properties, such as strength, elongation, evenness and hairiness, have been predicted from fibre properties by using different intelligence models, such as ANNs, SVMs and adaptive neuro fuzzy inference systems (ANFIS). A k-fold cross validation technique is applied to assess the expected generalization accuracies of these models. A comparison of the prediction efficiencies among these models shows that the performances of the SVM model has better accuracies than the other models.