Predicting Cotton Fibre Maturity by Using Artificial Neural Network
Predicting Cotton Fibre Maturity by Using Artificial Neural Network
Farooq, Assad; Sarwar, Muhammad Ilyas; Ashraf, Muhammad Azeem; Iqbal, Danish; Hussain, Azmat; Malik, Samander
2018-12-01 00:00:00
AbstractCotton fibre maturity is the measure of cotton’s secondary cell wall thickness. Both immature and over-mature fibres are undesirable in textile industry due to the various problems caused during different manufacturing processes. The determination of cotton fibre maturity is of vital importance and various methods and techniques have been devised to measure or calculate it. Artificial neural networks have the power to model the complex relationships between the input and output variables. Therefore, a model was developed for the prediction of cotton fibre maturity using the fibre characteristics. The results of predictive modelling showed that mean absolute error of 0.0491 was observed between the actual and predicted values, which show a high degree of accuracy for neural network modelling. Moreover, the importance of input variables was also defined.
http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.pngAutex Research Journalde Gruyterhttp://www.deepdyve.com/lp/de-gruyter/predicting-cotton-fibre-maturity-by-using-artificial-neural-network-fzIOFVac4c
Predicting Cotton Fibre Maturity by Using Artificial Neural Network
AbstractCotton fibre maturity is the measure of cotton’s secondary cell wall thickness. Both immature and over-mature fibres are undesirable in textile industry due to the various problems caused during different manufacturing processes. The determination of cotton fibre maturity is of vital importance and various methods and techniques have been devised to measure or calculate it. Artificial neural networks have the power to model the complex relationships between the input and output variables. Therefore, a model was developed for the prediction of cotton fibre maturity using the fibre characteristics. The results of predictive modelling showed that mean absolute error of 0.0491 was observed between the actual and predicted values, which show a high degree of accuracy for neural network modelling. Moreover, the importance of input variables was also defined.
To get new article updates from a journal on your personalized homepage, please log in first, or sign up for a DeepDyve account if you don’t already have one.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.