The use of extreme learning machines (ELM) algorithms to prediction strength for cotton ring spun yarn

다국어 초록 (Multilingual Abstract)

The increasing use of artificial neural network in the prediction of yarn quality properties calls for constant improvement of the models. This research work reports the use of a novel training algorithm christened extreme learning machines (ELM) to prediction yarn tensile strength (strength). ELM was compared to the Backpropagation (BP) and a hybrid algorithm composed of differential evolution and ELM and named DE-ELM. The three yarn strength prediction models were trained up to a mean squared error (mse) of 0.001. This is an arbitrary level of mse that was selected to enable a comparative study of the performance of the three algorithms. According to the results obtained in this research work, the BP model needed more time for training, while the ELM model recorded the shortest training time. The DE-ELM model was in between the two models. The correlation coefficient (R2) of the BP model was lower than that of ELM model. In comparison to the other two models the DE-ELM model gave the highest R2 value.

참고문헌 (Reference)

1 Zhu, Q. Y., "evolutionary extreme learning, machine" 38 : 1759-1763, 2005

2 Furferi, R., "Yarn strength prediction: A practical model based on artificial neural networks" 8 : 1-10, 2010

3 Cheng, L., "Yarn strength prediction using neural networks: part I: fiber properties and yarn strength relationship" 65 (65): 495-500, 1995

4 Huang, G. B., "Universal approximation using incremental constructive feedforward networks with random hidden nodes" 17 (17): 879-892, 2006

5 Hagan, M. T., "Training feedforward networks with the Marquardt algorithm" 5 (5): 989-993, 1994

6 Mwasiagi, J. I., "The use of hybrid algorithms to improve the performance of yarn parameters prediction models" 13 (13): 1201-1208, 2012

7 Ham, F. M., "Principles of neurocomputing for science and engineering" China Machine Press 24-135, 2003

8 Mehment, D., "Prediction of yarn properties using evaluation programing" 79 (79): 963-972, 2009

9 Majumdar, P. K., "Predicting the breaking elongation of ring spun yarns using mathematical statistical and artificial neural models" 74 (74): 652-655, 2004

10 Chattopadhyay, R., "Performance of neural networks for predicting yarn properties using principal component analysis" 91 : 1746-1751, 2004

11 Mwasiagi, J. I., "Performance of neural network algorithms during the prediction of yarn elongation" 9 (9): 80-86, 2008

12 Demuth, H. B., "Neural network toolbox" 5 : 25-, 2005

13 Desai, J. V., "Neural Networks: An alternative solution for statistically based parameter prediction" 74 (74): 227-230, 2004

14 MathWorks, "Matlab -The Language of technical computing" The MathWorks Inc 2004

15 Huang, G. B., "Extreme learning machine: Theory and applications" 70 : 489-501, 2006

16 Ureyen, M. E., "Comparison of artificial neural network and linear regression models for prediction of ring spun yarn properties. i: prediction of yarn tensile properties" 9 (9): 87-91, 2008

17 Ureyen, M. E., "Comparison of artificial neural network and linear regression models for prediction of ring spun yarn properties ii: prediction of yarn hairiness and unevenness" 9 (9): 92-96, 2008

18 Cybenko, G., "Approximation by superpositions of a sigmoidal function" 1989 (1989): 303-314, 1989

19 Bernstein, I. R., "Applied multivariate analysis" Springer 157-197, 1988

20 Majumdar, A., "Application of an adaptive neuro-fuzzy system for the prediction of cotton yarn strength from HVI fibre properties" 96 (96): 55-60, 2005

21 Guha, A., "A comparison of mechanistic statistical, and neural network models" 92 (92): 139-145, 2001