journal article·2012-11

The use of hybrid algorithms to improve the performance of yarn parameters prediction models

Josphat Igadwa Mwasiagi, XiuBao Huang, XinHou Wang

Fibers and Polymers· Volume 13· Issue 9
Publisher page

Abstract

Although gradient based Backpropagation (BP) training algorithms have been widely used in Artificial Neural Networks (ANN) models for the prediction of yarn quality properties, they still suffer from some drawbacks which include tendency to converge to local minima. One strategy of improving ANN models trained using gradient based BP algorithms is the use of hybrid training algorithms made of global based algorithms and local based BP algorithms. The aim of this paper was to improve the performance of Levenberg-Marquardt Backpropagation (LMBP) training algorithm, which is a local based BP algorithm by using a hybrid algorithm. The hybrid algorithms combined Differential Evolution (DE) and LMBP algorithms. The yarn quality prediction models trained using the hybrid algorithms performed better and exhibited better generalization when compared to the models trained using the LM algorithms.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Textile materials and evaluations · Industrial Vision Systems and Defect Detection · Material Properties and Processing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (26)

Show source-provided references
1. L. Cheng and D. L. Adams, Text. Res. J., 65, 495 (1995).10.1177/004051759506500901 ↗
2. J. V. Desai, C. D. Kane, and B. Bandyopadhayay, Text. Res. J., 74, 227 (2004).10.1177/004051750407400307 ↗
3. P. K. Majumdar and A. Majumdar, Text. Res. J., 74, 652 (2004).10.1177/004051750407400717 ↗
4. M. E. Ureyen and P. Gurkan, Fiber. Polym., 9, 87 (2008).10.1007/s12221-008-0014-4 ↗
5. M. E. Ureyen and P. Gurkan, Fiber. Polym., 9, 92 (2008).10.1007/s12221-008-0015-3 ↗
6. R. Furferi and M. Gelli, Adv. Mech. Eng., 2010, 11 (2010).
7. L. Burke and J. P. Ignizio, Journal of Intelligent Manufacturing, 8, 157 (1997).10.1023/A:1018513006083 ↗
8. R. Chattopadhyay, A. Guha, and J. Jayadeva, J. Appl. Polym. Sci., 91, 1746 (2004).10.1002/app.13231 ↗
9. J. I. Mwasiagi, X. H. Wang, and X. B. Huang, J. Appl. Polym. Sci., 108, 320 (2008).10.1002/app.27586 ↗
10. J. I. Mwasiagi, X. B. Huang, and X. H. Wang, Fiber. Polym., 8, 80 (2007).
11. S. Sotirov, Neural Processing Letters, 22, 163 (2005).10.1007/s11063-005-3094-9 ↗
12. A. Atakulreka and D. Sutivong, “Avoiding Local Minima in Feedforward Neural Networks by Simultaneous Learning” (M. A. Orgun and J. Thornton Eds.), pp.100–109, AI 2007, LNAI 4830, Springer-Berlin, 2007.10.1007/978-3-540-76928-6_12 ↗
13. L. S. Admuthe and S. D. Apte, International Journal of Computer Theory and Engineering, 1, 441 (2009).10.7763/IJCTE.2009.V1.71 ↗
14. A. Majumdar, Ind. J. Fibres Text. Res., 35, 121 (2010).
15. K. Hornik, M. Stinchcombe, and H. White, Neural Networks, 2, 359 (1989).10.1016/0893-6080(89)90020-8 ↗
16. G. Cybenko, Math. Control Signals Systems, 2, 303 (1989).10.1007/BF02551274 ↗
17. H. B. Demuth, M. Beale, and M. T. Hagan, “Neural Network Toolbox, For Use with MATLAB”, The MathWorks, Natick, 2005.
18. F. M. Ham and I. Kostanic, “Principles of Neurocomputing for Science & Engineering”, China Machine Press, Beijing, 2003.
19. M. T. Hagan, H. B. Demuth, and M. Beale, “Neural Network Design”, China Machine Press, Beijing, 2002.
20. J. I. Mwasiagi, X. B. Huang, and X. H. Wang, Fiber. Polym., 9, 80 (2008).10.1007/s12221-008-0013-5 ↗
21. R. Storn and K. Price, Journal of Global Optimization, 1, 341 (1997).10.1023/A:1008202821328 ↗
22. N. K. Madavan, Proc. Congr. Evol. Comput., 145 (2002).
23. D. Karaboga and S. Okdem, Turkish Journal of Electrical Engineering, 12, 53 (2004).
24. J. Vesterstrom and R. Thomsen, Proc. Congr. Evol. Computation, 980 (2004).
25. J. Ilonen, K. Kamarainen, and J. Lampinen, Neural Processing Letters, 17, 93 (2003).10.1023/A:1022995128597 ↗
26. D. Floreano, P. Durr, and C. Mattiussi, Evol. Intel., 1, 47 (2008).10.1007/s12065-007-0002-4 ↗