The Use of BP Neural Network in Evaluation about the Appearance of the Garments

Abstract:

This article reports the use of BP neural network for evaluation of the appearance of garment after dry wash. The selected data about parameters of fabrics and interlinings are analyzed by principal analysis and eight principal components are obtained through this method. A BP neural network with a single hidden layer is constructed including eight input nodes, six hidden nodes and one output nodes. During training the network with a back-propagation algorithm, the eight principal components are used as input parameters, while the rate of the appearance of the garment are used as output parameters. The weight values are modified with momentum and learning rate self-adaptation to solve the two defects of the BP network. All original data are preprocessed and the learning process is successful in achieving a global error minimum. The rate of the appearance can be evaluated with this training network and there is a good agreement between the evaluated and tested values.

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 4320-4323
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.4320
• Online since: January 2012
• Authors: Jing Wang, Jin Ying Song, Ai Qing Tang
• Keywords: Appearance, BP Neural Network (BPNN), Garment

References

[1] J, Fan., and Ng, YN., Objective Evaluation of the Hand of Nonwoven Fusible Interling[J], Textile Research Journal, 2001, 71(8), P661-666.

DOI: 10.1177/004051750107100802

[2] Jeong, S.H., and Jung, H. Kim., Selecting Optimal Interlinings with a Neural Network[J], Textile Research Journal, 2000, 70(11), P1005 -1010.

DOI: 10.1177/004051750007001111

[3] Jeong, S.H., and Barker, R.L., Composite Performance of Fusible Interlinings on Apparel Fabrics(I) [J], Journal of Korea Fiber Society, 1996, 33, P83-88.

[4] Jeong, S.H., Choi, Y.Y., and Barker, R.L., Composite Performance of Fusible Interlinings on Apparel Fabrics(II) [J], Journal of Korea Fiber Society, 1996, 33, P905-911.