IJIMT 2013 Vol.4(4): 390-392 ISSN: 2010-0248
DOI: 10.7763/IJIMT.2013.V4.427

The Performance of Data Mining Techniques in Prediction of Yarn Quality

Khalid A. A. Abakar and Chongwen Yu
Abstract— The data mining techniques such as Artificial Neural network algorithm (ANN) and support vector machine (SVM) based models are utilized in this study. Three different kernel functions were used as SVM kernel functions which are polynomial, Radial Basis Function (RBF), and Pearson VII function-based Universal Kernel (PUK). The SVM models based on these three kernel functions and ANN model were used in forecasting the quality of ring and compact spinning yarn such as yarn unevenness, hairiness, yarn tenacity, and yarn elongation. The comparison of results indicates that the SVM models based on RBF and PUK Performs yarn properties forecasts more accurately than ANN model.

Index Terms— Data mining, artificial neural network (ANN), support vector machine (SVM), kernel functions, yarn properties.

The authors are with the College of Textiles, Donghua University, Shanghai 201620, People's Republic of China (e-mail: kheloo333@hotmail.com; yucw@dhu.edu.cn).

[PDF]

Cite: Khalid A. A. Abakar and Chongwen Yu, " The Performance of Data Mining Techniques in Prediction of Yarn Quality," International Journal of Innovation, Management and Technology vol. 4, no. 4, pp. 390-392, 2013.

Copyright © 2008-2015. International Journal of Innovation, Management and Technology. All rights reserved.
E-mail: ijimt@ejournal.net