Affiliation:
1. Qujing Normal University
Abstract
We studied moisture and volatile determination in bituminous coal samples using near-infrared (NIR) spectra. This research applied support vector machine (SVM) and discrete wavelet transform (DWT). Firstly, NIR spectra were pre-processed by DWT for fitting and compression. Then, DWT coefficients were used to build regression model with SVM. We used NIR spectra to determination moisture and volatile determination in coal samples separately. Through parameters optimization, the results show that DWT-SVM can obtain satisfactory performance for moisture and volatile determination in coal samples.
Publisher
Trans Tech Publications, Ltd.
Reference21 articles.
1. M. Ferrari, L. Mottola, V Quaresima: Canadian J. Applied Physiology Vol. 29 (2004), p.463.
2. J. Trygg and S. Wold: J. Chemom. Vol. 16 (2002), p.119.
3. M.T. Bona and J.M. Andrés: Talanta Vol. 72 (2007), p.1423.
4. S. Wang, X. Feng, J. Zhou and X. Wang: Advanced Materials Research Vol. 236-238 (2011), p.799.
5. Y. Wang, G. Shi, X. Zhong and D. Wang: Applied Mechanics and Materials Vol. 80-81 (2011), pp.279-283.