1. 浙江大学智能系统与控制研究所, 工业控制技术国家重点实验室，浙江 杭州 310027 2. Computer Learning Research Centre, Royal Holloway, University of London,Egham Hill, Egham, Surrey TW20 0EX, UK
Rapid Coal Classification Based on Confidence Machine and Near Infrared Spectroscopy
WANG Ya-sheng1, YANG Meng2, LUO Zhi-yuan2, WANG You1, LI Guang1, HU Rui-fen1*
1. State Key Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou 310027, China 2. Computer Learning Research Centre, Royal Holloway, University of London, Egham Hill, Egham, Surrey TW20 0EX, UK
Abstract：Near-infrared reflectance spectroscopy (NIRS) is a simple, convenient and safe technology which is widely used in many industries. NIRS was employed to the rapid classification of coal in this study. The new method can be a replacement of the chemical analysis which is laborious and time consuming. Confidence machine was firstly applied to NIRS in this study which was used to evaluate the risk of the analysis. The near infrared reflectance spectrum of 199 coal samples including four types of coal (50 fat coal samples, 50 coking coal samples, 49 lean coal samples and 50 meager lean coal samples) from different mines in China were collected and classifiers based on the near infrared spectra of coal samples which were established by using machine learning methods to realize the rapid classification of coal samples. Confidence machine was introduced into the analysis technology based on NIRS in this paper. Confidence machine based on support vector machine (CM-SVM) was built and applied to the classification of coal samples via NIRS. Confidence machine is a probabilistic algorithm and instead of using hyper plane (SVM) to carry out the classification, using probability (CM-SVM) turned to be more effective which had 95.45% of the samples correctly grouped. Besides that, CM-SVM also estimated the confidence and credibility for each predicted sample. By setting different confidence levels, CM-SVM can perform region prediction whose error rate was predefined by the different confidence levels, which was very important for the control of product quality when NIRS was applied to the analysis of productions. Confidence machine is designed as an on-line learning method; new samples can be added to the training set one by one to improve the efficiency of the model and is very appropriate for industry on-line analysis. On-line CM-SVM models showed that the confidence of prediction would be raised as the samples increased, which was valuable for industry on-line analysis.
王雅圣1，杨 梦2，骆志远2，王 酉1，李 光1, 胡瑞芬1*. 基于置信学习机与近红外光谱的煤种快速分类方法[J]. 光谱学与光谱分析, 2016, 36(06): 1685-1689.
WANG Ya-sheng1, YANG Meng2, LUO Zhi-yuan2, WANG You1, LI Guang1, HU Rui-fen1*. Rapid Coal Classification Based on Confidence Machine and Near Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(06): 1685-1689.
[1] Cozzolino D. Planta Medica, 2009, 75(7): 746. [2] Jamrógiewicz M. Journal of Pharmaceutical and Biomedical Analysis, 2012, 66: 1. [3] Agelet L E, Hurburgh Jr C R. Critical Reviews in Analytical Chemistry, 2010, 40(4): 246. [4] Kim D W, Lee J M, Kim J S. Korean Journal of Chemical Engineering, 2009, 26(2): 489. [5] Andres J, Bona M. Talanta, 2006, 70(4): 711. [6] Bona M, Andres J. Talanta, 2007, 72(4): 1423. [7] Andres J, Bona M. Analytica Chimica Acta, 2005, 535(1): 123. [8] Wang Y, Yang M, Wei G, et al. Sensors and Actuators B: Chemical, 2014, 193: 723. [9] Vovk V, Gammerman A, Shafer G. Algorithmic Learning in a Random World: Springer Science & Business Media, 2005. [10] Wang H, Lin C, Yang F, et al. Journal of Information and Computational Science, 2009, 6(1): 305. [11] Shafer G, Vovk V. The Journal of Machine Learning Research, 2008, 9: 371. [12] Burges C J. Data Mining and Knowledge Discovery, 1998, 2(2): 121. [13] Chen Q, Zhao J, Fang C, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2007, 66(3): 568. [14] Zhao J, Chen Q, Huang X, et al. Journal of Pharmaceutical and Biomedical Analysis, 2006, 41(4): 1198. [15] Widjaja E, Zheng W, Huang Z. International Journal of Oncology, 2008, 32(3): 653.
