Near Infrared Spectroscopy Wavelength Selection Method and the Application Based on Synergy Interval Gaussian Process
XU Chen, YIN Yan-yan, LIU Fei*
Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University, Wuxi 214122, China
Abstract:Based on Gaussian Process (GP), a wavelength selection algorithm named Synergy Interval Gaussian Process (siGP) model is proposed in this paper by using near infrared spectroscopy technology. Full spectrum is divided into a series of unique and equal spacing intervals, before selecting optimal several intervals to establish GP model. Due to the GP model with nonlinear processing ability, the method reduces the disadvantages of nonlinear factor. Taking the near infrared spectrum data of moisture content and pH in solid-state fermentation of monascus as performance verification object of this new algorithm, the prediction correlation coefficient (Rp) of moisture content and pH are 0.956 4 and 0.977 3, respectively. The root mean square errors for prediction set (RMSEP) are 0.012 7 and 0.161 0, respectively. Data points participating in modeling decrease respectively from the original 1 500 to 225 and 375. In the prediction for independent samples, it shows good accuracy. Comparing with traditional synergy interval partial least squares (siPLS) algorithm, the results show that the siGP achieves the best prediction result. The prediction correlation coefficient of moisture content and pH in new algorithm has increased respectively by 3.37% and 3.51% under the model of Gaussian Process, with increases of 29.4% and 34.8% in the root mean square errors for prediction set. This study shows that the combination of siGP and GP model can select wavelength effectively and improves the prediction accuracy of the NIR model. This method is reference for realizing the online detection and optimization control.
[1] Zou Xiaobo, Zhao Jiewen, Povey M J W, et al. Analytica Chimica Acta, 2010, 667(1): 14. [2] Agelet L, Hurburgh C. Jr. Critical Reviews in Analytical Chemistry,2010, 40(4): 246. [3] Balabin R, Smirnov S. Analytica Chemica Acta,2011, 692(1): 63. [4] Chen M L, Khare S, Huang B, et al. Industrial & Engineering Chemistry Research, 2013, 52(23): 7886. [5] Blanco M, Coello J, Iturriaga H, et al. Chemometrics and Intelligent Laboratory Systems,2000, 50(1): 75. [6] Chauchard F, Cogdill R, Roussel S, et al. Chemometrics and Intelligent Laboratory Systems,2004, 71(2): 141. [7] Chen Q S, Zhao J W, Liu M H, et al. Journal of Pharmaceutical and Biomedical Analysis, 2008, 46(3): 568. [8] Chen T, Morris J, Martin E. Chemometrics and Intelligent Laboratory Systems,2007, 87(1): 59. [9] Rasmussen C E,Williams C K I. Massachusetts Institute of Technology: The MIT Press, 2006. [10] HE Zhi-kun, LIU Guang-bin, ZHAO Xi-jing, et al(何志昆, 刘光斌, 赵曦晶, 等). Control and Decision(控制与决策), 2013, 28(8): 1121. [11] Chen T, Wang B. Neurocomputing, 2010, 73(13): 2718. [12] LEI Yu, YANG Hui-zhong(雷 瑜, 杨慧中). CIESC Journal(化工学报), 2013, 64(12): 4434. [13] Peng Jiangtao, Jiang An, Peng Silong. Analytica Chemica Acta,2010, 667(1): 14.