Near Infrared Spectroscopy Transfer Based on Deep Autoencoder
LIU Zhen-wen1, XU Ling-jie2*, CHEN Xiao-jing3
1. College of Harbour and Environmental Engineering, Jimei University,Xiamen 361021, China
2. College of Mechanical and Electrical Engineering, Wenzhou University,Wenzhou 325035, China
3. College of Electrical and Electronic Engineering, Wenzhou University,Wenzhou 325035, China
Abstract:The establishment of a near-infrared spectroscopy multivariate calibration model relies on calibration samples. However, changes in the near-infrared spectroscopy measurement environment can cause differences between the spectra easily. In order to reduce the consumption of rebuilding calibration model on offset spectrum, this paper proposes a nonlinear spectral transfer method based on deep autoencoder (DAE), which can realize the spectral transfer in an end-to-end way. This method compensates for the poor performance of existing linear spectral transfer methods in the face of nonlinear offset spectra. Moreover, this method can realize the transfer between raw spectra without data process and feature extraction operations. In the paper, we propose an error function penalty term based on the conditional probability distribution and parameter maximum likelihood method, and combine it to the gradient back-propagation algorithm to optimize the parameters of DAE. In order to verify the effectiveness of the method, we perform the proposed method on tablet dataset and corn dataset, which are both public near-infrared spectral datasets. First, we divide the two datasets into the calibration set, validation set, and prediction set using Kennard-Stone (KS) method respectively. Then, we design a network structure that conforms to the spectral sample dimension of the dataset. Finally, samples in calibration set are input to the DAE, and the network parameters are iteratively optimized by the proposed error function and back-propagation algorithm. After the transfer model is established, we compare it with the spatial transformation (SST) and piecewise direct standardization (PDS), both of them are classical linear transfer algorithm. The transferred spectrum obtained by these three algorithms are respectively inputted into the established multivariate calibration model, and we can find that the root means square error of prediction (RMSEP) of the proposed method averagely improves 5.7% and 10.1% than SST and PDS respectively, which can be demonstrated that the spectral samples transferred by the nonlinear deep autoencoder are highly efficient and useful.
Key words:Near infrared spectroscopy; Model transfer; Multivariate calibration; Deep auto-encoder
刘贞文,徐玲杰,陈孝敬. 深度自编码器的近红外光谱转移研究[J]. 光谱学与光谱分析, 2020, 40(07): 2313-2318.
LIU Zhen-wen, XU Ling-jie, CHEN Xiao-jing. Near Infrared Spectroscopy Transfer Based on Deep Autoencoder. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(07): 2313-2318.
[1] Abdali S, Daneshfar A, Ghaedi M, et al. Analytical Methods, 2016,8: 6074.
[2] Huang G Z, Chen X J, Li L M, et al. Chemometrics and Intelligent Laboratory Systems, 2020, 201: 103986.
[3] Feudale R N, Woody N A, Tan H, et al. Chemometrics and Intelligent Laboratory Systems, 2002, 64: 181.
[4] Sulub Y, LoBrutto R, Vivilecchia R, et al. Analytica Chimica Acta, 2008, 611: 143.
[5] Bouveresse E, Hartmann C, Massart D L, et al. Analytical Chemistry, 1996,68:982.
[6] Zhang J, Guo C, Cui X, et al. Analytica Chimica Acta, 2019,1050:25.
[7] Wang Y, Veltkamp D J, Kowalski B R. Analytical Chemistry, 1991,63:2750.
[8] Tan H W, Brown S D. Journal of Chemometrics, 2001,15:647.
[9] Fan W, Liang Y, Yuan D, et al. Analytica Chimica Acta, 2008,623:22.
[10] Du W, Chen Z P, Zhong L J, et al. Analytica Chimica Acta, 2011,690:64.
[11] Kalivas J H. Journal of Chemometrics, 2012, 26: 218.
[12] Jansen J J, Hoefsloot H C J, van der Greef J, et al. Analytica Chimica Acta, 2005,530:173.
[13] Liu T, Li Z, Yu C, et al. Infrared Physics & Technology, 2017,87:124.
[14] Cybenko G. Mathematics of Control, Signals and Systems, 1989,2:303.
[15] Goodfellow I, Bengio Y, Courville A. Deep Learning, MIT Press, 2016.
[16] Zhang J, Cui X, Cai W, et al. Journal of Chemometrics, 2018,32:e2971.
[17] Kennard R W, Stone L A. Technometrics, 1969, 11(1): 137.
[18] Chen X J, Xu Y L, Meng L W, et al. Sensors and Actuators B: Chemical, 2020, 311: 127924.