|
|
|
|
|
|
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.
|
Received: 2019-10-08
Accepted: 2020-01-30
|
|
Corresponding Authors:
XU Ling-jie
E-mail: grapefruitxlj@163.com
|
|
[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. |
[1] |
GAO Feng1, 2, XING Ya-ge3, 4, LUO Hua-ping1, 2, ZHANG Yuan-hua3, 4, GUO Ling3, 4*. Nondestructive Identification of Apricot Varieties Based on Visible/Near Infrared Spectroscopy and Chemometrics Methods[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 44-51. |
[2] |
BAO Hao1, 2,ZHANG Yan1, 2*. Research on Spectral Feature Band Selection Model Based on Improved Harris Hawk Optimization Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 148-157. |
[3] |
HU Cai-ping1, HE Cheng-yu2, KONG Li-wei3, ZHU You-you3*, WU Bin4, ZHOU Hao-xiang3, SUN Jun2. Identification of Tea Based on Near-Infrared Spectra and Fuzzy Linear Discriminant QR Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3802-3805. |
[4] |
LIU Xin-peng1, SUN Xiang-hong2, QIN Yu-hua1*, ZHANG Min1, GONG Hui-li3. Research on t-SNE Similarity Measurement Method Based on Wasserstein Divergence[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3806-3812. |
[5] |
BAI Xue-bing1, 2, SONG Chang-ze1, ZHANG Qian-wei1, DAI Bin-xiu1, JIN Guo-jie1, 2, LIU Wen-zheng1, TAO Yong-sheng1, 2*. Rapid and Nndestructive Dagnosis Mthod for Posphate Dficiency in “Cabernet Sauvignon” Gape Laves by Vis/NIR Sectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3719-3725. |
[6] |
WANG Qi-biao1, HE Yu-kai1, LUO Yu-shi1, WANG Shu-jun1, XIE Bo2, DENG Chao2*, LIU Yong3, TUO Xian-guo3. Study on Analysis Method of Distiller's Grains Acidity Based on
Convolutional Neural Network and Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3726-3731. |
[7] |
LUO Li, WANG Jing-yi, XU Zhao-jun, NA Bin*. Geographic Origin Discrimination of Wood Using NIR Spectroscopy
Combined With Machine Learning Techniques[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3372-3379. |
[8] |
ZHANG Shu-fang1, LEI Lei2, LEI Shun-xin2, TAN Xue-cai1, LIU Shao-gang1, YAN Jun1*. Traceability of Geographical Origin of Jasmine Based on Near
Infrared Diffuse Reflectance Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3389-3395. |
[9] |
YANG Qun1, 2, LING Qi-han1, WEI Yong1, NING Qiang1, 2, KONG Fa-ming1, ZHOU Yi-fan1, 2, ZHANG Hai-lin1, WANG Jie1, 2*. Non-Destructive Monitoring Model of Functional Nitrogen Content in
Citrus Leaves Based on Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3396-3403. |
[10] |
HUANG Meng-qiang1, KUANG Wen-jian2, 3*, LIU Xiang1, HE Liang4. Quantitative Analysis of Cotton/Polyester/Wool Blended Fiber Content by Near-Infrared Spectroscopy Based on 1D-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3565-3570. |
[11] |
HUANG Zhao-di1, CHEN Zai-liang2, WANG Chen3, TIAN Peng2, ZHANG Hai-liang2, XIE Chao-yong2*, LIU Xue-mei4*. Comparing Different Multivariate Calibration Methods Analyses for Measurement of Soil Properties Using Visible and Short Wave-Near
Infrared Spectroscopy Combined With Machine Learning Algorithms[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3535-3540. |
[12] |
KANG Ming-yue1, 3, WANG Cheng1, SUN Hong-yan3, LI Zuo-lin2, LUO Bin1*. Research on Internal Quality Detection Method of Cherry Tomatoes Based on Improved WOA-LSSVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3541-3550. |
[13] |
HUANG Hua1, LIU Ya2, KUERBANGULI·Dulikun1, ZENG Fan-lin1, MAYIRAN·Maimaiti1, AWAGULI·Maimaiti1, MAIDINUERHAN·Aizezi1, GUO Jun-xian3*. Ensemble Learning Model Incorporating Fractional Differential and
PIMP-RF Algorithm to Predict Soluble Solids Content of Apples
During Maturing Period[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3059-3066. |
[14] |
CHEN Jia-wei1, 2, ZHOU De-qiang1, 2*, CUI Chen-hao3, REN Zhi-jun1, ZUO Wen-juan1. Prediction Model of Farinograph Characteristics of Wheat Flour Based on Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3089-3097. |
[15] |
GUO Ge1, 3, 4, ZHANG Meng-ling3, 4, GONG Zhi-jie3, 4, ZHANG Shi-zhuang3, 4, WANG Xiao-yu2, 5, 6*, ZHOU Zhong-hua1*, YANG Yu2, 5, 6, XIE Guang-hui3, 4. Construction of Biomass Ash Content Model Based on Near-Infrared
Spectroscopy and Complex Sample Set Partitioning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3143-3149. |
|
|
|
|