Abstract：The modulus of elasticity is an important mechanical index of wood. The advantages of spectral analysis technology include a simple, convenient and fast operation process, which has become an important tool for wood testing. However, in practical applications, we often face changes in temperature and humidity of near-spectrometer testing conditions or aging of instrument components and replacement of accessories when the collected spectral data will be shifted. In order to solve this problem, this paper proposes a near-infrared spectral modeling method combining migration learning and spectral transfer calibration to address the poor generalization of the master model due to the difference data from different types of spectrometers，taking the near-infrared spectral prediction model of larch bending strength as the research object. Firstly, 200 sets of Larch test specimens were processed. Two kinds of spectrometers, the NIRQuest512 spectrometer as the master instrument and the One-chip as the slave, were used to collect the spectral data of Larch test specimens respectively. And the true values of the test specimens were detected by the mechanical universal testing machine. Secondly, the preprocessing of SNV, S-G and spectral shearing was employed, and then the method of PDS transfer correction was applied to complete the linear transformation from the slave instrument to the master. Thirdly, the SWCSS was used to extract the features of two kinds of spectral data, and the stable wave points were optimized. Finally, the GFK-SVM model was established by using two types of near-infrared spectral data of 100 sets of specimens. 100 sets of data were applied to test and compare the modeling methods such as DS-PLS, PDS-PLS, DS-SWCSS-GFK-SVM, and PDS-SWCSS-GFK-SVM. The experimental results show that PDS, compared with DS, can better complete the linear mapping of spectral data due to the sliding window, which could unify the optical length and wave points between the two spectrometers, and improve the modeling accuracy to a certain extent; As a feature extraction method, SWSS can select wavebands according to the differences and similarities of the two groups of spectral data sets, which can ensure the effectiveness and stability of features, and improve the modeling accuracy; The GFK-SVM is suitable for the migration of different spectral data. It can realize high-dimensional mapping of different types of spectral data through reasonable kernel function parameters. A generalized model for different datasets is constructed to realize the generalization of the master model on the slave spectral prediction, which improves the data efficiency, and the test set correlation coefficient Rp reaches 0.875, and the root mean square error RMSEP is 11.975.
Key words：Wood bending strength; Calibration transfer; Transfer learning; GFK-SVM
陈金浩，蒋大鹏，张怡卓，王克奇. 实木板材抗弯强度的SWCSS-GFK-SVM数据迁移建模方法[J]. 光谱学与光谱分析, 2022, 42(05): 1471-1477.
CHEN Jin-hao, JIANG Da-peng, ZHANG Yi-zhuo, WANG Ke-qi. Research on Data Migration Modeling Method for Bending Strength of
Solid Wood Based on SWCSS-GFK-SVM. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1471-1477.
[1] LIU Ya-na, YANG Zhong, LÜ Bin, et al(刘亚娜, 杨 忠, 吕 斌, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(3): 648.
[2] WANG Cheng-kun, ZHAO Peng(王承琨, 赵 鹏). Journal of Infrared and Millimeter Waves(红外与毫米波学报), 2020, 39(1): 72.
[3] CHAI Yu-bo, SUN Bo-ling, LIU Jun-liang, et al(柴宇博, 孙柏玲, 刘君良, 等). Scientia Silvae Sinicae(林业科学), 2014, 50(9): 124.
[4] Workman J. J. Applied Spectroscopy, 2018, 72(3): 340.
[5] Shi Yunying, Li Jingyan, Chu Xiaoli. Chinese Journal of Analytical Chemistry, 2019, 47(4): 479.
[6] ZHANG Jin, CAI Wen-sheng, SHAO Xue-guang(张 进, 蔡文生, 邵学广). Progress in Chemistry(化学进展), 2017, 29(8): 902.
[7] Chen W R, Bin J, Lu H M, et al. Analyst, 2016, 141(6): 1973.
[8] Greensill C V, Wolfs P J, Spiegelman C H, et al. Applied Spectroscopy, 2001, 55(5): 647.
[9] Pu Y Y, Sun D W, Riccioli C, et al. Food Analytical Methods, 2018, 11(4): 1021.
[10] Qin Y, Gong H. Infrared Physics & Technology, 2016, 77: 239.
[11] Luoma P, Natschläger T, Malli B, et al. Analytica Chimica Acta, 2018, 1007: 10.
[12] Fernandez L, Guney S, Gutierrez-Galvez A, et al. Sensors and Actuators B: Chemical, 2016, 231: 276.
[13] Zhang F, Zhang R, Ge J, et al. Analytical Methods, 2018, 10(18): 2169.
[14] Workman J J. Applied Spectroscopy, 2018, 72(3): 340.
[15] Chen Y, Wang Z. Chemometrics and Intelligent Laboratory Systems, 2019, 192: 103824.
[16] Poerio D V, Brown S D. Applied Spectroscopy, 2018, 72(3): 378.
[17] Yu B, Ji H. Analytical Methods, 2015, 7(6): 2714.
[18] ZHUANG Fu-zhen, LUO Ping, HE Qing, et al(庄福振, 罗 平, 何 清, 等). Journal of Sofeware(软件学报), 2015, 26(1): 26.
[19] Gong B, Shi Y, Sha F, et al. Geodesic Flow Kernel for Unsupervised Domain Adaptation. 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2012, 2066.
[20] Ni L, Han M, Luan S, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 206: 350.
[21] NI Li-jun, HAN Ming-yue, ZHANG Li-guo, et al(倪力军, 韩明月, 张立国, 等). Chinese Journal of Analytical Chemistry(分析化学), 2018, 46(10): 1660.
[22] Teye E, Anyidoho E, Agbemafle R, et al. Infrared Physics & Technology, 2020, 104: 103127.
