Quantitative Analysis Modeling of Near Infrared Spectroscopy With
Parallel Convolution Neural Network
YU Shui1, HUAN Ke-wei1*, LIU Xiao-xi2, WANG Lei1
1. College of Physics, Changchun University of Science and Technology, Changchun 130022, China
2. Jilin Institute of Science and Technology Information, Changchun 130033, China
Abstract：Near-infrared spectroscopy has become an indispensable analysis method in industrial and agricultural production process quality monitoring. It has been widely used in the qualitative and quantitative analysis of food, agriculture, medicine and others.-A near-infrared spectroscopy prediction model with high prediction accuracy, high-speed running,and strong generalization ability plays an essential role in the qualitative and quantitative analysis of different substances. However, due to the increase innear-infrared spectroscopy data, the disadvantages of traditional near-infrared spectroscopy modeling methods are obvious. With the development of artificial intelligence technology, deep learning algorithms have been widely used in the field of near-infrared spectroscopy. The quantitative analysis model of near-infrared spectroscopy based on a parallel convolution neural network (PaBATunNet) was proposed. PaBATunNet comprisedone1-D convolutional layer, one parallel convolution module (Module), one flattening layer, four fully connected layers and one parameter regulator (PR).The Module included five submodules and one Concatenate function, which was used to extract the linear and nonlinear multidimensional features of the spectral data, respectively and concatenate them. The prediction accuracy of PaBATunNet was improved by PR, which optimized the model parameters. The high contribution characteristic wavelengths of PaBATunNet were given based on Gard-CAM, which improved the interpretability of PaBATunNet. By taking public near-infrared spectroscopy datasets of grain, diesel fuel, beer and milk as examples, the prediction results of PaBATunNet were compared with partial least squares (PLS),principal component regression (PCR), support vector machine (SVM) and back propagation neural network (BP). The results showed that the prediction accuracies of PaBATunNet tograin, diesel fuel, beer and milk datasets were respectively increased by 30.0%, 40.7%, 43.0% and 52.8% in comparison with PLS, 28.8%, 35.9%, 40.8% and 52.2% in comparison with PCR, 45.5%, 37.4%, 45.3% and 54.7% in comparison with SVM, and 7.9%, 32.4%, 90.1% and 62.0% in comparison with BP. Compared with the traditional near-infrared spectroscopy modeling methods, the PaBATunNet based on the parallel convolutional neural network, has solved the problems of low prediction accuracy, long running time, poor generalization ability and poor interpretability. It can be effectively applied to quantitative analysis in industrial and agricultural production. It provides a theoretical basis for establishing the rapid, nondestructive and high-precision near-infrared spectroscopy quantitative analysis model.
Key words：Near-infrared spectroscopy; Deep learning; Parallel convolution neural network; Quantitative analysis; Prediction model
[1] Huan K W, Chen X, Song X Y, et al. Infrared Physics and Technology, 2021, 119: 103937.
[2] CHU Xiao-li, LU Wan-zhen(褚小立, 陆婉珍). Electronic Instrumentation Customers(仪器仪表用户), 2013, 20(2): 11.
[3] Zheng A B, Yang H H, Pan X P, et al. Sensors, 2021, 21(4): 1088.
[4] Chen C, Yang B, Si R M, et al. Optik, 2021, 242: 167080.
[5] Bourne N, Blyth D, Simon C. Journal of Near Infrared Spectroscopy, 2021, 29(4): 216.
[6] Li J, Yu X N, Ge W Z, et al. Analytical Letters, 2019, 52(2): 249.
[7] Afseth N K, Dankel K, Andersen P V, et al. Foods, 2022, 11(7): 962.
[8] Teng F, Ji J B, Yang Y, et al. Journal of Near Infrared Spectroscopy, 2022, 30(5): 246.
[9] Thien T F, Yeo W S. Chemical Engineering Communications, 2022, 209(11): 1439.
[10] ZHOU Hua-mao, CHEN Tian-bing, LIU Mu-hua, et al(周华茂, 陈添兵, 刘木华, 等). Chinese Journal of Analytical Chemistry(分析化学), 2020, 48(6): 811.
[11] He Y, Zhao X Y, Zhang W, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2022, 266: 120439.
[12] Aulia M N, Khodra M L, Koesoema A P. IOP Conference Series: Materials Science and Engineering, 2020, 803(1): 012019.
[13] Mishra P, Passos D. Chemometrics and Intelligent Laboratory Systems, 2021. 212: 104287.
[14] Zhang X L, Lin T, Xu J F, et al. Analytica Chimica Acta, 2019, 1058: 48.
[15] Ma X Y, Zhang S I, Sun J L, et al. Infrared Physics and Technology, 2022, 126: 104329.
[16] Chai Q Q, Zeng J, Lin D H, et al. Journal of Pharmaceutical and Biomedical Analysis, 2021, 199: 114035.
[17] WANG Lei, HUAN Ke-wei, LIU Xiao-xi, et al(王 磊, 宦克为, 刘小溪, 等). Chinese Journal of Analytical Chemistry(分析化学), 2022, 50(12): 1918.
[18] LI Ming, HAN Dong-hai, LU Ding-qiang, et al(李 明, 韩东海, 鲁丁强, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(11): 3355.
[19] Ma Y B, Babu K S, Amamcharla J K. LWT—Food Science and Technology, 2019, 109: 319.
[20] Marinoni L, Monti L, Barzaghi S, et al. Journal of Near Infrared Spectroscopy, 2013, 21 (5): 385.
[21] XU Guang-tong, LU Wan-zhen, YUAN Hong-fu(徐广通, 陆婉珍, 袁洪福). Petrochemical Technology(石油化工), 1999, 28(4): 51.
[22] Yun Y H, Wang W T, Deng B C, et al. Analytica Chimica Acta, 2015, 862: 14.
[23] Nørgaard L, Saudland A, Wagner J, et al. Applied Spectroscopy, 2000, 54(3): 413.
[24] Khosroshahi E M, Petel Y, Woll-Morison V. Laser Physics Letters, 2022, 19(7): 075602.
[25] Yun Y H, Li H D, Leslie R E, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2013, 111: 31.
[26] Deng B C, Yun Y H, Cao D S, et al. Analytica Chimica Acta, 2016, 908: 63.
[27] Ba T L, Thai T L H. Spectroscopy Letters, 2019, 52(10): 671.
[28] ZHAO Huan, HUAN Ke-wei, SHI Xiao-guang, et al(赵 环, 宦克为, 石晓光, 等). Chinese Journal of Analytical Chemistry(分析化学), 2018, 46(1): 136.
[29] CHEN Xiao, HUAN Ke-wei, ZHAN Huan, et al(陈 笑, 宦克为, 赵 环, 等). Chinese Journal of Analytical Chemistry(分析化学), 2021, 49(10): 1743.
