Latent Variable Machine Learning Methods Applied for NIR Quantitative Analysis of Coffee
CHEN Hua-zhou1,2, XU Li-li3, QIAO Han-li1,2, HONG Shao-yong4*
1. College of Science, Guilin University of Technology, Guilin 541004, China
2. Center for Data Analysis and Algorithm Technology, Guilin University of Technology, Guilin 541004, China
3. College of Marine Sciences, Beibu Gulf University, Qinzhou 535011, China
4. School of Data Science, Guangzhou Huashang College, Guangzhou 511300, China
Abstract：Near-infrared (NIR) spectroscopy rapid detection technology was used to determine protein content in instant coffee. Support vector machine (SVM) and extreme learning machine (ELM) was applied for validating their practicality in modeling analysis. We proposed the latent variable SVM (LV-SVM) and latent variable ELM (LV-ELM) methods combined with latent variable analysis technique. Thetuning of latent variables and the optimization of the key parameters in machines were joint in-one so that the data dimension reduction and the selection of machine parameters can be both accomplished in one single modeling process. The calibrating-validating-testing mechanism was used for sample division. The NIR analytical models were trained based on the calibrating sample set. The model prediction results were generated and saved as a 3D box as they were determined by the simultaneous tuning of the latent variable and the machine parameter. Then the joint optimization of model parameters was selected in the way of predicting the validating samples. Further, the optimal model was evaluated by the testing samples. The optimal LV-SVM model gave the validating root mean square error as 6.797; the corresponding testing root mean square error as 8.384. The optimal LV-ELM model obtained the validating root mean square error as 6.118. The corresponding testing root means square error as 7.837. Compared with the common partial least square method, the LV-SVM and LV-ELM methods have better prediction results, which verified the application advantages of the latent variable machine learning method in near-infrared quantitative analysis. This proposed method is expected for further application in content detection of other kinds of coffee.
[1] Janissen B, Huynh T. Resources, Conservation and Recycling, 2018, 128: 110.
[2] YANG Kai-zhou, ZHAI Xiao-na, DU Bing-jian, et al(杨剀舟, 翟晓娜, 杜秉健, 等). Food Science(食品科学), 2014, 35(3): 243.
[3] Waters D M, Arendt E K, Moroni, A V. Critical Reviews in Food Science and Nutrition, 2017, 57(2): 259.
[4] CHEN Lei, AN Miao, YAN Hui-ying, et al(陈 雷, 安 苗, 闫会莹,等). Journal of Jilin Normal University·Natural Science Edition(吉林师范大学学报·自然科学版), 2017, 38(3): 79.
[5] HE Yong, PENG Ji-yu, LIU Fei, et al(何 勇, 彭继宇, 刘 飞,等). Transactioins of the Chinese Society of Agricultural Engineering(农业工程学报), 2015, 31(3): 174.
[6] Sakudo A. Clinica Chimica Acta, 2016, 455: 181.
[7] Jamshidi B, Mohajerani E, Jamshidi J. Measurement, 2016, 89: 1.
[8] Prieto N, Juarez M, Larsen I L, et al. Meat Science, 2015, 110: 76.
[9] LIANG Man, HUANG Fu-rong, HE Xue-jia, et al(梁 曼, 黄富荣, 何学佳, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(8): 2132.
[10] CHEN Wan-chao, TAO Xin, FAN Chang-chun, et al(陈万超, 陶 鑫, 范长春, 等). Chinese Journal of Analytical Chemistry(分析化学), 2019, 47(2): 315.
[11] Liu J, Chen N, Yang J, et al. Food Chemistry, 2018, 253: 284.
[12] Chen H, Xu L, Jia Z, et al. Analytical Letters, 2018, 51: 1564.
[13] Liu T, Li Z, Yu C, et al. Infrared Physics & Technology, 2017, 87: 124.
[14] Chen H, Liu X, Jia Z, et al. Chemometrics and Intelligent Laboratory Systems, 2018, 182: 101.
[15] BIN Jun, FAN Wei, ZHOU Ji-heng, et al(宾 俊, 范 伟, 周冀衡, 等). Tobacco Science & Technology(烟草科技), 2016, 49(9): 50.
[16] Shao X, Du G, Jing M, et al. Chemometrics and Intelligent Laboratory Systems, 2012, 114: 44.
[17] Henriquez P A, Ruz G A. Engineering Applications of Artificial Intelligence, 2019, 79: 13.
[18] Jin Y, Li J, Lang C Y,et al. Multidimensional Systems and Signal Processing, 2017, 28(3): 905.
