Infrared Spectra Modeling of Insoluble Dietary Fiber Content in Moso Bamboo Shoot Based on Autoencoder Network Manifold Learning
YU Xin-jie1, YIN Jiao-jiao1,3, YU Xin1, HE Yong2*
1. Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, China 2. College of Biosystems Engineering and Food Science，Zhejiang University，Hangzhou 310058，China 3. Taiyuan University of Science and Technology, Taiyuan 030024，China
Abstract：Autoencoder network (AN) is a nonlinear dimension reduction manifold learning algorithm which can find out nonlinear low-dimensional manifold structure from high dimensional spectra data effectively. In the present paper, a nonlinear infrared (IR) spectra modeling method AN-PLS was proposed by combining AN and partial least squares (PLS) to reflect the nonlinear correlations existing between IR spectra and physicochemical properties of samples. In AN-PLS, AN and PLS were adopted to deduct the dimensions of IR spectra and build regression calibration model, respectively. The AN-PLS was then applied to correlate the near infrared (NIR) spectra and the mid infrared (MIR) spectra with the concentrations of insoluble dietary fiber in bamboo shoots. The results indicate that AN-PLS can predict the concentrations of insoluble dietary fiber in bamboo shoots with a lower cross validation RMS error (RMSECV) and higher determinative coefficient (R2), than other common spectra data preprocessing methods combined with PLS or sole PLS. It can be concluded that AN-PLS can effectively model the nonlinear correlations between IR spectra and physicochemical properties of the samples. And it is feasible to accurately detect the concentrations of insoluble dietary fiber in the bamboo shoots by coupling NIR and MIR spectra with AN-PLS modeling method.
[1] YAN Yan-lu, ZHAO Long-lian, HAN Dong-hai, et al(严衍禄, 赵龙莲, 韩东海, 等). Basic and Application of Near Infrared Spectroscopy Analysis(近红外光谱分析基础与应用). Beijing: China Light Industry Press(北京: 中国轻工业出版社), 2005. 1. [2] QIN Feng, YANG Hui-hua, Lü Lin-ang, et al(覃 锋, 杨辉华, 吕琳昂, 等). Chinese Traditional Patent Medicine(中成药), 2008, 30(10): 1465. [3] Hinton G E, Salakhutdinov R R. Science, 2006, 313: 504. [4] HU Zhao-hua, SONG Yao-liang(胡昭华, 宋耀良). Journal of Electronics & Information Technology(电子与信息学报), 2009, 31(5): 1189 [5] Anderson J W, Baird P, Davis R H, et al. Nutr. Rev., 2009, 67: 188. [6] Le Roux N, Bengio Y. Neural Computation, 2008, 20(6): 1631. [7] Plaut D C, Hinton G E. Computer Speech and Language, 1987, 2: 35. [8] Nair V, Hinton G E. Rectified linear units improve Restricted Boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel, 2010. 807. [9] Tan C C, Eswaran C. Neural. Comput. & Applic., 2010, 19: 1069. [10] Lee S C, Prosky L, De Vries J W. Journal of AOAC, 1992, 75: 395.
