NIR Spectral Feature Selection Using Lasso Method and Its Application in the Classification Analysis
LI Yu-qiang1, PAN Tian-hong1, 2*, LI Hao-ran1, ZOU Xiao-bo3
1. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China
2. School of Electrical Engineering and Automation, Anhui University, Hefei 230061, China
3. School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China
Abstract：Near-infrared spectroscopy (NIRS) is a non-destructive detection method for qualitative or quantitative analysis by using spectral feature data. The integrity and representativeness of feature data determine the performance of the analytical model. However, existing analytical methods can only extract the feature data from the spectral subinterval. Then the developed models using these feature extracting methods have poor stability. In order to extract the feature from the high-dimensional NIR spectral data and improve the accuracy and stability of NIR spectral model, a spectral screening method using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm is proposed in this paper. Furthermore, the Tricholoma Matsutake, one of the high-value foreign trade products in China is taken as example to validate the developed classified model using LASSO algorithm. The effectiveness of the feature screening algorithm for the high-dimensional spectral data is discussed, and predictive accuracy and stability of the Tricholoma Matsutake distinguished and edible fungus classified model using LASSO and PCA are also analyzed. It is well known that the fresh Tricholoma Matsutake has the unique shape and it is easy to distinguish its counterfeit. However, it is difficult to distinguish the dry Tricholoma Matsutake from other mushrooms because all of dry mushrooms have the similar flake shape. As a result, dry Tricholoma Matsutake adulteration incidents have occurred frequently. 166 dry samples of Yunnan Tricholoma Matsutake, Pleurotuseryngii, Jujube hilt nipple mushroom and Agaricusblazei were selected in this experiment, and 166×512-dimensional raw spectral data were obtained by NIRQuest 512 NIR spectrometer with a spectral range of 900～1 700 nm. The standard normal transformation (SNV) was taken to pre-process the spectral data after the anomalous data eliminating. The LASSO was used to extract feature variables from the high-dimensional NIR spectral data based on the spectral pretreatment. Then the typical linear (k-Nearest Neighbor, KNN) and the nonlinear modeling (Back-Propagation neural network, BP) algorithms combined with the Kennard-Stone method were used to construct the Tricholoma Matsutake distinguished and edible fungus classified model. The effectiveness of models using LASSO and PCA were also analyzed. Furthermore, the predictive accuracy and the stability of the developed KNN model and BP model were analyzed by using the Monte Carlo method. The experimental results demonstrated that the prediction accuracy and stability of model using LASSO were better than those of the model using PCA. The prediction accuracy of the distinguished and edible fungus classified models using the original spectral data were 69.57% (BP), 60.87%(KNN) and 67.39% (BP), 65.22% (KNN) respectively. And the prediction accuracy of the distinguished and edible fungus classified models using LASSO algorithm were up to 100% (BP), 67.39% (KNN) and 89.13% (BP), 80.43% (KNN) respectively. The two models were performed by 10 times Monte Carlo method and the average results were 99.93% and 97.22%, respectively. Compared with the conventional feature selection methods (such as PCA), the LASSO algorithm can extract the feature from the high-dimensional NIR spectral data. And the accuracy and stability of the models using NIR spectral data can be improved. Furthermore, the developed algorithm is alternative to be a new feature extraction method for NIR spectral data analysis.
Key words：NIRS; Feature extraction; LASSO; Tricholoma Matsutake discrimination; Monte Carlo method
李鱼强，潘天红，李浩然，邹小波. 近红外光谱LASSO特征选择方法及其聚类分析应用研究[J]. 光谱学与光谱分析, 2019, 39(12): 3809-3815.
LI Yu-qiang, PAN Tian-hong, LI Hao-ran, ZOU Xiao-bo. NIR Spectral Feature Selection Using Lasso Method and Its Application in the Classification Analysis. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(12): 3809-3815.
[1] WANG Meng-dong, WANG Sheng-peng(王梦东, 王胜鹏). Journal of Huazhong Agricultural University(华中农业大学学报), 2015, 34(1): 123.
[2] Yahui L, Xiaobo Z, Tingting S，et al. Food Anal. Methods，2017：10: 1034.
[3] Balabin R M, Smirnov S V. Analytica Chimica Acta, 2011, 692(1): 63.
[4] WU Xi-yu, ZHU Shi-ping, WANG Qian, et al(吴习宇, 祝诗平, 王 谦, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(8): 2369.
[5] Xu Y, Kutsanedzie F Y H, Sun H，et al. Food Anal. Methods，2018，11: 1199.
[6] LI Lu, HUANG Han-ying, LI Yi, et al(李 路, 黄汉英, 李 毅，等). Food and Fermentation Industries(食品与发酵工业), 2018, 44(2): 87.
[7] Saptoro A, Tadé M, Vuthaluru H. Chemical Product and Process Modeling, 2012, 7(1): 1.
[8] Wu X, Wu B, Sun J, et al. Journal of Food Process Engineering, 2017, 40(2): 23.
[9] LIU Pi-lian, WANG Xiao, LIU Mu-hua, et al(刘丕莲, 王 晓, 刘木华，等). Chinese Journal of Pesticide Science(农药学学报), 2014, 16(1): 106.
[10] Frank A F, Hlutkowsky C, Bemis L, et al. NeuroImage, 2019, 184: 68.
[11] Zhang Liguo, Zhang Xin, Ni Lijun, et al. Food Chemistry, 2014, 145: 342.
[12] Yosra A, Estrella Funes L Gabriel Beltran M, et al. Journal of Near Infrared Spectroscopy, 2015, 23(2): 111.
[13] Teye E, Huang X Y, Lei W, et al. Food Research International, 2014, 55: 288.
[14] Verleker A P, Shaffer M, Fang Q, et al. Applied Optics, 2017, 56(4): 1131.
