改进和声搜索算法的近红外光谱特征变量选择

doi:10.3964/j.issn.1000-0593(2020)06-1869-07

Abstract
References
Related Citation (15)

Download: PDF (2694 KB)
Export: BibTeX | EndNote (RIS)

Abstract Near-infrared spectroscopy has been widely used in many fields for detection and analysis because of its advantages of simplicity, speed, efficiency, low cost, and environment protection. However, the NIR spectra also contain interferences such as high variable dimension, multiple collinearities, redundant information, and high frequency noise. The direct construction of the prediction model not only increases the modeling complexity but also affects the prediction performance and generalization. For this purpose, a spectral feature variable selection method based on the improved Harmony Search algorithm (HS) is proposed. HS is often used to solve feature variable optimization problem. When the spectral variable selection is applied by the HS algorithm, the feature contribution of spectra is firstly calculated by the PLS loading coefficient as the disturbance weight of the improved HS. In the process of optimizing the spectral feature variables, the variable feature contribution is introduced as the excitation factor, and the initial solution vectors are generated by the combination of random traversal and excitation factor. When generating the new harmony vector, the feature contribution is applied as a penalty factor, and the parameters of HS are dynamically adjusted with the number of iterations by adding the balance factor, so as to adapt to the search of spectral variables. It enhances the ergodicity of the search process and the diversity of the population. In order to verify the effectiveness of the algorithm, the NIR PLS models of nicotine, total sugar and total nitrogen using tobacco samples are constructed. After pre-processing the original spectra, this method is used to optimize spectral variables. The prediction performance of each model corresponding to the number of different variables is calculated according to the cumulative frequency at which the variables are selected, and the final selected spectral variables are determined by the increasing trend of the Root Mean Square Error of Calibration (RMSEC) with the variables. The three PLS models are established on the training set and the test set respectively, and they are compared with the full spectrum, Uninformative Variables Elimination (UVE) and Particle Swarm Optimization (PSO). The experimental results show that the coefficient of determination (R²) of nicotine, total sugar and total nitrogen models using the selected variables is 0.921 1, 0.925 7 and 0.941 2, respectively; and the Root Mean Square Error of Prediction (RMSEP) is 0.102 3, 1.034 6 and 0.053 1. Compared with other methods, the RMSEP of this study is low, the R² of these models is more than 0.92, and the spectral characteristic variables are small. It is shown that the improved HS algorithm can effectively filter the feature spectrum, reduce the modeling complexity, improve the model prediction performance and generalization ability.

Key words：Near infrared spectroscopy; Feature variables; Harmony search algorithm; Loading factor; Partial least squares

Received: 2019-04-15 Accepted: 2019-08-04

ZTFLH:

O657.3

Corresponding Authors: WU Li-jun E-mail: wallis8@126.com

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2020)06-1869-07 OR https://www.gpxygpfx.com/EN/Y2020/V40/I06/1869

[1] CHEN Li-ju，LIU Wei（陈丽菊, 刘巍）. Modern Physics（现代物理知识）, 2016, 18(2)：10.
[2] SUN Wen-ping，GONG Hui-li，WANG Mei-xun，et al（孙文苹, 宫会丽, 王梅勋, 等）. Microcomputer & Its Applications（微型机与应用）, 2015, 34(1): 78.
[3] LI Qian-qian，TIAN Kuang-da，LI Zu-hong，et al（李倩倩, 田旷达, 李祖红, 等）. Chinese Journal of Analytical Chemistry（分析化学）, 2013, 41(6): 917.
[4] XU Bao-ding，QIN Yu-hua，YANG Ning，et al（徐宝鼎, 秦玉华, 杨宁, 等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2019, 39(3)：717.
[5] WANG Yong，WANG Li-fu，ZOU Hui，et al（王勇, 王李福, 邹辉, 等）. Computer Engineering and Design（计算机工程与设计）, 2018, 378(6): 127.
[6] Moayedikia A, Ong K L, Boo Y L, et al. Engineering Applications of Artificial Intelligence, 2017, 57(C): 38.
[7] Enayatifar R, Yousefi M, Abdullah A H, et al. Communications in Nonlinear Science & Numerical Simulation, 2013, 18(12): 3481.
[8] ZHAI Jun-chang，GAO Li-qun，OUYANG Hai-bin，et al（翟军昌, 高立群, 欧阳海滨, 等）. Control and Decision（控制与决策）, 2015, 30(11): 1953.
[9] Khalili M, Kharrat R, Salahshoor K, et al. Applied Mathematics & Computation, 2014, 228(9): 195.
[10] Sutskever I, Hinton G E. Neural Computation, 2014, 20(11): 2629.
[11] OUYANG Hai-bin，GAO Li-qun，ZOU De-xuan，et al（欧阳海滨, 高立群, 邹德旋, 等）. Control Theory and Applications（控制理论与应用）, 2014, 31(1): 57.
[12] JIANG Hong，SU Yang（江虹, 苏阳）. Laser and Infrared（激光与红外）, 2016, 46(1): 119.
[13] Abdelgayed T S, Morsi W G, Sidhu T S. IEEE Transactions on Smart Grid, 2018, 9(2): 521.
[14] LIU Yan，CAI Wen-sheng，SHAO Xue-guang（刘言, 蔡文生, 邵学广）. Chinese Science Bulletin（科学通报）, 2015，(8): 704.