粗精选策略二进制灰狼优化算法用于红外光谱特征选择

doi:10.3964/j.issn.1000-0593(2023)10-3067-08

Abstract
References
Related Citation (15)

Download: PDF (3455 KB)
Export: BibTeX | EndNote (RIS)

Abstract Due to the seriously overlapped infrared spectral peaks of each component in hydrocarbon gas mixtures, which is caused by the high similarity of molecular structures, it has always been a difficult problem in stoichiometry to precisely monitor the concentration. A rough and fine selection strategy binary gray wolf optimization (RSBGWO) algorithm is proposed to optimize infrared spectral features and establish a high-precision quantitative analysis model to address this challenge. It takes the mean value of root mean square error (RMSECV) of the spectral quantitative analysis model based on cross-validation as the fitness function. In the rough selection stage, the first global iteration is carried out to update the location information of the selected characteristic variables for α wolf, β wolf and δ wolf. In the fine selection stage, combining the characteristic variables for α wolf, the characteristic variables for β wolf and δ wolf after eliminating the corresponding characteristic variables in which position are not selected for α wolf, are used to update the location information of wolves, in order to reduce the RMSECV value gradually and make sure that the extracted characteristic wavelength is globally optimal. In addition, a nonlinear convergence factor is introduced to accelerate the convergence speed.The algorithm is tested on the infrared spectral data set of 359 mixed alkane gas samples, and the effect of the proposed algorithm is verified. Compared with bGWO and bPSO feature extraction algorithms, the MLR model based ontheRSBGWO algorithm proposed in this paper reduces the number of the selected feature by more than 96% and increases the relative prediction deviation (RPD) by more than 15. The root mean square error of prediction (RMSEP) is lower than the instrument error of gas distribution system used for data acquisition when analyzing the concentrations of methane, ethane, propane and carbon dioxide. Compared with the MLR model and PLS model of full spectrum modeling, the prediction accuracy of the MLR model and PLS model based on the RSBGWO algorithm proposed in this paper is significantly improved, and the dependence of prediction effect on the quantitative analysis model is reduced. The experimental results show that the method proposed in this paper can significantly improve the analysis effect of the quantitative analysis model of infrared spectroscopy. The method can promote the application of spectral detection technology in biopharmaceuticals, the food chemical industry, oil and gas exploration, etc., especially in the application occasions containing homologous organic compounds.

Key words：Rough and fine selection strategy; Binary gray wolf optimization algorithm; Cross validation; Feature selection; Infrared spectroscopy; Quantitative analysis

Received: 2022-04-05 Accepted: 2022-10-17

ZTFLH:

O657.3

Cite this article:

LI Zhong-bing,JIANG Chuan-dong,LIANG Hai-bo, et al. Rough and Fine Selection Strategy Binary Gray Wolf Optimization Algorithm for Infrared Spectral Feature Selection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3067-3074.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2023)10-3067-08 OR https://www.gpxygpfx.com/EN/Y2023/V43/I10/3067

[1] Li Jiayi，Yu Mei，Li Shangke，et al. Food Science & Nutrition，2021，9(8)：4176.
[2] Chen Hui，Tan Chao，Lin Zan，et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy，2018，189：183.
[3] TAO Meng-qi，LIU Jia-xiang，WU Yue，et al(陶孟琪，刘家祥，吴越，等). Acta Optica Sinica(光学学报)，2020，40(7)：201.
[4] Mohammadi M，Khorrami M K K，Vatani A，et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy，2021，245：118945.
[5] Hu Leqian，Yin Chunling，Ma Shuai，et al. Food Analytical Methods，2019，12(3)：633.
[6] WANG Ke，JIANG Xiao-xiao，WANG Yong-qi，et al(王珂，江潇潇，王永琦，等). Manufacturing Automation (制造业自动化)，2021，43(4)：19.
[7] Al-Tashi Q，Kadir S J A，Rais H M，et al. IEEE Access，2019，7：39496.
[8] Mirjalili S，Mirjalili S M，Lewis A. Advances in Engineering Software，2014，69：46.
[9] Dhal P，Azad C. Applied Soft Computing，2021，107：7394.
[10] Gölcük $\dot{I}$ ，Ozsoydan F B. Knowledge-Based Systems，2020，194：105586.
[11] Nadimi-Shahraki M H，Taghian S，Mirjalili S. Expert Systems With Applications，2020，166：113917.
[12] Salgotra R，Singh U，Sharma S. Neural Computing & Applications，2020，32(8)：3709.
[13] Emary E，Zawbaa H M，Hassanien A E. Neurocomputing，2016，172：371.
[14] WU Xin-yan，BIAN Xi-hui，YANG Sheng，et al(武新燕，卞希慧，杨盛，等). Journal of Instrumental Analysis(分析测试学报)，2020，39(10)：1288.
[15] Abdel-Basset M，Sallam K M，Mohamed R，et al. IEEE Access，2021，9：139792.
[16] Abdel-Basset M，El-Shahat D，El-henawy I，et al. Expert Systems With Applications，2020，139：112824.
[17] Li Hongduan，Xu Qingsong，Liang Yizeng. Chemometrics and Intelligent Laboratory Systems，2018，176：34.
[18] LIU Xue-yi，LI Ping，GAO Chuan-hou(刘学艺，李平，郜传厚). Journal of Shanghai Jiaotong University(上海交通大学学报)，2011，45(8)：1140.