|
|
|
|
|
|
A Mid-Infrared Wavelength Selection Method Based on the Impact Value of Variables and Population Analysis |
ZHANG Feng1, TANG Xiao-jun1*, TONG Ang-xin1, WANG Bin1, TANG Chun-rui2, WANG Jie2 |
1. State Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University, Xi’an 710049, China
2. CCTEG Chongqing Engineering (Group) Co., Ltd., Chongqing 400042, China |
|
|
Abstract The Fourier transform infrared spectra absorption peaks of alkane gases are overlapping seriously in the mid-infrared region. A wavelength selection method based on the impact value of variables and population analysis (IVPA) is proposed to select the wavelength of five alkane gases infrared spectra composed with methane, eth, propane, iso-butane and n-butane. IVPA algorithm will go through a number of iterations to select variables. In each iteration, the variables are divided into sample space and variable space. The impact value of variables is calculated in the sample space. According to the impact value, the variables are divided into elite variables and normal variables by using the weighted bootstrap sampling technology. Meanwhile, in the variable space, the frequency of each variable in the optimal model is counted. Finally, the variables with a lower frequency of normal variables are eliminated by the exponential decay function, and the root means squared error (RMSE) value obtained during each iteration is recorded. The variable subset corresponding to the minimum RMSE as the final selected variable. The proposed algorithm is tested by alkane dataset, and the results are compared with stability competitive adaptive reweighted sampling (SCARS) and iteratively variable subset optimization (IVSO) variable selection method proposed in recent years. Taking iso-butane analysis results as an example, the minimum cross-sensitivity of IVSO, IVPA and IVPA to the other four gases was 0.67%, 0.56% and 0.11%, respectively. The maximum cross sensitivity was 1.69%, 1.49% and 1.02%, respectively. The relative errors of iso-butane prediction were 1.94%, 1.65% and 0.51%, respectively. The number of selected variables by the above three methods is 52, 17 and 13, respectively. The results show that the IVPA method selected the least variables, only 0.36% of the original spectral data, obtained the lowest cross sensitivity for the other four gases, and got the most accurate prediction for iso-butane, which shows that the proposed wavelength selection method can be applied to the absorption overlapping spectra, and can improve the prediction accuracy and efficiency of the analytical model.
|
Received: 2020-06-18
Accepted: 2020-10-08
|
|
Corresponding Authors:
TANG Xiao-jun
E-mail: xiaojun_tang@xjtu.edu.cn
|
|
[1] Tao L, Lin Z,Chen J, et al. Journal of Pharmaceutical & Biomedical Analysis, 2017, 145: 1.
[2] Shen X C, Xu L, Ye S B, et al. Optics Express, 2018, 26(10): A609.
[3] Jiang W, Lu C, Zhang Y, et al. Analytical Methods, 2019, 11: 3108.
[4] Tang X J, Li Y J, Zhu L J, et al. Chemometrics and Intelligent Laboratory Systems, 2015, 146: 371.
[5] ZHANG Feng, TANG Xiao-jun, TONG Ang-xin, et al(张 峰, 汤晓君, 仝昂鑫, 等). J. Infrared Millim. Waves(红外与毫米学报),2020, 39(3): 318.
[6] Tian H, Li M, Wang Y, et al. Infrared Physics & Technology, 2017, 86: 98.
[7] Xia Z, Sun Y, Cai C, et al. Sensors, 2019, 19: 1981.
[8] Chen J, Yang C, Zhu H, et al. Chemometrics and Intelligent Laboratory Systems, 2018, 182: 188.
[9] Xu D, Liu S, Cai Y, et al. Applied Optics, 2019, 58(14): 3913.
[10] Han Q J, Wu H L, Cai C B, et al. Analytica Chimica Acta, 2008, 612: 121.
[11] LIU Guo-hai, XIA Rong-sheng, JIANG Hui, et al(刘国海,夏荣盛,江 辉,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2014, 34(8): 2094.
[12] Zheng K, Li Q, Wang J, et al. Chemometrics & Intelligent Laboratory Systems, 2012, 112: 48.
[13] Wang W, Yun Y, Deng B, et al. RSC Advances, 2015, 5: 95771.
[14] Deng B C, Yun Y H, Cao D S, et al. Analytica Chimica Acta, 2016, 908: 63.
[15] Zhang F, Tang X, Tong A, et al. Sensors, 2020, 20(7): 2015. |
[1] |
LI Shu-jie1, LIU Jie1, DENG Zi-ang1, OU Quan-hong1, SHI You-ming2, LIU Gang1*. Study of Germinated Rice Seeds by FTIR Spectroscopy Combined With Curve Fitting[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1832-1840. |
[2] |
PENG Qing-qing1, CHEN Song-chao2, ZHOU Ming-hua3, LI Shuo1*. Developing of Local Model From Soil Spectral Library With Spectral
Dissimilarity[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1614-1619. |
[3] |
WANG Li-qi1, YAO Jing1, WANG Rui-ying1, CHEN Ying-shu1, LUO Shu-nian2, WANG Wei-ning2, ZHANG Yan-rong1*. Research on Detection of Soybean Meal Quality by NIR Based on
PLS-GRNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1433-1438. |
[4] |
JIANG Qing-hu1, LIU Feng1, YU Dong-yue2, 3, LUO Hui2, 3, LIANG Qiong3*, ZHANG Yan-jun3*. Rapid Measurement of the Pharmacological Active Constituents in Herba Epimedii Using Hyperspectral Analysis Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1445-1450. |
[5] |
JIANG Xiao-yu1, 2, LI Fu-sheng2*, WANG Qing-ya1, 2, LUO Jie3, HAO Jun1, 2, XU Mu-qiang1, 2. Determination of Lead and Arsenic in Soil Samples by X Fluorescence Spectrum Combined With CARS Variables Screening Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1535-1540. |
[6] |
ZHA Ling-ling1, 2, 3, WANG Wei2*, XIE Yu1, SHAN Chang-gong2, ZENG Xiang-yu2, SUN You-wen2, YIN Hao2, HU Qi-hou2. Observation of Variations of Ambient CO2 Using Portable FTIR
Spectrometer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1036-1043. |
[7] |
ZHENG Kai-yi1, ZHANG Wen1, DING Fu-yuan1, ZHOU Chen-guang1, SHI Ji-yong1, Yoshinori Marunaka2, ZOU Xiao-bo1*. Using Ensemble Refinement (ER) Method to OptimizeTransfer Set of Near-Infrared Spectra[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1323-1328. |
[8] |
FAN Nai-yun, LIU Gui-shan*, ZHANG Jing-jing, YUAN Rui-rui, SUN You-rui, LI Yue. Rapid Determination of TBARS Contents in Tan Mutton Using Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 713-718. |
[9] |
AIBIBAIHAN Maturzi1, XU Rong2, LI Xiao-jin1, 3*, FAN Cong-zhao3, QI Zhi-yong3, ZHU Jun3, WANG Guo-ping3, ZHAO Ya-qin3. Study on Infrared Spectrum Fingerprint of Apocynumvenetum L. in Xinjiang Based on Double Index Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 757-763. |
[10] |
LI Ying-ying1, ZHANG Zhi-qing1*, WU Xiao-hong2, Andy Hsitien Shen1*. Photoluminescence in Indonesian Fossil Resins[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 814-820. |
[11] |
JIANG Yan1, 2, MENG He1, ZHAO Yi-rong1, WANG Xian-xu1, WANG Sui1, XUE En-yu3, WANG Shao-dong1*. Rapid Analysis of Main Quality Parameters in Forage Soybean by Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 919-923. |
[12] |
XIE Lin-jiang, HONG Ming-jian*, YU Zhi-rong. A Wavelength Selection Method Combining Direct Orthogonal Signal Correction and Monte Carlo[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(02): 440-445. |
[13] |
LI Qing-bo1, WEI Yuan1, CUI Hou-xin2, FENG Hao2, LANG Jia-ye2. Quantitative Analysis of TOC in Water Quality Based on UV-Vis Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(02): 376-380. |
[14] |
LU Qi-peng1, WANG Dong-min2*, SONG Yuan1*, DING Hai-quan3, GAO Hong-zhi3. Effect of Wavelength Drift on PLSR Calibration Model of Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(02): 405-409. |
[15] |
JIANG Jie1, YU Quan-zhou1, 2, 3*, LIANG Tian-quan1, 2, TANG Qing-xin1, 2, 3, ZHANG Ying-hao1, 3, ZHANG Huai-zhen1, 2, 3. Analysis of Spectral Characteristics of Different Wetland Landscapes Based on EO-1 Hyperion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(02): 517-523. |
|
|
|
|