|
|
|
|
|
|
A Wavelength Selection Method of UV-Vis Based on Variable Stability and Credibility |
SUN Tao, YANG Chun-hua, ZHU Hong-qiu*, LI Yong-gang, CHEN Jun-ming |
School of Automation, Central South University, Changsha 410083,China |
|
|
Abstract This paper proposes a wavelength selection method based on stability and credibility partial least squares (SCPLS), to solve the problem that the ultraviolet visible (UV-Vis) spectra of multi-metal ion mixture solution were seriously overlapped and difficult to separate. In SCPLS, an exponentially decreasing function (EDF) is applied to select the variables in an iterative manner. In each iteration, a series of models are built with the sub-datasets sampled using the Monte Carlo strategy. Then, the stability and credibility of each variable are calculated, and the variables with high stability and credibility are selected by the EDF. Subsequently, the selected variables are used to construct a new variable subset for the next iteration. After the selection iterations are terminated, the root mean square error of cross validation (RMSECV) of each subset is calculated. The variable subset with the minimum RMSECV value is considered to be the optimal variable subset. The performance of SCPLS is evaluated with UV-Vis Spectral data set of Zn(Ⅱ), Cu(Ⅱ) and Co(Ⅱ) mixture solution and UV-Vis Spectral data set of Zn(Ⅱ) and Co(Ⅱ) mixture solution, and compared with that of full spectrum partial least squares (PLS) modeling and the moving window PLS (MWPLS), Monte Carlo uninformative variable elimination (MC-UVE), competitive adaptive reweighted sampling (CARS) and stability competitive adaptive reweighted sampling (SCARS) methods. The results show that SCPLS can not only reduce the complexity of the wavelength selection, but also ensure the stability of the wavelength selection process. And it can select the subset with the minimum RMSECV value. Thus, the RMSECV of Zn(Ⅱ), Cu(Ⅱ) and Co(Ⅱ) models obtained by SCPLS are 60.5%,40.2% and 31.8% respectively lower than that of full spectrum PLS, and 29.8%,26.1% and 0.8% respectively lower than that of SCARS. The average relative error of Zn(Ⅱ), Cu(Ⅱ) and Co(Ⅱ) is 2.14%, 1.25% and 0.74% respectively, of which the maximum relative error of Zn(Ⅱ) is 4.67%, the maximum relative error of Cu(Ⅱ) is 3.99%, and the maximum relative error of Co(Ⅱ) is 3.12%. And the RMSECV of Zn(Ⅱ) and Co(Ⅱ) models obtained by SCPLS are 39.4% and 24.9% respectively lower than that of full spectrum PLS, and 35.3% and 13.3% respectively lower than that of SCARS. The average relative error of Zn(Ⅱ) and Co(Ⅱ) are 1.23% and 1.10% respectively, of which the maximum relative error of Zn(Ⅱ) is 4.45% and the maximum relative error of Co(Ⅱ) is 4.57%. The proposed method can efficiently improve modeling accuracy.
|
Received: 2018-09-19
Accepted: 2019-01-25
|
|
Corresponding Authors:
ZHU Hong-qiu
E-mail: hqcsu@csu.edu.cn
|
|
[1] TANG Bin, WEI Biao, MAO Ben-jiang, et al(汤 斌,魏 彪,毛本将,等). Laser & Optoelectronics Progress, 2014, 51(4): 043002.
[2] Zhu Hongqiu, Wang Guowei, Yang Chunhua, et al. Transactions of Nonferrous Metals Society of China, 2013, 23(7): 2181.
[3] Suhandy D,Yulia M,Ogawa Y,et al. Engineering in Agriculture,Environment and Food,2013,6(3):111.
[4] Chen H Z, Pan T, Chen J M, et al. Chemometrics and Intelligent Laboratory Systems, 2011, 107(1): 139.
[5] Brusco Michael J. Computational Statistics & Data Analysis,2014,77:38.
[6] Xu Deng,Fan Wei,Lv Huiying, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2014,123: 430.
[7] Liu S S, Zhang J, Lin S H, et al. Laser & Optoelectronics Progress, 2018, 55(2): 023001.
[8] Rahman A, Kondo N, Ogawa Y, et al. Biosystems Engineering, 2016, 141: 12.
[9] WANG Yu-tian,YANG Zhe,HOU Pei-guo, et al(王玉田,杨 哲,侯培国,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2016,36(7):2144.
[10] ZHU Hong-qiu, CHEN Jun-ming, YIN Dong-hang, et al(朱红求, 陈俊名, 尹冬航, 等). Journal of Chemical Industry and Engineering(化工学报), 2017, (3): 206.
[11] Zhang Bo,Sun Lanxiang,Yu Haibin,et al. Spectrochimica Acta Part B,2015,107(1): 32. |
[1] |
LI Wei1, TAN Feng2*, ZHANG Wei1, GAO Lu-si3, LI Jin-shan4. Application of Improved Random Frog Algorithm in Fast Identification of Soybean Varieties[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3763-3769. |
[2] |
LIN Hong-jian1, ZHAI Juan1*, LAI Wan-chang1, ZENG Chen-hao1, 2, ZHAO Zi-qi1, SHI Jie1, ZHOU Jin-ge1. Determination of Mn, Co, Ni in Ternary Cathode Materials With
Homologous Correction EDXRF Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3436-3444. |
[3] |
KONG De-ming1, LIU Ya-ru1, DU Ya-xin2, CUI Yao-yao2. Oil Film Thickness Detection Based on IRF-IVSO Wavelength Optimization Combined With LIF Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2811-2817. |
[4] |
WANG Yi-ru1, GAO Yang2, 3, WU Yong-gang4*, WANG Bo5*. Study of the Electronic Structure, Spectrum, and Excitation Properties of Sudan Red Ⅲ Molecule Based on the Density Functional Theory[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2426-2436. |
[5] |
YAO Kun-shan1, SUN Jun1*, CHEN Chen2, XU Min1, CHENG Jie-hong1, ZHOU Xin1. Non-Destructive Identification for Panax Notoginseng Powder of Different Parts Based on Hyperspectral Imaging Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2027-2031. |
[6] |
WANG Ke-qing1, 2*, WU Na1, 2, CHENG Xiao-xiang3, ZHANG Ran1, 2, LIU Wei1, 2*. Use of FTIR for the Quantitative Study of Corrosion Products of Iron
Cultural Relics[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1846-1853. |
[7] |
LIU Mei-jun, TIAN Ning*, YU Ji*. Spectral Study on Mouse Oocyte Quality[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1376-1380. |
[8] |
CI Cheng-gang*, ZANG Jie-chao, LI Ming-fei*. DFT Study on Spectra of Mn-Carbonyl Molecular Complexes[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1434-1441. |
[9] |
CHEN Qing1, TANG Bin1, 2*, LONG Zou-rong1, 2, MIAO Jun-feng1, HUANG Zi-heng1, DAI Ruo-chen1, SHI Sheng-hui1, ZHAO Ming-fu1, ZHONG Nian-bing1. Water Quality Classification Using Convolution Neural Network Based on UV-Vis Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 731-736. |
[10] |
WANG Hai-ping1, 2, ZHANG Peng-fei1, XU Zhuo-pin1, CHENG Wei-min1, 3, LI Xiao-hong1, 3, ZHAN Yue1, WU Yue-jin1, WANG Qi1*. Quantitative Determination of Na and Fe in Sorghum by LIBS Combined With VDPSO-CMW Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 823-829. |
[11] |
YANG Guo-wu1, HOU Yan-xia1, SUN Xiao-fei2, JIA Yun-hai1*, LI Xiao-jia1. Evaluation of Long-Term Stability for Non-Standard Method and
Application in Trace Element Analysis of Pure Nickel by Glow
Discharge Mass Spectrometry[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 867-876. |
[12] |
WANG Ren-jie1, 2, FENG Peng1*, YANG Xing3, AN Le3, HUANG Pan1, LUO Yan1, HE Peng1, TANG Bin1, 2*. A Denoising Algorithm for Ultraviolet-Visible Spectrum Based on
CEEMDAN and Dual-Tree Complex Wavelet Transform[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 976-983. |
[13] |
XU Meng-lei1, 2, GAO Yu3, ZHU Lin1, HAN Xiao-xia1, ZHAO Bing1*. Improved Sensitivity of Localized Surface Plasmon Resonance Using Silver Nanoparticles for Indirect Glyphosate Detection Based on Ninhydrin Reaction[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 320-323. |
[14] |
ZHANG Xue-fei1, DUAN Ning1, 2*, JIANG Lin-hua1, 2*, CHENG Wen2, YU Zhao-sheng3, LI Wei-dong2, ZHU Guang-bin4, XU Yan-li2. Study on Stability and Sensitivity of Deep Ultraviolet Spectrophotometry Detection System[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(12): 3802-3810. |
[15] |
ZHU Pan-pan1, 2, NIU Xiao-tao3, WANG Xue3, SI Xin1, 2, XIE Qing-gang3, CHEN Bo3, JIANG Shi-long3, JU Ning1*, ZHANG Shu-wen2*, LÜ Jia-ping2. The Stability of Room Temperature Liquid Cheese Based on Turbiscan Multiple Light Scattering Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3415-3422. |
|
|
|
|