基于偏最小二乘回归的藻类荧光光谱特征波长选取

余晓娅; 张玉钧; 殷高方; 肖雪; 赵南京; 段静波; 石朝毅; 方丽

doi:doi:10.3788/aos201434.0930002

光学学报, 2014, 34 (9): 0930002, 网络出版: 2014-08-15

基于偏最小二乘回归的藻类荧光光谱特征波长选取

Feature Wavelength Selection of Phytoplankton Fluorescence Spectra Based on Partial Least Squares

论文大纲

余晓娅 ^*张玉钧殷高方肖雪赵南京段静波石朝毅方丽

作者单位

中国科学院安徽光学精密机械研究所环境光学与技术重点实验室, 安徽合肥 230031

摘要

针对藻类荧光光谱解析中常见的信息冗余和光谱相关性问题，基于偏最小二乘（PLS）的方法,提出了区间蒙特卡罗偏最小二乘(IMC-PLS)方法，有效地解决了特征波长的选取问题。根据特征色素荧光峰位置预选出特征区域，综合利用了此特征区域内单个波段的信息和不同的随机波段组合对于模型的贡献，基于荧光光谱的三线性特点，联合了发射波长和激发波长的信息。研究结果表明，与无信息变量消除算法(UVE)相比，IMC-PLS反演4种藻类浓度得到的平均相对标准偏差分别降低了0%、34.3%、55.9%、30.5%，选择出的特征波长数和运算时间分别减少了80.1%、81.3%，IMC-PLS方法有效地解决了实时监测问题，也为离散三维荧光光谱仪器的研制提供了理论支持。

Abstract

For spectral information redundancy and correlation in phytoplankton spectral analysis, interval Monte Carlo partial least squares (IMC-PLS) which effectively solves the problem of feature wavelength selection is presented based on partial least squares (PLS). Feature region is preselected according to the location of the pigment fluorescence peaks, the internal informations of a single band and the contributions of different random band combinations to the model are plenarily used. Based on three-linear feature of fluorescence spectra, emission wavelength band and excitation wavelength band are considered as a unit. The result shows that comparing with the uninformative variable eliminotion (UVE), feature wavelength points and computation time obtained by IMC-PLS decrease by 80.1% and 81.3% and average relative tolerances (ARTs) by inversion of four algae concentrations decrease by 0%, 34.3%, 55.9%, 30.5%. IMC-PLS algorithm effectively solves the problem of real-time monitoring, and provides theoretical support for the development of a discrete three-dimensional fluorescence spectrometer meanwhile.

参考文献

[1] Y P Li, C Y Tang, Z B Yu, et al.. Correlations between algae and water quality: factors driving eutrophication in Lake Taihu, China [J]. Int J Environ Sci Technol, 2014, 11(1): 169-182.

[2] 刘晶, 刘文清, 赵南京, 等. 浮游植物在不同光质和光强激发下的叶绿素荧光特性[J]. 光学学报, 2013, 33(9): 0930001.

Liu Jing, Liu Wenqing, Zhao Nanjing, et al.. Phytoplankton chlorophyll fluorescence characteristics excited by various light qualities and intensities [J]. Acta Optica Sinica, 2013, 33(9): 0930001.

[3] 王志刚, 刘文清, 张玉钧, 等. 三维荧光光谱法分类测量水体浮游植物浓度[J]. 中国环境科学, 2008, 28(2): 136-141.

Wang Zhigang, Liu Wenqing, Zhang Yujun, et al.. The classified measuring of three dimensional excitation-emission fluorescence matrix technique on phytoplankton concentration in water body [J]. China Environmental Science, 2008, 28(2): 136-141.

[4] 王志刚, 刘文清, 张玉钧, 等. 基于激发荧光光谱的浮游植物分类测量方法[J]. 中国环境科学, 2008, 28(4): 329-333.

Wang Zhigang, Liu Wenqing, Zhang Yujun, et al.. The phytoplankton classified measure based on excitation fluorescence spectra technique [J]. China Environmental Science, 2008, 28(4): 329-333.

[5] L Mhlanga, W Mhlanga, P Tendaupenyu. Response of phytoplankton assemblages isolated for short periods of time in a hyper-eutrophic reservoir (Lake Chivero, Zimbabwe) [J]. Water SA, 2014, 40(1): 157-164.

[6] 段亚丽, 苏荣国, 石晓勇, 等. 基于小波高频分量的浮游植物活体荧光识别技术研究[J]. 中国激光, 2012, 39(7): 0715003.

Duan Yali, Su Rongguo, Shi Xiaoyong, et al.. Differentiation of phytoplankton populations by in vivo fluorescence based on high-frequency component of wavelet [J]. Chinese J Lasers, 2012, 39(7): 0715003.

[7] R Leardi. Genetic algorithms in chemometrics and chemistry: a review [J]. Journal of Chemometrics, 2001, 15(7): 559-569.

[8] 赵杰文, 惠喆, 黄林, 等. 高光谱成像技术检测鸡肉中挥发性盐基氮含量[J]. 激光与光电子学进展, 2013, 50(7): 073003.

Zhao Jiewen, Hui Zhe, Huang Lin, et al.. Quantitative detection of TVB-N content in chicken meat with hyperspectral imaging technology [J]. Laser & Optoelectronics Progress, 2013, 50(7): 073003.

[9] M Shamsipur, V Zare-Shahabadi, B Hemmateenejad, et al.. Ant colony optimisation: a powerful tool for wavelength selection [J]. Journal of Chemometrics, 2006, 20(3-4): 146-157.

[10] M Zhang, S Zhang, J Iqbal. Key wavelengths selection from near infrared spectra using Monte Carlo sampling-recursive partial least squares [J]. Chemometrics and Intelligent Laboratory Systems, 2013, 128: 17-24.

[11] W Cai, Y Li, X Shao. A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra [J]. Chemometrics and Intelligent Laboratory Systems, 2008, 90(2): 188-194.

[12] 韩清娟. 多维光谱数据解析的化学计量学算法及应用研究[D]. 长沙: 湖南大学, 2008.

Han Qingjuan. New Chemometric Algorithms and Their Application Studies for Multiway Spectroscopy data[D]. Changsha: Hunan University, 2008.

[13] J Zhou, J J Wang, A Baudon, et al.. Improved fluorescence excitation-emission matrix regional integration to quantify spectra for fluorescent dissolved organic matter [J]. Journal of Environmental Quality, 2013, 42(3): 925-930.

[14] 杜树新, 杜阳锋, 袁之报. 三维荧光光谱的特征区域选择方法[J]. 发光学报, 2012, 33(3): 341-345.

Du Shuxin, Du Yangfeng, Yuan Zhibao. Characteristic region selection methods for three-dimensional fluorescence spectrometry [J]. Chinese Journal of Luminescence, 2012, 33(3): 341-345.

[15] V Esposito Vinzi, W W Chin, J Henseler, et al.. Handbook of Partial Least Squares: Concepts, Methods and Applications [M]. Heidelberg, Dordecht, London, New York: Springer, 2010.

[16] V Centner, D L Massart, O E de Noord, et al.. Elimination of uninformative variables for multivariate calibration [J]. Analytical Chemistry, 1996, 68(21): 3851-3858.

[17] W Cai, Y Li, X Shao. A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra [J]. Chemometrics and Intelligent Laboratory Systems, 2008, 90(2): 188-194.

[18] M Beutler. Spectral Fluorescence of Chlorophyll and Phycobilins as an In-Situ Tool of Phytoplankton Analysis-Models, Algorithms and Instruments [D]. Kile: Kile University, 2003.

余晓娅, 张玉钧, 殷高方, 肖雪, 赵南京, 段静波, 石朝毅, 方丽. 基于偏最小二乘回归的藻类荧光光谱特征波长选取[J]. 光学学报, 2014, 34(9): 0930002. Yu Xiaoya, Zhang Yujun, Yin Gaofang, Xiao Xue, Zhao Nanjing, Duan Jingbo, Shi Chaoyi, Fang Li. Feature Wavelength Selection of Phytoplankton Fluorescence Spectra Based on Partial Least Squares[J]. Acta Optica Sinica, 2014, 34(9): 0930002.

基于偏最小二乘回归的藻类荧光光谱特征波长选取

关于本站 Cookie 的使用提示

全站搜索

基于偏最小二乘回归的藻类荧光光谱特征波长选取

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索