Water Quality Analysis by Three-Dimensional Fluorescence Spectra Based on Selective Model Combination
WU Xiao-li1, LI Yan-jun2, WU Tie-jun3*
1. Zhejiang University of Science and Technology, Hangzhou 310023, China 2. City College, Zhejiang University, Hangzhou 310015, China 3. State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China
Abstract：A selective model combination method is proposed in this paper to improve the precision of water quality analysis with three dimensional fluorescence spectra. A correlation coefficient criterion was designed to select effective excitation wavelengths for sub-models building, based on which the ridge regression method was adopted to combine the selected sub-models to get the stacked model. Thirty two samples from surface water and urban wastewater were used as research objects with total organic carbon (TOC) index from 3.41 to 125.35 mg·L-1, and chemical oxygen demand (COD) index from 22.80 to 330.60 mg·L-1, and 10 excitation wavelengths in the range of 220-400 nm were adopted to generate three dimensional fluorescence spectra. Following the proposed correlation coefficient criterion, the excitation wavelengths of 260, 280 and 400 nm, and the excitation wavelengths of 220, 280 and 400 nm were selected respectively for TOC analysis and COD analysis, based on which two stacked models were built by using partial least square regression method for sub-models building and ridge regression method for sub-models combination. The experimental results show that, compared with the sub-models with the best prediction precision, the root mean square errors of prediction (RMSEP) of the stacked models decreased by 15.4% for TOC analysis, and 17.5% for COD analysis; and compared with the models without sub-models selection, the RMSEP of the stacked models decreased by 6.1% for TOC analysis and 10.9% for COD analysis.
武晓莉1，李艳君2，吴铁军3* . 基于选择性模型组合的三维荧光光谱水质分析方法[J]. 光谱学与光谱分析, 2010, 30(04): 996-1001.
WU Xiao-li1, LI Yan-jun2, WU Tie-jun3* . Water Quality Analysis by Three-Dimensional Fluorescence Spectra Based on Selective Model Combination . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(04): 996-1001.
[1] LI Hong-bin, LIU Wen-qing, ZHANG Yu-jun, et al(李宏斌, 刘文清, 张玉筠，等). Optical Technology(光学技术), 2006, 32(1): 27. [2] Henderson R K, Baker A, Murphy K R, et al. Water Research, 2009, 43: 863. [3] Baker A. Environmental Science and Technology, 2001, 35(5): 948. [4] SIMA Wei-chang, ZHANG Yu-jun, WANG Zhi-gang, et al(司马伟昌, 张玉筠，王志刚，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2008, 28(1): 165. [5] Baker A, Inverarity R. Hydrological Processes，2004, 18(15): 2927. [6] Lee S, Ahn K H. Water Science and Technology，2004, 50(8): 57. [7] CHEN Mao-fu, WU Jing, Lü Yan-li, et al(陈茂福，吴 静，律严励，等). Acta Optica Sinica(光学学报)，2008，28(3)：578. [8] Marhaba T F, Bengraine K, Pu Y, et al. Journal of Hazardous Materials, 2003, B97: 83. [9] FU Ping-qing, WU Feng-chang, LIU Cong-qiang, et al(傅平青，吴丰昌，刘丛强，等). Oceanologia Et Limnologia Sinica(海洋与湖沼)，2007，38(6)：512. [10] WU Xiao-li, LI Yan-jun, WU Tie-jun(武晓莉, 李艳君，吴铁军). Chinese Journal of Analytical Chemistry(分析化学), 2007, 35(12): 1716. [11] Wolpert D. Neural Networks, 1992, 5: 241. [12] Breiman L. Machine Learning, 1996, 24: 49. [13] XIA Lu-yue, YU Li(夏陆岳, 俞 立). Journal of Chemical Industry and Engineering(化工学报), 2008, 59(7): 1631. [14] Guyon J, Elisseeff A. Journal of Machine Learning Research, 2003, 3: 1157. [15] Zepp R G, Sheldon W M, Moran M A. Marine Chemistry，2004, 89: 15. [16] XU Jin-gou, WANG Zun-ben(许金钩, 王尊本). Fluorescence Analysis Method(Third Edition)(荧光分析法，第3版). Beijing: Science Press(北京：科学出版社), 2006. [17] LIANG Yi-zeng, YU Ru-qin(梁逸增, 俞汝勤). Chemometrics(化学计量学). Beijing: Higher Education Press(北京：高等教育出版社), 2003. [18] Blanco M, Coello J, Iturriaga H. Chemometrics and Intelligent Laboratory Systems, 2000, 50: 75.
