1. College of Science, Hohai University, Nanjing 210098, China
2. CCCC Airport Investigation and Design Institute Co., Ltd., Guangzhou 510000, China
3. CCCC-FHDI Engineering Co., Ltd., Guangzhou 510000, China
4. College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Abstract：Human serum fluorescence spectrum within the range of 220～900 nm excited by 240 nm excitation wavelength is studied and analyzed in the modeling for the detection of human serum glucose concentration. Wavelength variable selection strategy was improved on the basis of simulated annealing algorithm and partial least square algorithm. According to the frequency of wavelengths selected in modeling and uninformative variable elimination method, this paper executed a rough and handpicked process for wavelength variable selection which speeded up the convergence rate and reduced the quantity of calculation such as introducing the self-adaptive property for the number of principle components. Basis interpolation functions for partial least square algorithm such as linear, cubic spline function and Gaussian function as well as the original spectra and the 3rd, the 4th detail signal decomposed by Daubechies wavelet were studied and compared in the modeling process. The result shows that the enhancement avoids the time cost by parameter setting attempts, the parameter gradually becomes stable in the calculation process and the best determination of the principle components is found. The prediction and analysis ability for independent samples have been a significant improvement with the new strategy of wavelength variable selection. The minimum least square error for prediction is 0.25 mmol·L-1 in modeling results, which is up to most clinical standards for human glucose level detection. The model is apparently improved by adding the nonlinear condition, of which the best result is based on the spline function, and the second is on the gauss function. Original fluorescence spectra are decomposed and produce a better result for modeling. The 4th detail signal spectra are better than the 3rd detail signal on the whole. Given the experimental condition, the frequency of wavelength selection is meant for the distribution of glucose concentration information, which provides the statistical interpretation for the physicochemical characteristics of glucose in human serum to some extent.
桂铭成，朱卫华，朱 峰，耿 颖，华伟豪，唐春梅，赵志敏. 基于人体血清荧光光谱和改进变量选择方法对血糖浓度测定的研究[J]. 光谱学与光谱分析, 2017, 37(09): 2817-2821.
GUI Ming-cheng, ZHU Wei-hua, ZHU Feng, GENG Ying，HUA Wei-hao, TANG Chun-mei, ZHAO Zhi-min. Research on the Determination of Glucose Based on Human Serum Fluorescence Spectrum and Improved Variable Selection Strategy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(09): 2817-2821.
[1] Khatib K M E, Hameed R M A. Biosensors & Bioelectronics, 2011, 26(8): 3542.
[2] Goodarzi M, Sharma S, Ramon H. Trac Trends in Analytical Chemistry, 2015, 67: 147.
[3] Vargas E, Ruiz M A, Campuzano S. Analytica Chimica Acta, 2016, 914: 53.
[4] Dong W, Ding H. Neurocomputing, 2016，214： 902.
[5] Fan J, Lv J. Statistica Sinica, 2010, 20(1): 101.
[6] Rommel G Regis, Christine A Shoemaker. Engineering Optimization, 2012, 45(5): 1.
[7] Regis R G. Engineering Optimization, 2014, 46(2): 218.
[8] Kaneko H, Funatsu K. Aiche Journal, 2012, 58(58): 1829.
[9] Yong H, Peng S, Peng J. Talanta, 2012, 94(6): 301.
[10] Zhao K, Valle D, Popescu S. Remote Sensing of Environment, 2013, 132(10): 102.
[11] Yun Y H, Cao D S, Tan M L. Chemometrics & Intelligent Laboratory Systems, 2014, 130(2): 76.
[12] Goodarzi M, Saeys W. Talanta, 2016, 146: 155.
[13] Goodarzi M, Sharma S, Ramon H. Trac Trends in Analytical Chemistry, 2015, 67: 147.
[14] Meinshausen N, Bühlmann P. Journal of the Royal Statistical Society, 2010, 72(4): 417.
