Abstract:The method of useful information extraction is one of the most important one in the detection application for complex samples using near infrared (NIR) spectroscopy. Due to various noise, baseline drift, peak overlapping and complex background, informative spectra were hidden and cannot be extracted by conventional methods. Thus, a new hybrid algorithm (EWPIE) was proposed for informative spectra extraction based on wavelet packet transform (WPT) and entropy theory in this study. In EWPIE algorithm, WPT algorithm and its reconstruction algorithm were adopted to split the raw spectra into serval subspectra in different frequency bands. To take advantage of the multiscale property of NIR spectroscopy, each subspectra was further processed through entropy-based phase and orthogonal signal correction (OSC)-based phase. In entropy-based phase, the information entropy theory was used as a filter to remove the interference, which are uncorrelated to analyte contents and would increase the uncertainty of whole spectra. According to the variation of entropy value, some subspectra representing basedline in low frequency band and some subspectra representing noise in high frequency band were filtered out. In OSC-based phase, the OSC algorithm was applied to each of the remaining subspectra and the useful spectra were obtained with accumulation of all the OSC-filtered subspectra. To validate this algorithm, a real NIR spectral dataset of milk was prepared to extract the correlated spectra about the content of fat and protein. Using the EWPIE-filtered spectra, a series of PLS prediction model were constructed. Experimental results show that the prediction ability and robustness of PLS_based prediction models developed with EWPIE algorithm are superior to those developed by conventional algorithms. The root mean square errors of the prediction models for fat and protein can reach up to 0.132% and 0.121%, which indicates that the EWPIE algorithm is a promise tool to extract the useful information from NIR spectra and has certain theoretical significance and practical application value for detection in complex systems.
Key words:Infrared spectra; Useful information; Information entropy; Wavelet packet transform
彭 丹,岳金霞,毕艳兰. 小波包熵的复杂体系近红外光谱信息提取[J]. 光谱学与光谱分析, 2017, 37(11): 3409-3413.
PENG Dan, YUE Jin-xia, BI Yan-lan. Information Extraction of Near Infrared Spectra for Complex Samples Based on Wavelet Packet Transform and Entropy Theory. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(11): 3409-3413.
[1] Maruo K, Tsurugi M, Tamura M, et al. Appl. Spectrosc., 2003, 57(10): 1236.
[2] Fernández-Cuesta álvaro, Fernández-Martínez J M, Velasco L. J. Am. Oil Chem. Soc., 2012, 89(3): 431.
[3] GUO Zhi-ming, HUANG Wen-qian, PENG Yan-kun, et al(郭志明, 黄文倩, 彭彦昆, 等). Chinese Journal of Analytical Chemistry(分析化学),2014, 42(4): 513.
[4] XIA Hui, HUANG Sheng-xiang, LI Hong-jian(夏 辉,黄生祥,李宏建). Chinese Journal of Lasers(中国激光),2008,35(1):102.
[5] Ben X, Yi H L, Tan H P. Appl. Opt., 2014, 53(7): 1427.
[6] Duarte M S, Pontes M J C, Ramos C S. J. Appl. Spectrosc., 2016, 82(6): 1042.
[7] LI Hua, WANG Ju-xiang, XING Zhi-na, et al(李 华,王菊香,邢志娜,等). Computers and Applied Chemistry(计算机与应用化学),2011,28(1):99.
[8] Cai C B, Xu L, Han Q J, et al. Talanta, 2010, 81(3): 799.
[9] Shannon C E. Bell. Syst. Tech., 1948, 27: 379.
[10] Eckschlager K, Stepanek V. Anal. Chem., 1982, 54: 1115.
[11] Wold S, Antti H, Lindgren F, et al. Chemom. Intell. Lab. Syst., 1998, 44: 175.
[12] PENG Dan, XU Ke-xin(彭 丹, 徐可欣). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2010, 30(2): 318.