利用主成分权重重置实现牛奶成分浓度快速检测中近红外光谱的净化去噪

王丽杰; 杨羽翼

doi:doi:10.3788/aos201737.1030003

光学学报, 2017, 37 (10): 1030003, 网络出版: 2017-10-09

利用主成分权重重置实现牛奶成分浓度快速检测中近红外光谱的净化去噪

Purification and Noise Elimination of Near Infrared Spectrum in Rapid Detection of Milk Components Concentration by Using Principal Component Weight Resetting

论文大纲

王丽杰 ^1,2,*杨羽翼 ^1,2

作者单位

¹ 哈尔滨理工大学测控技术与通信工程学院, 黑龙江哈尔滨 150080

² 哈尔滨理工大学测控技术与仪器黑龙江省高校重点实验室, 黑龙江哈尔滨 150080

AI 词云图 AI一句话精读 AI短摘要

注：本部分内容由 AI 自动生成，请您知悉。

摘要

为了利用近红外光谱技术对牛奶中脂肪、蛋白质和乳糖的浓度进行快速检测, 提出了基于直方图规定化和模糊层次分析法的近红外光谱主成分权重重置预处理方法。针对牛奶样品的光谱进行主成分分析, 确定光谱数据中的最佳主成分数, 得到了各主成分的得分和权重。采用直方图规定化的数学统计思想实现二维光谱矩阵的滤波及净化去噪, 利用模糊层次分析方法对有效主成分信息的权重进行重置映射, 滤掉无关的主成分干扰信息, 建立权重重置后的光谱。在此基础上, 对预处理后的光谱数据进行脂肪、蛋白质和乳糖的偏最小二乘回归1（PLS1）建模, 得到脂肪的相关系数为0.980, 预测均方根误差为0.158×10-2 g·mL-1; 蛋白质的相关系数为0.997, 实际预测偏差为0.050×10-2 g·mL-1; 乳糖的相关系数为0.985, 实际预测偏差为0.152×10-2 g·mL-1。由模型预测结果可知, 基于直方图规定化和模糊层次分析法的近红外光谱主成分权重重置预处理方法比常规预处理方法具有更好的滤波和去噪效果, 说明将直方图规定化和模糊层次分析法相结合对牛奶近红外光谱进行预处理具有可行性。

Abstract

In order to use the near infrared spectroscopy to rapidly detect the concentrations of fat, protein and lactose in the milk, a preprocessing method of weight resetting for near infrared spectroscopy based on histogram normalization and fuzzy analytic hierarchy process is proposed. The principal component analysis is conducted for the spectrum of milk samples, the best principal component number in the spectral data is determined, and the scores and weights of the principal components are obtained. Filtering and purification and noise elimination of two-dimensional spectral matrix are realized by using the mathematical statistic idea of histogram normalization. The fuzzy analytic hierarchy process is used to reset the weight of the active principal component information, and the irrelevant interference information of principal component is filtered out, thereby, the spectrum is reconstructed. On this basis, partial least squares 1 (PLS1) regression models of fats, proteins and lactose are built after spectral data preprocessing, getting the correlation coefficient of fat is 0.980 and predicted root mean square error is 0.158×10-2 g·mL-1; the correlation coefficient of protein is 0.997 and predicted root mean square error is 0.050×10-2 g·mL-1; the correlation coefficient of lactose is 0.985 and predicted root mean square error is 0.152×10-2 g·mL-1. Through the model prediction results, we can see that this pretreatment method has better filtering and noise elimination effect than the conventional pretreatment method. It is feasible to pretreat the near infrared spectrum of milk by combining histogram normalization and fuzzy analytic hierarchy process.

参考文献

[1] 陆婉珍, 袁洪福, 褚小立. 近红外光谱仪器［M］. 北京: 化学工业出版社, 2010.

[2] Botros L L, Jablonski J, Chang C, et al. Exploring authentic skim and nonfat dry milk power variance for the development of nontargeted adulterant detection methods using near-infrared spectroscopy and chemometrics［J］. Journal of Agricultural and Food Chemistry, 2013, 61(41): 9810-9818.

[3] 傅博, 胡永翔, 刘蓉, 等. 基于中等浓度样品参考测量的近红外光谱检测方法［J］. 光学学报, 2016, 36(2): 0230003.

Fu Bo, Hu Yongxiang, Liu Rong, et al. Near-infrared measurement with medium concentration sample as reference［J］. Acta Optica Sinica, 2016, 36(2): 0230003.

[4] 邢笑雪, 吉淑娇. 基于Matlab的灰度直方图规定化实现方法的研究［J］. 长春大学学报, 2010, 20(2): 37-38.

Xing Xiaoxue, Ji Shujiao. A research on the implementing method of gray level histogram specification based on Matlab［J］. Journal of Changchun University, 2010, 20(2): 37-38.

[5] Sen D, Pal S K. Automatic exact histogram specification for contrast enhancement and visual system based quantitative evaluation［J］. IEEE Transactions on Image Processing, 2011, 20(5): 1211-1220.

[6] 戴成栋, 柏芳敏, 陈朝祖, 等. 基于模糊层次分析法的环洞庭湖防护林体系建设布局［J］. 湖南林业科技, 2010, 37(6): 21-24.

Dai Chengdong, Bo Fangmin, Chen Chaozu, et al. The layout of protection forest around Dongting lake with fuzzy analytic hierarchy process［J］. Journal of Hunan Forestry Science and Technology, 2010, 37(6): 21-24.

[7] 严衍禄, 景茂, 张录达, 等. 付里叶变换近红外漫反射光谱分析测量误差的研究［J］. 北京农业大学学报, 1990, 16(S2): 37-48.

Yan Yanlu, Jing Mao, Zhang Luda, et al. Studies on error of FTNIRDRSA［J］. Journal of Agricultural University of Beijing, 1990, 16(S2): 37-48.

[8] 张龙, 潘家荣, 朱诚, 等. 基于近红外光谱的不同发酵类型茶叶判别［J］. 食品科学, 2012, 33(20): 149-152.

Zhang Long, Pan Jiarong, Zhu Cheng, et al. Discrimination of different types of fermented tea by near infrared spectroscopy［J］. Food Science, 2012, 33(20): 149-152.

[9] 王云, 徐可欣, 常敏. 近红外光谱技术检测牛奶中脂肪及蛋白质含量校正模型的建立［J］. 光学仪器, 2006, 28(3): 3-7.

Wang Yun, Xu Kexin, Chang Min. Study on multi-band NIR spectroscopy for the determination of fat and protein contents in milk［J］. Optical Instrument, 2006, 28(3): 3-7.

[10] 李庆波. 近红外光谱分析中若干关键技术的研究［D］. 天津: 天津大学, 2003.

Li Qingbo. The research of several key technologies in infrared spectroscopy［D］. Tianjin: Tianjin University, 2003.

[11] 王丽杰. 快速检测牛奶成分的近红外光谱测量方法及系统研究［D］. 哈尔滨: 哈尔滨理工大学, 2006.

Wang Lijie. Research on rapid measuring method and system for milk constituents detecting by NIR spectrum［D］. Harbin: Harbin University of Science and Technology, 2006.

[12] 仇逊超, 曹军. 近红外光谱波段优化在东北松子蛋白质定量检测中的应用［J］. 现代食品科技, 2016, 32(11): 303-309.

Qiu Xunchao, Cao Jun. Application of band optimization of near-infrared spectra for quantitative detection of protein in northeastern pine huts［J］. Modern Food Science and Technology, 2016, 32(11): 303-309.

王丽杰, 杨羽翼. 利用主成分权重重置实现牛奶成分浓度快速检测中近红外光谱的净化去噪[J]. 光学学报, 2017, 37(10): 1030003. Wang Lijie, Yang Yuyi. Purification and Noise Elimination of Near Infrared Spectrum in Rapid Detection of Milk Components Concentration by Using Principal Component Weight Resetting[J]. Acta Optica Sinica, 2017, 37(10): 1030003.

利用主成分权重重置实现牛奶成分浓度快速检测中近红外光谱的净化去噪

关于本站 Cookie 的使用提示

全站搜索

利用主成分权重重置实现牛奶成分浓度快速检测中近红外光谱的净化去噪

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索