Study on Non-Destructive Detection Method for Egg Freshness Based on LLE-SVR and Visible/Near-Infrared Spectrum
DUAN Yu-fei1, WANG Qiao-hua1, 2*, MA Mei-hu2, 3, LU Xi1, WANG Cai-yun1
1. College of Engineering, Huazhong Agricultural University, Wuhan 430070, China 2. National Research and Development Center for Egg Processing, Huazhong Agricultural University, Wuhan 430070, China 3. College of Food Science and Technology, Huazhong Agricultural University, Wuhan 430070, China
摘要： 鸡蛋新鲜度是反映鸡蛋内部品质的一个重要指标。为了能够实现鸡蛋新鲜度的快速无损检测，利用微型光纤光谱仪采集鸡蛋550～950 nm的透射率光谱曲线，与鸡蛋的哈夫单位值进行了定量分析。通过不同的预处理方式分别结合偏最小二乘回归(partial least squares regression, PLSR)与支持向量回归(support vector regression, SVR)建立模型，比较了不同模型的预测结果，发现一阶微分结合SVR能够实现较好地预测，且利用SVR建模要优于PLSR。为了提高运算效率，减少无用信息对建模的不良影响，分别利用线性降维主成分分析法(principal component analysis, PCA)与非线性降维局部线性嵌入(locally linear embedding, LLE)对一阶微分后的光谱数据降维，比较两种降维方法的预测效果，得出了LLE降维要优于PCA降维，其训练集和预测集的相关系数与均方根误差分别为92.2%，7.21和91.1%，8.80，训练集交叉验证的均方根误差相比减少了0.79。实验结果表明，利用局部线性嵌入结合支持向量回归进行非线性建模，能够提高鸡蛋新鲜度的预测能力，表明该方法对鸡蛋新鲜度的可见/近红外光谱检测可行。
关键词：可见/近红外光谱;鸡蛋;支持向量回归;局部线性嵌入;新鲜度
Abstract：The freshness of egg is an important index to reflect the internal quality. In order to achieve non-destructive detection of freshness, micro fiber spectrometer was used to sample 550～950 nm transmittance spectra of eggs which performed quantitative analysis with haugh unit of eggs. Different pretreatment was combined with partial least squares regression(PLS) and support vector regression(SVR) respectively to find that first derivative combined with SVR predicted better than others through comparison, and it was better to model by SVR than by PLS. In order to improve efficiency and decrease adverse effects of useless information for modeling, the linear dimensionality reduction with principal component analysis (PCA) and the nonlinear dimensionality reduction with locally linear embedding(LLE) were used for the data of first derivative respectively. It indicated that LLE was better than PCA after comparison, and the correlation coefficient of calibration and prediction were 92.2%, 91.1%, and the root mean square error were 7.21, 8.80. The root mean square error of cross validation decreased 0.79.The experimental result illustrated that the nonlinear model of LLE combined with SVR improved predictive performance of egg freshness. It is feasible for the detection of visible/near-infrared spectrum of egg freshness to apply this method.
Key words：Visible/near-infrared spectrum;Egg;Support vector regression;Locally linear embedding;Freshness
段宇飞1，王巧华1, 2*，马美湖2, 3，芦 茜1, 王彩云1 . 基于LLE-SVR的鸡蛋新鲜度可见/近红外光谱无损检测方法 [J]. 光谱学与光谱分析, 2016, 36(04): 981-985.
DUAN Yu-fei1, WANG Qiao-hua1, 2*, MA Mei-hu2, 3, LU Xi1, WANG Cai-yun1 . Study on Non-Destructive Detection Method for Egg Freshness Based on LLE-SVR and Visible/Near-Infrared Spectrum . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(04): 981-985.
[1] LI Hui, QIN Yu-chang, Lü Xiao-wen, et al(李 辉，秦玉昌，吕小文，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报)，2006, 22(11): 264. [2] XIAO Wu, LI Xiao-yu, LI Pei-wu, et al(肖 武，李小昱，李培武，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报)，2009, 25(3): 33. [3] HUANG Ling-xia, WU Di, JIN Hang-feng, et al(黄凌霞，吴 迪，金航峰，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报)，2010, 26(2): 231. [4] WANG Hong, LI Qing-bo, LIU Ze-yi, et al(王 宏，李庆波，刘则毅，等). Chinese Journal of Analytical Chemistry(分析化学)，2002, 30(7): 779. [5] LI Gang, ZHAO Zhe, LIU Rui, et al(李 刚，赵 喆，刘 蕊，等). Chinese Journal of Analytical Chemistry(分析化学)，2011, 39(4): 588. [6] SHI Bo-lin, ZHAO Lei, LIU Wen, et al(史波林，赵 镭，刘 文，等). Transactions of the Chinese Society of Agricultural Machinery(农业机械学报)，2010, 41(2): 132. [7] XU Yun, WANG Yi-ming, WU Jing-zhu, et al(徐 云，王一鸣，吴静珠，等). Journal of Infrared and Millimeter Waves(红外与毫米波学报)，2010, 29(1): 53. [8] CAI Jian-rong, WAN Xin-min, CHEN Quan-sheng, et al(蔡健荣，万新民，陈全胜，等). Acta Optica Sinica(光学学报)，2009, 29(10): 2808. [9] LIU Yan-de, ZHOU Ting-rui, PENG Yan-ying, et al(刘燕德，周廷睿，彭彦颖，等). Optics and Precision Engineering(光学精密工程)，2013, 21(1): 40. [10] Bart J Kemps, Flip R Bamelis, Bart De Ketelaere, et al. Journal of the Science of Food and Agriculture, 2006, 86(9): 1399. [11] Nicolas Abdel-Nour, Michael Ngadi, Shiv Prasher, et al. Food Bioprocess Technol, 2011，(4): 731. [12] DU Shu-xin, WU Tie-jun(杜树新，吴铁军). Journal of System Simulation(系统仿真学报)，2003, 15(11): 1580. [13] Roweis S T, Saul L K. Science, 2000, 290(5500): 2323. [14] MA Rui, WANG Jia-xin, SONG Yi-xu(马 瑞，王家廞，宋亦旭). Journal of Tsinghua University·Science and Technology(清华大学学报·自然科学版)，2008, 48(4): 582.
