On-Line Detection and Classification of Egg Freshness Based on Consensus Uninformative Variable Elimination-Partial Least Squares-Discriminant Analysis (CUVE-PLS-DA)

doi:10.7506/spkx1002-6630-201622028

Abstract

Abstract: Although there are many methods available to detect egg freshness at present, they have shortcomings including laboriousness, low precision and low classification efficiency. An on-line monitoring device based on visible/near infrared spectroscopy (501–1 000 nm) was fitted to the 4 800 eggs per hour egg transport machine for the purpose of dynamically collecting transmittance spectral data for eggs. The collected data were used to establish a partial least squares discriminant (PLS-DA) model for the Haugh unit value of eggs. A total of 226 egg samples were randomly divided into two set: calibration set (n = 169) and validation set (n = 57). By compared different spectral pretreatments and two wavelength selection methods, it was found that standard normal variate (SNV) transformation and multi-pattern consensus method could effectively improve the accuracy, efficiency and predictive ability of the PLS-DA model. The final calibration and validation accuracy were 92.31% and 91.23%, respectively. This study showed that visible-near infared spectroscopy could be used as a real-time and non-destructive detection method to classify egg freshness.

Key words: egg, freshness, online, partial least squares, multi-pattern

CLC Number:

TS253.7

WANG Qiaohua, LI Xiaoming, DUAN Yufei. On-Line Detection and Classification of Egg Freshness Based on Consensus Uninformative Variable Elimination-Partial Least Squares-Discriminant Analysis (CUVE-PLS-DA)[J]. FOOD SCIENCE, 2016, 37(22): 187-191.

References

[1] 王巧华, 周平, 熊利荣, 等. 鸡蛋反射特性及其与新鲜度的关系[J]. 华中农业大学学报, 2008, 27(1): 140-143.
[2] 顾小红, 冯宇, 汤坚. 偏最小二乘法在红外光谱识别茶叶中的应用[J]. 分析科学学报, 2008, 24(2): 131-135.
[3] 黄涛, 李小昱, 彭毅, 等. 基于近红外光谱的淡水鱼新鲜度在线检测方法研究[J]. 光谱学与光谱分析, 2014, 34(10): 2732-2736.
[4] 宁井铭, 宛晓春, 张正竹, 等. 近红外光谱技术结合人工神经网络判别普洱茶发酵程度[J]. 农业工程学报, 2013, 29(11): 255-259.
[5] 张仲源, 刘静, 管骁, 等. 近红外光谱技术在食品检测中的应用研究进展[J]. 食品与发酵工业, 2011, 37(11): 159-165. DOI:10.13995/J.cnki.11-1802/ts.2011.11.012.
[6] 张彬, 陈剑虹, 焦明星. 氯盐溶液近红外光谱分析研究[J]. 光谱学与光谱分析, 2015, 35(7): 1840-1843.
[7] 介邓飞, 谢丽娟, 饶秀勤, 等. 近红外光谱变量筛选提高西瓜糖度预测模型精度[J]. 农业工程学报, 2013, 29(12): 264-270.
[8] 侯卓成, 杨宁, 李俊英, 等. 傅里叶变换近红外反射用于鸡蛋品质的研究[J]. 光谱学与光谱分析, 2009, 29(8): 2063-2068.
[9] 林颢, 赵杰文, 陈全胜, 等. 近红外光谱结合一类支持向量机算法检测鸡蛋的新鲜度[J]. 光谱学与光谱分析, 2010, 30(4): 929-92; 312.
[10] SOLTANI M, OMID M. Detection of poultry egg freshness by dielectric spectroscopy and machine learning techniques[J]. LWT-Food Science and Technology, 2015, 62: 1034-1042. DOI:10.1016/j.lwt.2015.02019.
[11] GIUNCHI A, BERARDINELLI A, RAGNI L, et al. Non-destructive freshness assessment of shell eggs using FT-NIR spectroscopy[J]. Journal of Food Engineering, 2008, 89: 142-148. DOI:10.1016/ j.talanta.2014.10.042.
[12] 岑易科. 基于机器视觉的鸡蛋品质检测方法研究[D]. 杭州: 浙江大学, 2006.
[13] 潘磊庆. 基于机器视觉和声学技术融合检测鸡蛋品质的研究[D]. 南京: 南京农业大学, 2007.
[14] 刘艳, 李庆武, 黄小微, 等. 鸡蛋透光图像特征提取与新鲜度检测模型研究[J]. 科学技术与工程, 2015, 15(25): 72-77.
[15] BALLABIO D, CONSONNI V. Classification tools in chemistry part 1: linear models PLS-DA[J]. The Royal Society of Chemistry, 2013, 5: 3790-3798. DOI:10.1039/C3ay40582f.
[16] 高荣强, 范世福, 严衍禄, 等. 近红外光谱的数据预处理研究[J]. 光谱学与光谱分析, 2004, 24(12): 1563-1565.
[17] 尼珍, 胡昌勤, 冯芳. 近红外光谱分析中光谱预处理方法的作用及其发展[J]. 药物分析杂志, 2008, 28(5): 824-829.
[18] 江泽慧, 费本华, 杨忠. 光谱预处理对近红外光谱预测木材纤维素结晶度的影响[J]. 光谱学与光谱分析, 2007, 27(3): 435-438.
[19] CENTNER V, MASSART D, NOORD O E D. Elimination of uninformative variables for multivariate calibration analytical chemistry[J]. 1996, 69(21): 3851-3858.
[20] 孙俊, 金夏明, 毛罕平, 等. 基于高光谱图像光谱与纹理信息的生菜氮素含量检测[J]. 农业工程学报, 2014, 30(5): 167-173.
[21] 余晓雅, 张玉钧, 殷高方, 等. 基于偏最小二乘回归的藻类荧光光谱特征波长选取[J]. 光学学报, 2014, 34(9): 1-6.
[22] 徐秋, 李娜, 赵慧洁, 等. 基于光谱特征的自适应子空间波段选择方法[J]. 北京航空航天大学学报, 2013, 39(5): 635-639.
[23] 黄维, 田丰玲, 刘振尧, 等. 基于不同PLS算法的方竹笋中蛋白质分析的近红外光谱特征波段选择[J]. 2013, 34(22): 133-137.
[24] GOUVINHAS I, MACHADO N, CARVALHO T, et al. Short wavelength Raman spectroscopy applied to the discrimination and characterization of three cultivars of extra virgin olive iils in different maturation stages[J]. Talanta, 2015, 132: 829-835. DOI:10.1016/j.talanta.2014.10.042.
[25] 韩清娟, 张梦军, 曹文轩, 等. 基于多模式共识的近红外光谱波长的选择方法[J]. 分析科学学报, 2013, 29(6): 758-762.