高光谱成像技术快速预测鸡蛋液菌落总数
|
摘要
针对鸡蛋液中菌落总数分析方法操作繁琐、时效性低等问题,采用高光谱成像技术(400～1 000 nm)建立鸡蛋液中菌落总数的快速预测方法。于蛋清中接种铜绿假单胞菌后采集不同污染程度蛋液样本的原始高光谱信息,结合连续投影算法进行特征波段的提取,分别建立基于特征波段和全波段光谱信息下的偏最小二乘和支持向量机(support vector machine,SVM)预测回归模型。结果表明:标准化预处理效果相对最佳,蛋清、蛋黄以及全蛋液样本对应的相对最佳定量分析模型为基于特征波段下的SVM模型。其中蛋清预测集相关系数RP为0.81,预测集均方根误差(root mean square error of prediction,RMSEP)为0.63(lg(CFU/g));蛋黄预测集的R_P为0.82,RMSEP为0.47(lg(CFU/g));全蛋液样本中RP为0.75,RMSEP为0.75(lg(CFU/g))。结果表明,高光谱成像技术结合化学计量学方法,可以实现对鸡蛋内部微生物污染程度的定量预测。
The traditional method for detecting the total viable count of bacteria in liquid egg is laborious and time consuming. To overcome these drawbacks, the present study was undertaken to develop a fast method for predicting the total viable count of bacteria in liquid egg by using hyperspectral image technology(400–1 000 nm). The hyperspectral images of arti?cially inoculated liquid egg samples with different contamination levels of Pseudomonas aeruginosa were acquired.Then successive projections algorithm(SPA) was used to extract feature wavelengths, and partial least squares(PLS) and support vector machine(SVM) models were developed based on the feature wavelengths and the full spectra, respectively.Finally, the performance of the multivariate prediction models were compared and analyzed. The result showed that the Autoscale method was the best pretreatment method and the SVM model was the best prediction model for the total viable count of bacteria in liquid egg. The correlation coef?cient of prediction(RP) and the root mean square error of prediction(RMSEP) was 0.81 and 0.63(lg(CFU/g)) for egg white, 0.82 and 0.47(lg(CFU/g)) for egg yolk, 0.75 and 0.75(lg(CFU/g))for liquid whole egg, respectively. Overall, hyperspectral imaging combined with chemometrics enables quantitative prediction of the degree of microbial contamination in liquid egg.
The traditional method for detecting the total viable count of bacteria in liquid egg is laborious and time consuming. To overcome these drawbacks, the present study was undertaken to develop a fast method for predicting the total viable count of bacteria in liquid egg by using hyperspectral image technology(400–1 000 nm). The hyperspectral images of arti?cially inoculated liquid egg samples with different contamination levels of Pseudomonas aeruginosa were acquired.Then successive projections algorithm(SPA) was used to extract feature wavelengths, and partial least squares(PLS) and support vector machine(SVM) models were developed based on the feature wavelengths and the full spectra, respectively.Finally, the performance of the multivariate prediction models were compared and analyzed. The result showed that the Autoscale method was the best pretreatment method and the SVM model was the best prediction model for the total viable count of bacteria in liquid egg. The correlation coef?cient of prediction(RP) and the root mean square error of prediction(RMSEP) was 0.81 and 0.63(lg(CFU/g)) for egg white, 0.82 and 0.47(lg(CFU/g)) for egg yolk, 0.75 and 0.75(lg(CFU/g))for liquid whole egg, respectively. Overall, hyperspectral imaging combined with chemometrics enables quantitative prediction of the degree of microbial contamination in liquid egg.
引文
[1]赵法利,刘静波,刘瑜,等.鸡蛋中功能成分的研究[J].食品科学,2006,27(12):798-802.DOI:10.3321/j.issn:1002-6630.2006.12.209.
[2]平凡.禽蛋的药用与食疗[J].农产品加工,2006(2):31.DOI:10.3969/j.issn.1671-9646-C.2006.02.016.
[3]毕夏坤,赵杰文,林颢,等.便携式近红外光谱仪判别鸡蛋的贮藏时间[J].食品科学,2013,34(22):281-285.DOI:10.7506/spkxl1002-6630-201322057.
[4]陈力力,杨伊磊,青文哲,等.鸡蛋壳表面细菌数量及种群多样性分析[J].现代食品科技,2015,31(10):74-79.DOI:10.13982/j.mfst.1673-9078.2015.10.013.
[5]宾冬梅,钟金凤.蛋壳及禽蛋中微生物的来源与腐败变质[J].上海畜牧兽医通讯,2006(3):45-47.DOI:10.3969/j.issn.1000-7725.2006.03.030.
[6]罗岩,卢晓明,熊星星,等.鸡蛋长期贮存蛋清变绿原因分析[J].食品工业,2013,34(8):1-5.
[7]陈健锋,汪玲玲,张韵思.储存温度对鸡蛋微生物及品质的影响[J].食品科学,2009,30(20):52-54.
[8]TECHER C,BARON F,JAN S.Microbial spoilage of eggs and egg products[M]//Encylopedia of food microbiology.2nd ed.Academic Press,2014:439-445.DOI:10.1016/B978-0-12-384730-0.00371-2.
[9]GU X Z,SUN Y,TU K,et al.Predicting the growth situation of Pseudomonas aeruginosa on agar plates and meat stuffs using gas sensors[J].Scientific Reports,2016,6:38721.DOI:10.1038/srep38721.
[10]戴奕杰,李宗军,王远亮.冷却肉中假单胞菌生长动力学模型的研究[J].肉类研究,2011,25(4):17-21.DOI:10.3969/j.issn.1001-8123.2011.04.004.
[11]魏超,代晓航,郭灵安,等.禽肉中铜绿假单胞菌的分离及其耐药性[J].肉类研究,2017,31(7):7-10.DOI:10.7506/rlyj1001-8123-201707002.
[12]刘志海,刘德俊,沈建忠.肉制品腐败菌铜绿假单胞菌产金属β-内酰胺酶的研究现状[C]//中国畜牧兽医学会兽医食品卫生学分会第十三次学术交流会论文集.北京:中国农业大学动物医学院,2016:288-291.
[13]卫生部.食品微生物学检验菌落总数测定:GB 4789.2-2010[S].北京:中国标准出版社,2010.
[14]李殿鑫,戴远威,苏新国.食品中菌落总数测定的稀释度选择和计数结果的探讨[J].农产品加工,2016(9):39-40.DOI:10.16693/j.cnki.1671-9646(x).2016.09.013.
[15]李志明.影响菌落总数测定结果的特殊因素[J].中国卫生检验杂志,2008,18(2):371.DOI:10.3969/j.issn.1004-8685.2008.02.080.
[16]刘木花,赵杰文,郑建鸿,等.农畜产品品质无损检测中高光谱图像技术的应用进展[J].农业机械学报,2005,36(9):139-143.DOI:10.3969/j.issn.1000-1298.2005.09.036.
[17]张嫱,潘磊庆,陈蒙,等.基于高光谱图像技术的油桃早期冷害无损检测[J].食品工业科技,2014,35(20):53-56.DOI:10.13386/j.issn1002-0306.2014.20.002.
[18]TAO F F,PENG Y K,GOMES C L,et al.A comparative study for improving prediction of total viable count in beef based on hyperspectral scattering characteristics[J].Journal of Food Engineering,2015,162:38-47.DOI:10.1016/j.jfoodeng.2015.04.008.
[19]FENG Y Z,ELMASRY G,SUN D W,et al.Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets[J].Food Chemistry,2013,138(2/3):1829-1836.DOI:10.1016/j.foodchem.2012.11.040.
[20]CHENG J H,SUN D W.Rapid and non-invasive detection of fish microbial spoilage by visible and near infrared hyperspectral imaging and multivariate analysis[J].LWT-Food Science and Technology,2015,62(2):1060-1068.DOI:10.1016/j.lwt.2015.01.021.
[21]HE H J,SUN D W,WU D.Rapid and real-time prediction of lactic acid bacteria(LAB)in farmed salmon flesh using near-infrared(NIR)hyperspectral imaging combined with chemometric analysis[J].Food Research International,2014,62:476-483.DOI:10.1016/j.foodres.2014.03.064.
[22]BARBIN D F,ELMASRY G,SUN D W,et al.Non-destructive assessment of microbial contamination in porcine meat using NIR hyperspectral imaging[J].Innovative Food Science and Emerging Technologies,2013,17:180-191.DOI:10.1016/j.foodchem.2012.11.040.
[23]FOCA G,FERRARI C,ULRICI A,et al.The potential of spectral and hyperspectral-imaging techniques for bacterial detection in food:a case study on lactic acid bacteria[J].Talanta,2016,153(1):111-119.DOI:10.1016/j.talanta.2016.02.059.
[24]丁佳兴,吴龙国,何建国,等.高光谱成像技术对灵武长枣果皮强度的无损检测[J].食品工业科技,2016,37(24):58-63.DOI:10.13386/j.issn1002-0306.2016.24.003.
[25]TAKIZAWA K,NAKANO K,OHASHI S,et al.Development of nondestructive technique for detecting internal defects in Japanese radishes[J].Journal of Food Engineering,2014,126:43-47.DOI:10.1016/j.jfoodeng.2013.10.041.
[26]郭志明,黄文倩,彭彦坤,等.高光谱图像感兴趣区域对苹果糖度模型的影响[J].现代食品科技,2014,30(8):59-75.DOI:10.13982/j.mfst.1673-9078.2014.08.003.
[27]仝其根,唐巍巍,宋美娜.鲜鸡蛋中溶菌酶的活性分布[J].食品科学,2011,32(9):18-21.
[28]于志鹏,赵文竹,刘静波.鸡蛋清中功能蛋白及活性肽的研究进展[J].食品工业科技,2015,36(7):387-391.DOI:10.13386/j.issn1002-0306.2015.07.073.
[29]顾欣哲,孙晔,王文雪,等.应用高光谱图像拟合铜绿假单胞菌的生长[J].南京农业大学学报,2016,39(3):502-510.DOI:10.7685/jnau.201509010.
[30]于智慧,王宁,蔡朝霞,等.鸡蛋蛋黄高密度脂蛋白结构、组成、来源及功能研究进展[J].中国家禽,2016,38(4):38-43.DOI:10.16372/j.issn.1004-6364.2016.04.009.
[31]农业部.无公害食品鲜禽蛋:NY 5039-2005[S].北京:中国标准出版社,2005.
[32]范金波,王瑞环,周素珍,等.不同杀菌方法对蛋清物化性质的影响[J].食品工业科技,2014,35(11):143-151.DOI:10.13386/j.issn1002-0306.2014.11.023.
[33]何柳.禽蛋不同结构部分的抗菌特性研究[D].武汉:华中农业大学,2012:26-42.DOI:10.7666/d.Y2161876.
[34]吴静珠,李慧,王克栋,等.光谱预处理在农产品近红外模型优化中的应用研究[J].农机化研究,2011(3):178-181.DOI:10.3969/j.issn.1003-188X.2011.03.045.
[35]ARAUJO M C U,SALDANHA T C B,GALVAO R K H,et al.The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J].Chemometrics and Intelligent Laboratory Systems,2001,57:65-73.
[2]平凡.禽蛋的药用与食疗[J].农产品加工,2006(2):31.DOI:10.3969/j.issn.1671-9646-C.2006.02.016.
[3]毕夏坤,赵杰文,林颢,等.便携式近红外光谱仪判别鸡蛋的贮藏时间[J].食品科学,2013,34(22):281-285.DOI:10.7506/spkxl1002-6630-201322057.
[4]陈力力,杨伊磊,青文哲,等.鸡蛋壳表面细菌数量及种群多样性分析[J].现代食品科技,2015,31(10):74-79.DOI:10.13982/j.mfst.1673-9078.2015.10.013.
[5]宾冬梅,钟金凤.蛋壳及禽蛋中微生物的来源与腐败变质[J].上海畜牧兽医通讯,2006(3):45-47.DOI:10.3969/j.issn.1000-7725.2006.03.030.
[6]罗岩,卢晓明,熊星星,等.鸡蛋长期贮存蛋清变绿原因分析[J].食品工业,2013,34(8):1-5.
[7]陈健锋,汪玲玲,张韵思.储存温度对鸡蛋微生物及品质的影响[J].食品科学,2009,30(20):52-54.
[8]TECHER C,BARON F,JAN S.Microbial spoilage of eggs and egg products[M]//Encylopedia of food microbiology.2nd ed.Academic Press,2014:439-445.DOI:10.1016/B978-0-12-384730-0.00371-2.
[9]GU X Z,SUN Y,TU K,et al.Predicting the growth situation of Pseudomonas aeruginosa on agar plates and meat stuffs using gas sensors[J].Scientific Reports,2016,6:38721.DOI:10.1038/srep38721.
[10]戴奕杰,李宗军,王远亮.冷却肉中假单胞菌生长动力学模型的研究[J].肉类研究,2011,25(4):17-21.DOI:10.3969/j.issn.1001-8123.2011.04.004.
[11]魏超,代晓航,郭灵安,等.禽肉中铜绿假单胞菌的分离及其耐药性[J].肉类研究,2017,31(7):7-10.DOI:10.7506/rlyj1001-8123-201707002.
[12]刘志海,刘德俊,沈建忠.肉制品腐败菌铜绿假单胞菌产金属β-内酰胺酶的研究现状[C]//中国畜牧兽医学会兽医食品卫生学分会第十三次学术交流会论文集.北京:中国农业大学动物医学院,2016:288-291.
[13]卫生部.食品微生物学检验菌落总数测定:GB 4789.2-2010[S].北京:中国标准出版社,2010.
[14]李殿鑫,戴远威,苏新国.食品中菌落总数测定的稀释度选择和计数结果的探讨[J].农产品加工,2016(9):39-40.DOI:10.16693/j.cnki.1671-9646(x).2016.09.013.
[15]李志明.影响菌落总数测定结果的特殊因素[J].中国卫生检验杂志,2008,18(2):371.DOI:10.3969/j.issn.1004-8685.2008.02.080.
[16]刘木花,赵杰文,郑建鸿,等.农畜产品品质无损检测中高光谱图像技术的应用进展[J].农业机械学报,2005,36(9):139-143.DOI:10.3969/j.issn.1000-1298.2005.09.036.
[17]张嫱,潘磊庆,陈蒙,等.基于高光谱图像技术的油桃早期冷害无损检测[J].食品工业科技,2014,35(20):53-56.DOI:10.13386/j.issn1002-0306.2014.20.002.
[18]TAO F F,PENG Y K,GOMES C L,et al.A comparative study for improving prediction of total viable count in beef based on hyperspectral scattering characteristics[J].Journal of Food Engineering,2015,162:38-47.DOI:10.1016/j.jfoodeng.2015.04.008.
[19]FENG Y Z,ELMASRY G,SUN D W,et al.Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets[J].Food Chemistry,2013,138(2/3):1829-1836.DOI:10.1016/j.foodchem.2012.11.040.
[20]CHENG J H,SUN D W.Rapid and non-invasive detection of fish microbial spoilage by visible and near infrared hyperspectral imaging and multivariate analysis[J].LWT-Food Science and Technology,2015,62(2):1060-1068.DOI:10.1016/j.lwt.2015.01.021.
[21]HE H J,SUN D W,WU D.Rapid and real-time prediction of lactic acid bacteria(LAB)in farmed salmon flesh using near-infrared(NIR)hyperspectral imaging combined with chemometric analysis[J].Food Research International,2014,62:476-483.DOI:10.1016/j.foodres.2014.03.064.
[22]BARBIN D F,ELMASRY G,SUN D W,et al.Non-destructive assessment of microbial contamination in porcine meat using NIR hyperspectral imaging[J].Innovative Food Science and Emerging Technologies,2013,17:180-191.DOI:10.1016/j.foodchem.2012.11.040.
[23]FOCA G,FERRARI C,ULRICI A,et al.The potential of spectral and hyperspectral-imaging techniques for bacterial detection in food:a case study on lactic acid bacteria[J].Talanta,2016,153(1):111-119.DOI:10.1016/j.talanta.2016.02.059.
[24]丁佳兴,吴龙国,何建国,等.高光谱成像技术对灵武长枣果皮强度的无损检测[J].食品工业科技,2016,37(24):58-63.DOI:10.13386/j.issn1002-0306.2016.24.003.
[25]TAKIZAWA K,NAKANO K,OHASHI S,et al.Development of nondestructive technique for detecting internal defects in Japanese radishes[J].Journal of Food Engineering,2014,126:43-47.DOI:10.1016/j.jfoodeng.2013.10.041.
[26]郭志明,黄文倩,彭彦坤,等.高光谱图像感兴趣区域对苹果糖度模型的影响[J].现代食品科技,2014,30(8):59-75.DOI:10.13982/j.mfst.1673-9078.2014.08.003.
[27]仝其根,唐巍巍,宋美娜.鲜鸡蛋中溶菌酶的活性分布[J].食品科学,2011,32(9):18-21.
[28]于志鹏,赵文竹,刘静波.鸡蛋清中功能蛋白及活性肽的研究进展[J].食品工业科技,2015,36(7):387-391.DOI:10.13386/j.issn1002-0306.2015.07.073.
[29]顾欣哲,孙晔,王文雪,等.应用高光谱图像拟合铜绿假单胞菌的生长[J].南京农业大学学报,2016,39(3):502-510.DOI:10.7685/jnau.201509010.
[30]于智慧,王宁,蔡朝霞,等.鸡蛋蛋黄高密度脂蛋白结构、组成、来源及功能研究进展[J].中国家禽,2016,38(4):38-43.DOI:10.16372/j.issn.1004-6364.2016.04.009.
[31]农业部.无公害食品鲜禽蛋:NY 5039-2005[S].北京:中国标准出版社,2005.
[32]范金波,王瑞环,周素珍,等.不同杀菌方法对蛋清物化性质的影响[J].食品工业科技,2014,35(11):143-151.DOI:10.13386/j.issn1002-0306.2014.11.023.
[33]何柳.禽蛋不同结构部分的抗菌特性研究[D].武汉:华中农业大学,2012:26-42.DOI:10.7666/d.Y2161876.
[34]吴静珠,李慧,王克栋,等.光谱预处理在农产品近红外模型优化中的应用研究[J].农机化研究,2011(3):178-181.DOI:10.3969/j.issn.1003-188X.2011.03.045.
[35]ARAUJO M C U,SALDANHA T C B,GALVAO R K H,et al.The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J].Chemometrics and Intelligent Laboratory Systems,2001,57:65-73.