融合不同成熟度的苹果可溶性固形物预测模型研究
|
摘要
目的为实现对不同成熟度的苹果可溶性固形物的预测,建立普适性强的混合分析模型。方法选取甘肃静宁241个不同成熟度的苹果作为研究对象,利用近红外光谱采集系统获取苹果漫反射光谱信息,并对苹果可溶性固形物含量进行测定。利用S-G卷积平滑、多元散射校正(multiplicative scatter correction,MSC)、以及标准正态变量变换(standard normal variable transformation,SNV)等预处理方法结合竞争自适应加权算法(competitive adaptive reweighted sampling,CARS)、随机蛙跳(random frog,RF)算法提取苹果可溶性固形物的特征变量,然后利用偏最小二乘回归(partial least squares regression,PLS R)和支持向量机(support vector machine,SVM)算法建立分析模型。结果对比发现,采用RF选取的特征波长变量数更少且预测精度优于CARS,原始波长点由1251个减少到55个,MSC-RF-PLSR建立的模型预测结果最好,其预测相关系数r和预测均方根误差分别为0.906和0.744。结论采用近红外光谱方法构建的苹果可溶性固形物混合分析模型可以实现对苹果不同成熟度的预测,为建立适用于不同成熟度苹果的可溶性固形物便携设备提供理论依据。
Objective To establish a model for achieving the prediction of soluble solid of apples with different maturity levels by a universally applicable mixed analysis. Methods In this study, 241 apples with different maturity levels in Jingning, Gansu were selected as the research object. Near-infrared spectroscopy was used to acquire diffuse reflectance spectra of apples and apple soluble solid content was measured. Pretreatment methods such as SG-Smooth,multiple scatter correction(MSC), and standard normal variable transformation(SNY) were combined with competitive adaptive weighting algorithm(CARS) and random frog leaping(RF) algorithm to extract characteristic variables of apple soluble solid, then the partial least squares regression(PLSR) and support vector machine(SVM) algorithms were used to establish the analytical model. Results It could be found that the number of feature wavelength variables selected by RF was fewer and the prediction accuracy was better than that of CARS. The number of original wavelength points was reduced from 1251 to 55. The model established by MSC-RF-PLSR had the most predictive results, its prediction correlation r and prediction root mean square error were 0.906 and 0.744. Conclusion The results show that the apple soluble solid hybrid analysis model constructed by near-infrared spectroscopy can realize the prediction of apple with different maturity levels and provide the theoretical basis for the establishment of soluble solid portable equipment suitable for apples of different maturity levels.
Objective To establish a model for achieving the prediction of soluble solid of apples with different maturity levels by a universally applicable mixed analysis. Methods In this study, 241 apples with different maturity levels in Jingning, Gansu were selected as the research object. Near-infrared spectroscopy was used to acquire diffuse reflectance spectra of apples and apple soluble solid content was measured. Pretreatment methods such as SG-Smooth,multiple scatter correction(MSC), and standard normal variable transformation(SNY) were combined with competitive adaptive weighting algorithm(CARS) and random frog leaping(RF) algorithm to extract characteristic variables of apple soluble solid, then the partial least squares regression(PLSR) and support vector machine(SVM) algorithms were used to establish the analytical model. Results It could be found that the number of feature wavelength variables selected by RF was fewer and the prediction accuracy was better than that of CARS. The number of original wavelength points was reduced from 1251 to 55. The model established by MSC-RF-PLSR had the most predictive results, its prediction correlation r and prediction root mean square error were 0.906 and 0.744. Conclusion The results show that the apple soluble solid hybrid analysis model constructed by near-infrared spectroscopy can realize the prediction of apple with different maturity levels and provide the theoretical basis for the establishment of soluble solid portable equipment suitable for apples of different maturity levels.
引文
[1]国家统计局.2016年年度统计数据:农业[EB/OL].[2015-12-10].http://www.stats.gov.cn/tjsj/ndsj/2016/indexch.htm.National Bureau of Statistics.Annual statistics for 2016:Agriculture[EB/OL].[2015-12-10].http://www.stats.gov.cn/tjsj/ndsj/2016/indexch.htm.
[2]樊书祥,黄文倩,李江波,等.特征变量优选在苹果可溶性固形物近红外便携式检测中的应用[J].光谱学与光谱分析,2014,34(10):2707-2712.Fan SX,Huang WQ,Li JB,et al.Application of characteristic NIR variables selection in portable detection of soluble solids content of apple by near infrared spectroscopy[J].Spectrosc Spect Anal,2014,34(10):2707-2712.
[3]宫元娟,裴军强,李宏博,等.便携式苹果品质快速检测系统设计[J].沈阳农业大学学报,2017,(2):238-243.Gong YJ,Pei JQ,Li HB,et al.Design of portable apple's quick detection system[J].J Shenyang Agric Univ,2017,(2):238-243.
[4]Wang JH,Wang J,Chen Z,et al.Development of multi-cultivar models for predicting the soluble solid content and firmness of European pear(Pyrus communis L.)using portable VIS-NIR spectroscopy[J].Postharv Biol Tec,2017,(129):143-151.
[5]郭文川,刘大洋.迷糊桃膨大果的近红外漫反射光谱无损识别[J].农业机械学报,2014,(9):230-235.Guo WC,Liu DY.Near-infrared diffuse reflectance spectroscopy for non-destructive identification of puffed peach enlargement[J].Chin J Agric Mach,2014,(9):230-235.
[6]刘燕德,朱丹宁,孙旭东,等.苹果可溶性固形物便携式检测实验研究[J].光谱学与光谱分析,2017,37(10):3260-3265.Liu YD,Zhu DN,Sun XD,et al.Study on detecting soluble solids in fruits based on portable near infrared spectrometer[J].Spectrosc Spect Anal,2017,37(10):3260-3265.
[7]陈帅帅,张鹏,李江阔,等.寒富苹果可溶性固形物可见/近红外光谱无损检测模型的优化[J].保鲜与加工,2018,18(2):86-93.Chen SS,Zhang P,Li JK,et al.Optimization of Hanfu apple soluble solids model by visible/near infrared spectroscopy nondestructive detection[J].StorProc,2018(2):86-93.
[8]欧阳爱国,谢小强,周延睿,等.苹果可溶性固形物近红外光谱检测的偏最小二乘回归变量筛选研究[J].光谱学与光谱分析,2012,32(10):2680-2684.Ou-Yang AG,Xie XQ,Zhou YR,et al.Partial least squares regression variable screening studies on apple soluble solids NIR spectral detection[J].Spectrosc Spect Anal,2012,32(10):2680-2684.
[9]郭亚,程亮,秦斌.一种便携式苹果糖度无损检测仪的研制[J].安徽农业科学,2017,45(14):191-198.Guo Y,Chen L,Qin B.Development of a portable nondestructive testing instrument for apple sugar content[J].J Anhui Agric Sci,2017,45(14):191-198.
[10]李艳肖,邹小波,董英.用遗传区间偏最小二乘法建立苹果糖度近红外光谱模型[J].光谱学与光谱分析,2007,27(10):2001-2004.Li YX,Zhou XB,Dong Y.Establishment of near infrared spectroscopy model of apple sugar by genetic partial partial least squares[J].Spectrosc Spect Anal,2007,27(10):2001-2004.
[11]Te M,Li XZ,Tetsuya I,et al.Noncontact evaluation of soluble solids content in apples bynear-infrared hyperspectral imaging[J].J Food Eng,2018,(224):53-61.
[12]Wang AC,Xie LJ.Technology using near infrared spectroscopic and multivariate analysis to determine the soluble solids content of citrus fruit[J].J Food Eng,2014,(143):17-24.
[13]Jiang BL,Wen QH,Chun JZ,et al.A comparative study for the quantitative determination of soluble solids content,pH and firmness of pears by VIS/NIR spectroscopy[J].J Food Eng,2013,(116):324-332.
[14]尹宝全,史银雪,孙瑞志,等.近红外光谱分析中的一种基于XY变量联合的异常样本剔除算法[J].中国科学技术大学学报,2016,46(3):208-214.Yin BQ,Shi YX,Sun RZ,et al.An abnormal sample suppression algorithm based on xy variable combination in near infrared spectroscopy[J].J Univ Sci Technol China,2016,46(3):208-214.
[15]苏文浩,何建国,刘贵珊,等.近红外高光谱图像技术在马铃薯外部缺陷检测中的应用[J].食品与机械,2013,(5):127-133.Su WH,He JG,Liu GS,et al.Application of near-infrared hyperspectral imaging in detecting potato externl defects[J].Food Mach,2013,(5):127-133.
[16]陈立旦,赵艳茹.可见-近红外光谱联合随机蛙跳算法检测生物柴油含水量[J].农业工程学报,2014,30(8):168-173.Chen LD,Zhao YR.Measurement of water content in biodiesel using visible and near infrared spectroscopy combined with random-frog algorithm[J].Trans Chin Soc Agr Eng,2014,30(8):168-173.
[17]李娟,李忠海,付湘晋.稻谷新陈度近红外快速无损检测的研究[J].光谱学与光谱分析,2012,32(8):2126-2130.Li J,Li ZH,Fu XJ.Study on rapid non-destructive testing of rice by near-infrared[J].Spectrosc Spect Anal.2012,32(8):2126-2130.
[2]樊书祥,黄文倩,李江波,等.特征变量优选在苹果可溶性固形物近红外便携式检测中的应用[J].光谱学与光谱分析,2014,34(10):2707-2712.Fan SX,Huang WQ,Li JB,et al.Application of characteristic NIR variables selection in portable detection of soluble solids content of apple by near infrared spectroscopy[J].Spectrosc Spect Anal,2014,34(10):2707-2712.
[3]宫元娟,裴军强,李宏博,等.便携式苹果品质快速检测系统设计[J].沈阳农业大学学报,2017,(2):238-243.Gong YJ,Pei JQ,Li HB,et al.Design of portable apple's quick detection system[J].J Shenyang Agric Univ,2017,(2):238-243.
[4]Wang JH,Wang J,Chen Z,et al.Development of multi-cultivar models for predicting the soluble solid content and firmness of European pear(Pyrus communis L.)using portable VIS-NIR spectroscopy[J].Postharv Biol Tec,2017,(129):143-151.
[5]郭文川,刘大洋.迷糊桃膨大果的近红外漫反射光谱无损识别[J].农业机械学报,2014,(9):230-235.Guo WC,Liu DY.Near-infrared diffuse reflectance spectroscopy for non-destructive identification of puffed peach enlargement[J].Chin J Agric Mach,2014,(9):230-235.
[6]刘燕德,朱丹宁,孙旭东,等.苹果可溶性固形物便携式检测实验研究[J].光谱学与光谱分析,2017,37(10):3260-3265.Liu YD,Zhu DN,Sun XD,et al.Study on detecting soluble solids in fruits based on portable near infrared spectrometer[J].Spectrosc Spect Anal,2017,37(10):3260-3265.
[7]陈帅帅,张鹏,李江阔,等.寒富苹果可溶性固形物可见/近红外光谱无损检测模型的优化[J].保鲜与加工,2018,18(2):86-93.Chen SS,Zhang P,Li JK,et al.Optimization of Hanfu apple soluble solids model by visible/near infrared spectroscopy nondestructive detection[J].StorProc,2018(2):86-93.
[8]欧阳爱国,谢小强,周延睿,等.苹果可溶性固形物近红外光谱检测的偏最小二乘回归变量筛选研究[J].光谱学与光谱分析,2012,32(10):2680-2684.Ou-Yang AG,Xie XQ,Zhou YR,et al.Partial least squares regression variable screening studies on apple soluble solids NIR spectral detection[J].Spectrosc Spect Anal,2012,32(10):2680-2684.
[9]郭亚,程亮,秦斌.一种便携式苹果糖度无损检测仪的研制[J].安徽农业科学,2017,45(14):191-198.Guo Y,Chen L,Qin B.Development of a portable nondestructive testing instrument for apple sugar content[J].J Anhui Agric Sci,2017,45(14):191-198.
[10]李艳肖,邹小波,董英.用遗传区间偏最小二乘法建立苹果糖度近红外光谱模型[J].光谱学与光谱分析,2007,27(10):2001-2004.Li YX,Zhou XB,Dong Y.Establishment of near infrared spectroscopy model of apple sugar by genetic partial partial least squares[J].Spectrosc Spect Anal,2007,27(10):2001-2004.
[11]Te M,Li XZ,Tetsuya I,et al.Noncontact evaluation of soluble solids content in apples bynear-infrared hyperspectral imaging[J].J Food Eng,2018,(224):53-61.
[12]Wang AC,Xie LJ.Technology using near infrared spectroscopic and multivariate analysis to determine the soluble solids content of citrus fruit[J].J Food Eng,2014,(143):17-24.
[13]Jiang BL,Wen QH,Chun JZ,et al.A comparative study for the quantitative determination of soluble solids content,pH and firmness of pears by VIS/NIR spectroscopy[J].J Food Eng,2013,(116):324-332.
[14]尹宝全,史银雪,孙瑞志,等.近红外光谱分析中的一种基于XY变量联合的异常样本剔除算法[J].中国科学技术大学学报,2016,46(3):208-214.Yin BQ,Shi YX,Sun RZ,et al.An abnormal sample suppression algorithm based on xy variable combination in near infrared spectroscopy[J].J Univ Sci Technol China,2016,46(3):208-214.
[15]苏文浩,何建国,刘贵珊,等.近红外高光谱图像技术在马铃薯外部缺陷检测中的应用[J].食品与机械,2013,(5):127-133.Su WH,He JG,Liu GS,et al.Application of near-infrared hyperspectral imaging in detecting potato externl defects[J].Food Mach,2013,(5):127-133.
[16]陈立旦,赵艳茹.可见-近红外光谱联合随机蛙跳算法检测生物柴油含水量[J].农业工程学报,2014,30(8):168-173.Chen LD,Zhao YR.Measurement of water content in biodiesel using visible and near infrared spectroscopy combined with random-frog algorithm[J].Trans Chin Soc Agr Eng,2014,30(8):168-173.
[17]李娟,李忠海,付湘晋.稻谷新陈度近红外快速无损检测的研究[J].光谱学与光谱分析,2012,32(8):2126-2130.Li J,Li ZH,Fu XJ.Study on rapid non-destructive testing of rice by near-infrared[J].Spectrosc Spect Anal.2012,32(8):2126-2130.