可见/近红外光谱结合遗传算法无损检测牛肉pH值

Nondestructive determination of pH value in beef using visible/near-infrared spectroscopy and genetic algorithm

为了实现牛肉在整个货架期内(4℃环境)pH值的无损快速检测,该文采用可见/近红外光谱技术并结合遗传算法(GA,genetic algorithm),搭建了可见/近红外光谱检测系统,采集储藏在4℃下1～18d的120个牛肉样品400～1700nm范围的光谱,用不同预处理方法处理,并分别建立全波段光谱和经过遗传算法提取有效光谱的预测牛肉pH值的多元线性回归(MLR,multiple linear regression)模型、偏最小二乘回归(PLSR,partial least-squares regression)模型和最小二乘支持向量机(LS-SVM,least square-support vector machine)模型。结果表明,多元散射校正(MSC,multiplicatives catter correction)结合Savitzky-Golay(SG)平滑为最佳预处理方法,遗传算法提取光谱后所建模型的预测精度均高于全波段光谱所建模型,其中LS-SVM为最佳预测模型,其预测相关系数和标准差分别为0.935和0.111,相比全波段LS-SVM模型预测,精度得到了提高。研究表明可见/近红外光谱技术结合遗传算法所建LS-SVM预测模型能够实现4℃下牛肉整个货架期内pH值的无损快速检测。该研究为进一步开发实用的牛肉pH值无损快速检测设备提供依据。

In order to realize nondestructive and rapid determination of beef pH stored at 4℃ during its whole shelf-life,a laboratory visible/near-infrared spectroscopy system using visible/near-infrared spectroscopy and genetic algorithm was built to collect 120 beef samples’ reflectance spectra in the 400-1700nm.These samples were stored at 4℃ for 1-18days.The reflectance spectra of samples were performed with different pretreatments,such as multiplicative scatter correction（MSC）,Savitzky-Golay（SG） smoothing method.The prediction model of multiple linear regression（MLR）,partial least squares regression（PLSR） and least square-support vector machine（LS-SVM） were constructed for prediction of pH value in beef with full-spectrum and effective wavelengths selected by genetic algorithm（GA）,respectively.The results showed that the MSC combined with SG smoothing was the best pretreatment,and the performance of models established with effective wavelengths selected by GA were better than the full-spectrum models,and the best performance was achieved by LS-SVM model,its correlation coefficient and standard deviation were 0.935 and 0.111,respectively.The prediction accuracy was improved.This study demonstrated that the LS-SVM model built by using visible/nearinfrared spectroscopy with GA could nondestructively and rapidly determine pH value in beef during its whole shelf-life.This research provides a basis of further developing device for nondestructive and rapid determine pH value in beef.