In this work,one-step growth models using hyperspectral imaging(HSI)(400-1000 nm)were successfully developed in order to estimate the microbial loads,minimum growth temperature(T_(min))and maximum specific growth rate...In this work,one-step growth models using hyperspectral imaging(HSI)(400-1000 nm)were successfully developed in order to estimate the microbial loads,minimum growth temperature(T_(min))and maximum specific growth rate(μ_(max))of Brochothrix thermosphacta in chilled beef at isothermal temperatures(4-25℃).Three different methods were compared for model development,particularly using(Model Ⅰ)the predicted microbial loads from partial least squares regression of the whole spectral variables;(Model Ⅱ)the selected spectral variables related to microbial loads;and(Model Ⅲ)the first principal scores of HSI spectra by principal component analysis.Consequently,Model Ⅰ showed the best ability to predict the microbial loads of B.thermosphacta,with the coefficient of determination(R_(v)^(2))and root mean square error in internal validation(RMSEV)of 0.921 and 0.498(lg(CFU/g)).The T_(min)(-12.32℃)andμmax can be well estimated with R^(2) and root mean square error(RMSE)of 0.971 and 0.276(lg(CFU/g)),respectively.The upward trend ofμmax with temperature was similar to that of the plate count method.HSI technique thus can be used as a simple method for one-step growth simulation of B.thermosphacta in chilled beef during storage.展开更多
Structured-illumination reflectance imaging(SIRI)provides a new means for food quality detection.This original work investigated the capability of(SIRI)technique coupled with multivariate chemometrics to evaluate the ...Structured-illumination reflectance imaging(SIRI)provides a new means for food quality detection.This original work investigated the capability of(SIRI)technique coupled with multivariate chemometrics to evaluate the microbial contamination in pork inoculated with Pseudomonas fluorescens and Brochothrix thermosphacta during storage at different temperatures.The prediction performances based on different spectrum and the textural features of direct component and amplitude component images demodulated from the SIRI pattern,as well as their data fusion were comprehensively compared.Based on the full wavelength spectrum(420-700 nm)of amplitude component images,the orthogonal signal correction coupled with support vector machine regression provided the best predictions of the number of P.fluorescens and B.thermosphacta in pork,with the determination coefficients of prediction(R_(p)^(2))values of 0.870 and 0.906,respectively.Besides,the prediction models based on the amplitude component or direct component image textural features and the data fusion models using spectrum and textural features from direct component and amplitude component images cannot significantly improve their prediction accuracy.Consequently,SIRI can be further considered as a potential technique for the rapid evaluation of microbial contaminations in pork meat.展开更多
基于NIR高光谱成像技术快速评估鸡肉热杀索丝菌含量。通过采集新鲜鸡肉高光谱图像并提取样本反射光谱信息(900~1699 nm),再采用多元散射校正(Multiplicative Scatter Correction,MSC)、基线校正(Baseline Correction,BC)和标准正态变量...基于NIR高光谱成像技术快速评估鸡肉热杀索丝菌含量。通过采集新鲜鸡肉高光谱图像并提取样本反射光谱信息(900~1699 nm),再采用多元散射校正(Multiplicative Scatter Correction,MSC)、基线校正(Baseline Correction,BC)和标准正态变量校正(Standard Normal Variable Correction,SNV)三种方法预处理原始光谱,分别利用偏最小二乘(Partial Least Squares,PLS)、多元线性回归(Multiple Linear Regression,MLR)挖掘光谱信息与鸡肉热杀索丝菌参考值之间的定量关系。同时采用PLS-β系数法、Stepwise算法和连续投影算法(Successive Projections Algorithm,SPA)筛选最优波长简化全波段模型(F-PLS)提高预测效率。结果显示,经BC预处理的全波段光谱(485个波长)构建的F-PLS模型预测热杀索丝菌效果较好,相关系数RP为0.973,误差RMSEP为0.295 lg CFU/g。基于PLS-β法从BC预处理光谱中筛选出25个最优波长构建的PLS-β-PLS(RP=0.931,RMSEP=0.434 lg CFU/g)模型预测较好。本试验表明,利用近红外高光谱成像技术可潜在实现鸡肉热杀索丝菌含量的快速评估。展开更多
基金supported by Key Research&Development Program of Jiangsu Province in China(BE2020693)Major Project of Science and Technology of Anhui Province(201903a06020010)+1 种基金Joint Key Project of Science and Technology Innovation of Yangtze River Delta in Anhui Province(202004g01020009)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)。
文摘In this work,one-step growth models using hyperspectral imaging(HSI)(400-1000 nm)were successfully developed in order to estimate the microbial loads,minimum growth temperature(T_(min))and maximum specific growth rate(μ_(max))of Brochothrix thermosphacta in chilled beef at isothermal temperatures(4-25℃).Three different methods were compared for model development,particularly using(Model Ⅰ)the predicted microbial loads from partial least squares regression of the whole spectral variables;(Model Ⅱ)the selected spectral variables related to microbial loads;and(Model Ⅲ)the first principal scores of HSI spectra by principal component analysis.Consequently,Model Ⅰ showed the best ability to predict the microbial loads of B.thermosphacta,with the coefficient of determination(R_(v)^(2))and root mean square error in internal validation(RMSEV)of 0.921 and 0.498(lg(CFU/g)).The T_(min)(-12.32℃)andμmax can be well estimated with R^(2) and root mean square error(RMSE)of 0.971 and 0.276(lg(CFU/g)),respectively.The upward trend ofμmax with temperature was similar to that of the plate count method.HSI technique thus can be used as a simple method for one-step growth simulation of B.thermosphacta in chilled beef during storage.
基金supported by Key Research&Development Program of Jiangsu Province in China(BE2020693)Major Project of Science and Technology of Anhui Province(201903a06020010)+1 种基金Joint Key Project of Science and Technology Innovation of Yangtze River Delta in Anhui Province(202004g01020009)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)。
文摘Structured-illumination reflectance imaging(SIRI)provides a new means for food quality detection.This original work investigated the capability of(SIRI)technique coupled with multivariate chemometrics to evaluate the microbial contamination in pork inoculated with Pseudomonas fluorescens and Brochothrix thermosphacta during storage at different temperatures.The prediction performances based on different spectrum and the textural features of direct component and amplitude component images demodulated from the SIRI pattern,as well as their data fusion were comprehensively compared.Based on the full wavelength spectrum(420-700 nm)of amplitude component images,the orthogonal signal correction coupled with support vector machine regression provided the best predictions of the number of P.fluorescens and B.thermosphacta in pork,with the determination coefficients of prediction(R_(p)^(2))values of 0.870 and 0.906,respectively.Besides,the prediction models based on the amplitude component or direct component image textural features and the data fusion models using spectrum and textural features from direct component and amplitude component images cannot significantly improve their prediction accuracy.Consequently,SIRI can be further considered as a potential technique for the rapid evaluation of microbial contaminations in pork meat.
文摘基于NIR高光谱成像技术快速评估鸡肉热杀索丝菌含量。通过采集新鲜鸡肉高光谱图像并提取样本反射光谱信息(900~1699 nm),再采用多元散射校正(Multiplicative Scatter Correction,MSC)、基线校正(Baseline Correction,BC)和标准正态变量校正(Standard Normal Variable Correction,SNV)三种方法预处理原始光谱,分别利用偏最小二乘(Partial Least Squares,PLS)、多元线性回归(Multiple Linear Regression,MLR)挖掘光谱信息与鸡肉热杀索丝菌参考值之间的定量关系。同时采用PLS-β系数法、Stepwise算法和连续投影算法(Successive Projections Algorithm,SPA)筛选最优波长简化全波段模型(F-PLS)提高预测效率。结果显示,经BC预处理的全波段光谱(485个波长)构建的F-PLS模型预测热杀索丝菌效果较好,相关系数RP为0.973,误差RMSEP为0.295 lg CFU/g。基于PLS-β法从BC预处理光谱中筛选出25个最优波长构建的PLS-β-PLS(RP=0.931,RMSEP=0.434 lg CFU/g)模型预测较好。本试验表明,利用近红外高光谱成像技术可潜在实现鸡肉热杀索丝菌含量的快速评估。
