Spice essential oils are crucial natural ingredients in the food industry,valued for their distinctive flavor,aroma,and antimicrobial activity.However,their high market value has led to widespread adulteration,necessi...Spice essential oils are crucial natural ingredients in the food industry,valued for their distinctive flavor,aroma,and antimicrobial activity.However,their high market value has led to widespread adulteration,necessitating robust detection methods.Although traditional sensory and chemical analyses are accurate,they are often constrained by high costs and time-consuming procedures.This study systematically evaluates near-infrared spectroscopy(NIR)and E-nose(EN)technologies,along with their integration with machine learning(ML),for identifying adulterated spice essential oils.Multiple ML algorithms including decision trees(DT),k-nearest neighbors(kNN),linear discriminant analysis(LDA),logistic regression(LR),naive Bayes(NB),random forests(RF),and support vector machines(SVM)were employed.Results indicate that feature selection and data fusion substantially enhance adulteration detection accuracy.When used independently,EN models achieved accu-racies of 0.51-0.99,and NIR models 0.45-1.00.After NIR-EN data fusion,model performance increased markedly,achieving accuracies of 0.86-1.00 across algorithms.The fused data preprocessed with standard normal variate(SNV)and synergy interval partial least squares(Si-PLS)achieved the best results,with SVM,LDA,and RF models reaching accuracy above 0.99.This integrated strategy offers a reliable,efficient solution for essential oil authentication,with significant potential to mitigate spice market fraud and support sustainable industry practices.展开更多
Gelatinous polysaccharide-based fresh products are influenced by environmental and temperature changes,and maintaining their quality and freshness has always been a challenge.Intelligent management and control of cold...Gelatinous polysaccharide-based fresh products are influenced by environmental and temperature changes,and maintaining their quality and freshness has always been a challenge.Intelligent management and control of cold chain logistics systems have been extensively used in transporting and storing these goods to overcome the problem.This review introduces common quality deterioration issues,including those encountered during the transportation and storage of these products,such as softening,water loss,and color changes.The application of intelligent detection technologies,including gas detection,intelligent label,and spectral detection is reviewed to achieve real-time monitoring and evaluation of product status.This article also introduces the Internet of Things,wireless sensor networks,and radio frequency identification for product data transmission.It utilizes artificial neural networks and digital twins to build quality models,achieving better management of gelatinous polysaccharide-based fresh products in the cold chain.Moreover,some preservation techniques are used to increase the longevity of these products in storage and reduce losses in the cold chain.These techniques include irradiation,chemical treatment,and coating preservation.This review will,hopefully,encourage additional work that may help reach the goal of having better intelligent quality control of gelatinous polysaccharide-based fresh products during cold chain logistics.展开更多
基金supports from the China Key R&D Program(Contract No.2023YFF1104205)the Fundamental Research Funds for the Central Universities(JUSRP202416005)+1 种基金National First-Class Discipline Program of Food Science and Technology(No.JUFSTR20180205)all of which enabled us to carry out this study.
文摘Spice essential oils are crucial natural ingredients in the food industry,valued for their distinctive flavor,aroma,and antimicrobial activity.However,their high market value has led to widespread adulteration,necessitating robust detection methods.Although traditional sensory and chemical analyses are accurate,they are often constrained by high costs and time-consuming procedures.This study systematically evaluates near-infrared spectroscopy(NIR)and E-nose(EN)technologies,along with their integration with machine learning(ML),for identifying adulterated spice essential oils.Multiple ML algorithms including decision trees(DT),k-nearest neighbors(kNN),linear discriminant analysis(LDA),logistic regression(LR),naive Bayes(NB),random forests(RF),and support vector machines(SVM)were employed.Results indicate that feature selection and data fusion substantially enhance adulteration detection accuracy.When used independently,EN models achieved accu-racies of 0.51-0.99,and NIR models 0.45-1.00.After NIR-EN data fusion,model performance increased markedly,achieving accuracies of 0.86-1.00 across algorithms.The fused data preprocessed with standard normal variate(SNV)and synergy interval partial least squares(Si-PLS)achieved the best results,with SVM,LDA,and RF models reaching accuracy above 0.99.This integrated strategy offers a reliable,efficient solution for essential oil authentication,with significant potential to mitigate spice market fraud and support sustainable industry practices.
基金Financial support from the National Key R&D Program of China(No.2022YFD2100601)the Fundamental Research Funds for the Central Universities(JUSRP202416005)+1 种基金the Jiangsu Province Key Laboratory Project of Advanced Food Manufacturing Equipment and Technology(No.FMZ202003)the National First-Class Discipline Program of Food Science and Technology(No.JUFSTR20180205).
文摘Gelatinous polysaccharide-based fresh products are influenced by environmental and temperature changes,and maintaining their quality and freshness has always been a challenge.Intelligent management and control of cold chain logistics systems have been extensively used in transporting and storing these goods to overcome the problem.This review introduces common quality deterioration issues,including those encountered during the transportation and storage of these products,such as softening,water loss,and color changes.The application of intelligent detection technologies,including gas detection,intelligent label,and spectral detection is reviewed to achieve real-time monitoring and evaluation of product status.This article also introduces the Internet of Things,wireless sensor networks,and radio frequency identification for product data transmission.It utilizes artificial neural networks and digital twins to build quality models,achieving better management of gelatinous polysaccharide-based fresh products in the cold chain.Moreover,some preservation techniques are used to increase the longevity of these products in storage and reduce losses in the cold chain.These techniques include irradiation,chemical treatment,and coating preservation.This review will,hopefully,encourage additional work that may help reach the goal of having better intelligent quality control of gelatinous polysaccharide-based fresh products during cold chain logistics.
