Detection of cold chain breaks using partial least squares-class modelling based on biogenic amine profiles in tuna

Reguera, Celia; Sanllorente, S.; Herrero, Ana M.; Sarabia, L.A.; Ortiz, M.C.

doi:10.1016/j.talanta.2019.04.072

Cited by 5 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In combination with intelligent decision support, the balance between system performance and EC can be optimized. With big data technology, not only can user participation in FCCL be improved through data centralization and exchange, but cold chain break problems can also be compensated for through information mining (Loisel et al., 2021; Reguera et al., 2019), with data support being provided to establish a digital twin system of FCCL. Blockchain can be integrated into existing cold chain infrastructure to promote more secure, more transparent information transfer that is both responsive and cost‐effective.…”

Section: Future Trends For Sustainable Fcclmentioning

confidence: 99%

Sustainable food cold chain logistics: From microenvironmental monitoring to global impact

Chen

Qian

Yang

et al. 2022

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

Food cold chain logistics (FCCL) is a systematic engineering process involving the use of a low-temperature environment to maintain the quality and safety of perishable food and reduce food loss and waste (FLW). From a mechanism perspective, FCCL must balance resource costs for a required level of food quality and safety with the costs of greenhouse gas (GHG) emissions. In the context of global warming, the sustainability trade-off between FLW and environmental impact has recently become an important topic in research on efficient, green FCCL. This is mainly reflected in technological innovation, management optimization, and policy responses. With a focus on three levels (micro, meso, macro), this review analyzes current research areas and the gaps and challenges of FCCL in microenvironmental monitoring, life cycle assessment (LCA), and global impact. Future trends pertaining to FCCL in technology, management, and industry and sustainable development are also summarized. Future trends involving sustainable FCCL must be intelligent, systematic, and low carbon.Industry empowerment through next-generation information technologies (e.g., IoT, AI, big data, blockchain) will promote the multidimensional perception, real-time information transmission, and sustainable control of microenvironmental monitoring, as well as support LCA management transformation from fragmentation to system integration. From a macro level, due to the serious global loss of perishable food, the FCCL scale demand is growing greatly, causing a huge environmental burden. Global cooperation, low-carbon consensus, and appropriate policies will become the basis for promoting sustainable FCCL development.

show abstract

Section: Future Trends For Sustainable Fcclmentioning

confidence: 99%

Sustainable food cold chain logistics: From microenvironmental monitoring to global impact

Chen

Qian

Yang

et al. 2022

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

show abstract

“…Class-modelling techniques (Forina et al, 2008) focus on the ability of the built class-models for recognizing their own objects (sensitivity of the computed class-model) and rejecting all others (specificity). The additional information that the class-models provide about the categories being modelled, as against a pure discriminant rule, is relevant for authentication of products (Rodionova et al, 2016a), for example, to characterize foods or beverages with recognized quality, such as denomination of origin wines or oil (Barbaste et al, 2002;Marini et al, 2006;Forina et al, 2009;Ruisánchez et al, 2021) combined with spectroscopic and chromatographic techniques to characterize green tea (Casale et al, 2018) with near infrared spectroscopy to antibiotic authentication (Chen et al, 2020) to identify bands for functional spectral data (Hermane et al, 2021) for food-authenticity claims (Oliveri and Downey, 2012) for detection of cold chain breaks in tuna (Reguera et al, 2019), or adulterations (Xu et al, 2013a), or nitro explosive vapors (Pablos et al, 2015). Also, a procedure based on band limits are successfully used as probabilistic one-class classifier (Avohou et al, 2021), among several other applications that can be found in a recent tutorial (Oliveri et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Handling Variables, via Inversion of Partial Least Squares Models for Class-Modelling, to Bring Defective Items to Non-Defective Ones

et al. 2021

View full text Add to dashboard Cite

In the context of binary class-modelling techniques, the paper presents the computation in the input space of linear boundaries of a class-model constructed with given values of sensitivity and specificity. This is done by inversion of a decision threshold, set with these values of sensitivity and specificity, in the probabilistic class-models computed by means of PLS-CM (Partial Least Squares for Class-Modelling). The characterization of the boundary hyperplanes, in the latent space (space spanned by the selected latent variables of the fitted PLS model) or in the input space, makes it possible to calculate directions that can be followed to move objects toward the class-model of interest. Different points computed along these directions will show how to modify the input variables (provided they can be manipulated) so that, eventually, a computed ‘object’ would be inside the class-model, in terms of the prediction with the PLS model. When the class of interest is that of “adequate” objects, as for example in some process control or product formulation, the proposed procedure helps in answering the question about how to modify the input variables so that a defective object would be inside the class-model of the adequate (non-defective) ones. This is the situation illustrated with some examples, taken from the literature when modelling the class of adequate objects.

show abstract

“…Las técnicas de modelado de clases [71] se centran en la capacidad de los modelos de clase construidos para reconocer sus propios objetos (sensibilidad del modelo de clase calculado) y rechazar todos los demás (especificidad). Esta información que los modelos proporcionan sobre las categorías modeladas es relevante, por ejemplo, en aplicaciones recientes para caracterizar alimentos o bebidas con calidad reconocida, tales como vinos o aceites con denominación de origen [72,73,74]; combinado con técnicas espectroscópicas y cromatográficas para caracterizar el té verde [75]; para la verificación de autenticidad alimentaria [76] o la detección de adulteraciones [77]; roturas de la cadena de frío en el atún [78]; detección de vapores nitro-explosivos [79]; etc.…”

Section: Introductionunclassified

Espacio de diseño con métodos de inversión de modelos de regresión sobre variables latentes

Miguel¹

View full text Add to dashboard Cite

Detection of cold chain breaks using partial least squares-class modelling based on biogenic amine profiles in tuna

Cited by 5 publications

References 24 publications

Sustainable food cold chain logistics: From microenvironmental monitoring to global impact

Sustainable food cold chain logistics: From microenvironmental monitoring to global impact

Handling Variables, via Inversion of Partial Least Squares Models for Class-Modelling, to Bring Defective Items to Non-Defective Ones

Espacio de diseño con métodos de inversión de modelos de regresión sobre variables latentes

Contact Info

Product

Resources

About