Ensemble Learning Models for Food Safety Risk Prediction

Ensemble learning was adopted to design risk prediction models with the aim of improving border inspection methods for food imported into Taiwan. Specifically, we constructed a set of prediction models to enhance the hit rate of non-conforming products, thus strengthening the border control of food...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Li-Ya Wu, Sung-Shun Weng
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	food safety risk prediction border control ensemble learning machine learning bagging Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/07f4a2acf777474da4f65f38a9d1b6b2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:07f4a2acf777474da4f65f38a9d1b6b2
record_format	dspace
spelling	oai:doaj.org-article:07f4a2acf777474da4f65f38a9d1b6b22021-11-11T19:50:28ZEnsemble Learning Models for Food Safety Risk Prediction10.3390/su1321122912071-1050https://doaj.org/article/07f4a2acf777474da4f65f38a9d1b6b22021-11-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/21/12291https://doaj.org/toc/2071-1050Ensemble learning was adopted to design risk prediction models with the aim of improving border inspection methods for food imported into Taiwan. Specifically, we constructed a set of prediction models to enhance the hit rate of non-conforming products, thus strengthening the border control of food products to safeguard public health. Using five algorithms, we developed models to provide recommendations for the risk assessment of each imported food batch. The models were evaluated by constructing a confusion matrix to calculate predictive performance indicators, including the positive prediction value (PPV), recall, harmonic mean of PPV and recall (F1 score), and area under the curve. Our results showed that ensemble learning achieved better and more stable prediction results than any single algorithm. When the results of comparable data periods were examined, the non-conformity hit rate was found to increase significantly after online implementation of the ensemble learning models, indicating that ensemble learning was effective at risk prediction. In addition to enhancing the inspection hit rate of non-conforming food, the results of this study can serve as a reference for the improvement of existing random inspection methods, thus strengthening capabilities in food risk management.Li-Ya WuSung-Shun WengMDPI AGarticlefood safetyrisk predictionborder controlensemble learningmachine learningbaggingEnvironmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 12291, p 12291 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	food safety risk prediction border control ensemble learning machine learning bagging Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
spellingShingle	food safety risk prediction border control ensemble learning machine learning bagging Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350 Li-Ya Wu Sung-Shun Weng Ensemble Learning Models for Food Safety Risk Prediction
description	Ensemble learning was adopted to design risk prediction models with the aim of improving border inspection methods for food imported into Taiwan. Specifically, we constructed a set of prediction models to enhance the hit rate of non-conforming products, thus strengthening the border control of food products to safeguard public health. Using five algorithms, we developed models to provide recommendations for the risk assessment of each imported food batch. The models were evaluated by constructing a confusion matrix to calculate predictive performance indicators, including the positive prediction value (PPV), recall, harmonic mean of PPV and recall (F1 score), and area under the curve. Our results showed that ensemble learning achieved better and more stable prediction results than any single algorithm. When the results of comparable data periods were examined, the non-conformity hit rate was found to increase significantly after online implementation of the ensemble learning models, indicating that ensemble learning was effective at risk prediction. In addition to enhancing the inspection hit rate of non-conforming food, the results of this study can serve as a reference for the improvement of existing random inspection methods, thus strengthening capabilities in food risk management.
format	article
author	Li-Ya Wu Sung-Shun Weng
author_facet	Li-Ya Wu Sung-Shun Weng
author_sort	Li-Ya Wu
title	Ensemble Learning Models for Food Safety Risk Prediction
title_short	Ensemble Learning Models for Food Safety Risk Prediction
title_full	Ensemble Learning Models for Food Safety Risk Prediction
title_fullStr	Ensemble Learning Models for Food Safety Risk Prediction
title_full_unstemmed	Ensemble Learning Models for Food Safety Risk Prediction
title_sort	ensemble learning models for food safety risk prediction
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/07f4a2acf777474da4f65f38a9d1b6b2
work_keys_str_mv	AT liyawu ensemblelearningmodelsforfoodsafetyriskprediction AT sungshunweng ensemblelearningmodelsforfoodsafetyriskprediction
_version_	1718431390221991936

Ensemble Learning Models for Food Safety Risk Prediction

Ejemplares similares