Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers

Since consuming gutter oil does great harm to people’s health, the Food Safety Administration has always been seeking for a more effective and timely supervision. As laboratory tests consume much time, and existing field tests have excessive limitations, a more comprehensive method is in great need....

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wei Jiang, Yuhanxiao Ma, Ruiqi Chen
Formato: article
Lenguaje:EN
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://doaj.org/article/aaa6a0e47c764b6a84f3619f7c817abc
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:aaa6a0e47c764b6a84f3619f7c817abc
record_format dspace
spelling oai:doaj.org-article:aaa6a0e47c764b6a84f3619f7c817abc2021-11-18T15:05:22ZGutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers10.7717/peerj-cs.7742376-5992https://doaj.org/article/aaa6a0e47c764b6a84f3619f7c817abc2021-11-01T00:00:00Zhttps://peerj.com/articles/cs-774.pdfhttps://peerj.com/articles/cs-774/https://doaj.org/toc/2376-5992Since consuming gutter oil does great harm to people’s health, the Food Safety Administration has always been seeking for a more effective and timely supervision. As laboratory tests consume much time, and existing field tests have excessive limitations, a more comprehensive method is in great need. This is the first time a study proposes machine learning algorithms for real-time gutter oil detection under multiple feature dimensions. Moreover, it is deployed on FPGA to be low-power and portable for actual use. Firstly, a variety of oil samples are generated by simulating the real detection environment. Next, based on previous studies, sensors are used to collect significant features that help distinguish gutter oil. Then, the acquired features are filtered and compared using a variety of classifiers. The best classification result is obtained by k-NN with an accuracy of 97.18%, and the algorithm is deployed to FPGA with no significant loss of accuracy. Power consumption is further reduced with the approximate multiplier we designed. Finally, the experimental results show that compared with all other platforms, the whole FPGA-based classification process consumes 4.77 µs and the power consumption is 65.62 mW. The dataset, source code and the 3D modeling file are all open-sourced.Wei JiangYuhanxiao MaRuiqi ChenPeerJ Inc.articleGutter oil detectionMachine learningFPGAK-NNApproximate multiplierElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e774 (2021)
institution DOAJ
collection DOAJ
language EN
topic Gutter oil detection
Machine learning
FPGA
K-NN
Approximate multiplier
Electronic computers. Computer science
QA75.5-76.95
spellingShingle Gutter oil detection
Machine learning
FPGA
K-NN
Approximate multiplier
Electronic computers. Computer science
QA75.5-76.95
Wei Jiang
Yuhanxiao Ma
Ruiqi Chen
Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers
description Since consuming gutter oil does great harm to people’s health, the Food Safety Administration has always been seeking for a more effective and timely supervision. As laboratory tests consume much time, and existing field tests have excessive limitations, a more comprehensive method is in great need. This is the first time a study proposes machine learning algorithms for real-time gutter oil detection under multiple feature dimensions. Moreover, it is deployed on FPGA to be low-power and portable for actual use. Firstly, a variety of oil samples are generated by simulating the real detection environment. Next, based on previous studies, sensors are used to collect significant features that help distinguish gutter oil. Then, the acquired features are filtered and compared using a variety of classifiers. The best classification result is obtained by k-NN with an accuracy of 97.18%, and the algorithm is deployed to FPGA with no significant loss of accuracy. Power consumption is further reduced with the approximate multiplier we designed. Finally, the experimental results show that compared with all other platforms, the whole FPGA-based classification process consumes 4.77 µs and the power consumption is 65.62 mW. The dataset, source code and the 3D modeling file are all open-sourced.
format article
author Wei Jiang
Yuhanxiao Ma
Ruiqi Chen
author_facet Wei Jiang
Yuhanxiao Ma
Ruiqi Chen
author_sort Wei Jiang
title Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers
title_short Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers
title_full Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers
title_fullStr Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers
title_full_unstemmed Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers
title_sort gutter oil detection for food safety based on multi-feature machine learning and implementation on fpga with approximate multipliers
publisher PeerJ Inc.
publishDate 2021
url https://doaj.org/article/aaa6a0e47c764b6a84f3619f7c817abc
work_keys_str_mv AT weijiang gutteroildetectionforfoodsafetybasedonmultifeaturemachinelearningandimplementationonfpgawithapproximatemultipliers
AT yuhanxiaoma gutteroildetectionforfoodsafetybasedonmultifeaturemachinelearningandimplementationonfpgawithapproximatemultipliers
AT ruiqichen gutteroildetectionforfoodsafetybasedonmultifeaturemachinelearningandimplementationonfpgawithapproximatemultipliers
_version_ 1718420803107684352