Federated Learning for Clients’ Data Privacy Assurance in Food Service Industry
Authors:
- Hamed Taheri GorjiHGHamed Taheri Gorji
- Mahdi SaeediMSMahdi Saeedi
- Erum MushtaqEMErum Mushtaq
- Hossein Kashani ZadehHZHossein Kashani Zadeh
- Kaylee HusarikKHKaylee Husarik
- Seyed Mojtaba ShahabiSSSeyed Mojtaba Shahabi
- Jianwei QinJianwei Qin
- Diane E. ChanDCDiane E. Chan
- Insuck BaekIBInsuck Baek
- Moon S. KimMKMoon S. Kim
- Alireza AkhbardehAAAlireza Akhbardeh
- Stanislav SokolovSSStanislav Sokolov
Open Access
- 17 August 2023
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (16) , 9330
Abstract
The food service industry must ensure that service facilities are free of foodborne pathogens hosted by organic residues and biofilms. Foodborne diseases put customers at risk and compromise the reputations of service providers. Fluorescence imaging, empowered by state-of-the-art artificial intelligence (AI) algorithms, can detect invisible residues. However, using AI requires large datasets that are most effective when collected from actual users, raising concerns about data privacy and possible leakage of sensitive information. In this study, we employed a decentralized privacy-preserving technology to address client data privacy issues. When federated learning (FL) is used, there is no need for data sharing across clients or data centralization on a server. We used FL and a new fluorescence imaging technology and applied two deep learning models, MobileNetv3 and DeepLabv3+, to identify and segment invisible residues on food preparation equipment and surfaces. We used FedML as our FL framework and Fedavg as the aggregation algorithm. The model achieved training and testing accuracies of 95.83% and 94.94% for classification between clean and contamination frames, respectively, and resulted in intersection over union (IoU) scores of 91.23% and 89.45% for training and testing, respectively, of segmentation of the contaminated areas. The results demonstrated that using federated learning combined with fluorescence imaging and deep learning algorithms can improve the performance of cleanliness auditing systems while assuring client data privacy.Keywords
Funding Information
- National Institute of Food and Agriculture (2020-33610-32479, 20-340, 21-282)
- North Dakota Department of Agriculture (2020-33610-32479, 20-340, 21-282)
- Bioscience Innovation Grant Program (2020-33610-32479, 20-340, 21-282)
This publication has 26 references indexed in Scilit:
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Surveillance for Foodborne Disease Outbreaks — United States, 2009–2015Morbidity and Mortality Weekly Report, 2018
- Bactericidal activity of strong acidic hypochlorous water against Escherichia coli O157:H7 and Listeria monocytogenes in biofilms attached to stainless steelFood Science and Biotechnology, 2017
- Real-time pixel based early apple bruise detection using short wave infrared hyperspectral imaging in combination with calibration and glare correction techniquesFood Control, 2016
- A machine vision system for automatic detection of parasites Edotea magellanica in shell-off cooked clam Mulinia edulisJournal of Food Engineering, 2016
- A computer vision based technique for identification of acrylamide in potato chipsComputers and Electronics in Agriculture, 2015
- A Review and Comparative Analysis of Various Encryption AlgorithmsInternational Journal of Security and Its Applications, 2015
- Privacy and Big DataComputer, 2014
- Attachment behaviour of Escherichia coli K12 and Salmonella Typhimurium P6 on food contact surfaces for food transportationFood Microbiology, 2012
- A critical evaluation of sampling methods used for assessing microorganisms on surfacesFood and Bioproducts Processing, 2010