The review of food safety inspection system based on artificial intelligence, image processing, and robotic

Chen, Tzu-Chia; Yu, Shuyan

doi:10.1590/fst.35421

Cited by 25 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in both underdeveloped and developed nations, it is crucial for human health [9]. AI, ML, Big data, blockchain, etc., have found their applications in identifying, sorting, and determining safety in food products that fasten this screening process, ultimately bene ting the food industry [10,11]. Food-borne illnesses, pathogenic genomes, and emerging dynamic data, such as literary, commercial, and market data, have seen developing machine learning applications, such as antibiotic-resistant forecasting, pathogen source tracing, and food-borne epidemic identi cation and vulnerability assessment [12].…”

Section: Literature Reviewmentioning

confidence: 99%

An Investigation in Applying Internet of Things Approach in Safe Food Dietary Plan for Better Chronic Diabetes Management among Elderly Adults

Geetha

Krishna

Vyas

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

Chronic diabetes among adults is a public health concern and clinicians are trying to implement new strategies to effectively manage the disease. Traditionally, healthcare professionals are used to monitor and track the lab reports of patients. After that, they used to provide respective medicines and lifestyle plans to manage the chronic disease. The lifestyle of the patients and access to safe and secure food products is also responsible for developing chronic diseases. Thus, the Internet of Things (IoT) has taken an utmost interest in managing diabetes. This research is going to analyze the accuracy of IoT in assisting chronic diabetes management and determining food safety. To accomplish the research objectives, the researchers performed a linear regression analysis to understand whether IoT devices and Artificial Intelligence (AI) assist in assessing food safety and diabetes management. The independent variables selected were lab test values, treatment records, epoch size of AI, and image resolution of the training dataset. Dependent variables were the accuracy of IoT. Here, the accuracy of IoT and AI has been determined. Moreover, the accuracy of clinicians in diabetes management has been observed. It has been found that clinicians have high variance in accuracy (max 99%) whereas machines have limited variance in accuracy (max. 98%). Secondary research identified that clinicians need to be involved along with IoT devices for better management of this chronic disease and help patients by providing the safest food options.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Investigation in Applying Internet of Things Approach in Safe Food Dietary Plan for Better Chronic Diabetes Management among Elderly Adults

Geetha

Krishna

Vyas

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

show abstract

“…Looking for the balance between accuracy and precision of diagnoses at meat inspection, another option could be to support the work of meat inspectors with new digital techniques and artificial intelligence. In particular, artificial intelligence can be used to analyze and process large amounts of data from various sources, such as image processing system, chemical sensors, and microbiological tests to identify patterns and anomalies in meat quality, classify carcasses, detect potential health hazards, and provide real-time feedback to inspectors ( 26 , 27 ). As a matter of fact, such options are already under development, such for instance the use of artificial intelligence for automatic detection of abattoir lesion ( ADAL | F4T Lab ) ( 28 ), photo artificial intelligence identification of animals ( Phaid | F4T Lab ) ( 29 ) and scanning animal tattoos on slaughter line for traceability ( ReaDop | F4T Lab ) ( 30 ).…”

Section: Discussionmentioning

confidence: 99%

Can we use meat inspection data for animal health and welfare surveillance?

Comin,

Jonasson,

Rockström

et al. 2023

Front. Vet. Sci.

View full text Add to dashboard Cite

Ante- and post-mortem inspections at abattoir were originally introduced to provide assurance that animal carcasses were fit for human consumption. However, findings at meat inspection can also represent a valuable source of information for animal health and welfare surveillance. Yet, before making secondary use of meat inspection data, it is important to assess that the same post-mortem findings get registered in a consistent way among official meat inspectors across abattoirs, so that the results are as much independent as possible from the abattoir where the inspection is performed. The most frequent findings at official meat inspections of pigs and beef cattle in Sweden were evaluated by means of variance partitioning to quantify the amount of variation in the probabilities of these findings due to abattoir and farm levels. Seven years of data (2012–2018) from 19 abattoirs were included in the study. The results showed that there was a very low variation between abattoirs for presence of liver parasites and abscesses, moderately low variation for pneumonia and greatest variation for injuries and nonspecific findings (e.g., other lesions). This general pattern of variation was similar for both species and implies that some post-mortem findings are consistently detected and so are a valuable source of epidemiological information for surveillance purposes. However, for those findings associated with higher variation, calibration and training activities of meat inspection staff are necessary to enable correct conclusions about the occurrence of pathological findings and for producers to experience an equivalent likelihood of deduction in payment (independent of abattoir).

show abstract

“…This type of algorithm is very important in artificial intelligence because it can reduce the programming burden by selecting explicit features. This algorithm can be used to solve problems in image recognition, speech recognition, text classification, and other applications that require supervision (supervised), no supervised (unsupervised), or some supervised (semi-supervised) [ 35 ].…”

Section: Methodsmentioning

confidence: 99%

Health to Eat: A Smart Plate with Food Recognition, Classification, and Weight Measurement for Type-2 Diabetic Mellitus Patients’ Nutrition Control

Salaki

Shin

Lee

et al. 2023

Sensors

View full text Add to dashboard Cite

The management of type 2 diabetes mellitus (T2DM) is generally not only focused on pharmacological therapy. Medical nutrition therapy is often forgotten by patients for several reasons, such as difficulty determining the right nutritional pattern for themselves, regulating their daily nutritional patterns, or even not heeding nutritional diet recommendations given by doctors. Management of nutritional therapy is one of the important efforts that can be made by diabetic patients to prevent an increase in the complexity of the disease. Setting a diet with proper nutrition will help patients manage a healthy diet. The development of Smart Plate Health to Eat is a technological innovation that helps patients and users know the type of food, weight, and nutrients contained in certain foods. This study involved 50 types of food with a total of 30,800 foods using the YOLOv5s algorithm, where the identification, measurement of weight, and nutrition of food were investigated using a Chenbo load cell weight sensor (1 kg), an HX711 weight weighing A/D module pressure sensor, and an IMX219-160 camera module (waveshare). The results of this study showed good identification accuracy in the analysis of four types of food: rice (58%), braised quail eggs in soy sauce (60%), spicy beef soup (62%), and dried radish (31%), with accuracy for weight and nutrition (100%).

show abstract

The review of food safety inspection system based on artificial intelligence, image processing, and robotic

Cited by 25 publications

References 44 publications

An Investigation in Applying Internet of Things Approach in Safe Food Dietary Plan for Better Chronic Diabetes Management among Elderly Adults

An Investigation in Applying Internet of Things Approach in Safe Food Dietary Plan for Better Chronic Diabetes Management among Elderly Adults

Can we use meat inspection data for animal health and welfare surveillance?

Health to Eat: A Smart Plate with Food Recognition, Classification, and Weight Measurement for Type-2 Diabetic Mellitus Patients’ Nutrition Control

Contact Info

Product

Resources

About