Intelligent food processing: Journey from artificial neural network to deep learning

Nayak, Janmenjoy; Vakula, Kanithi; Dinesh, Paidi; Naik, Bighnaraj; Pelusi, Danilo

doi:10.1016/j.cosrev.2020.100297

Cited by 92 publications

(43 citation statements)

References 169 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Researchers have reported the use of Tabu Search and Genetic Algorithm (GA) for optimization in different food engineering areas such as thermal processing, vehicle routing and heat exchangers design ( Wari and Zhu, 2016 ). The food processing industries have used Evolutionary Algorithms (GA, Differential Evolution (DE) and their hybrids with other techniques) in thermal processing, food quality, process design, drying, fermentation and hydrogenation processes and they found the extensive application of GA and DE in most of the cases and also reported that about the other algorithms which have proven to be quite as effective and in some cases better in terms of the best result attained and run time required ( Nayak et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Application of bio-inspired optimization algorithms in food processing

Sarkar

Salauddin

Mukherjee³

et al. 2022

Current Research in Food Science

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Application of bio-inspired optimization algorithms in food processing

Sarkar

Salauddin

Mukherjee³

et al. 2022

Current Research in Food Science

View full text Add to dashboard Cite

“…DNN algorithms have a wide variety of applications in the food domain, including food recognition and classification, food calorie estimation, food supply chain monitoring, food quality detection, food contamination detection, etc. 23 , 26 . Although applications of DNN algorithms have been studied in several food-related domains, to our knowledge, there is no study where the main focus is on the detection and segmentation of fecal contamination on meat surfaces.…”

Section: Introductionmentioning

confidence: 99%

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses

Gorji

Shahabi

Sharma

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Food safety and foodborne diseases are significant global public health concerns. Meat and poultry carcasses can be contaminated by pathogens like E. coli and salmonella, by contact with animal fecal matter and ingesta during slaughter and processing. Since fecal matter and ingesta can host these pathogens, detection, and excision of contaminated regions on meat surfaces is crucial. Fluorescence imaging has proven its potential for the detection of fecal residue but requires expertise to interpret. In order to be used by meat cutters without special training, automated detection is needed. This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images using EfficientNet-B0 to determine which meat surface images showed fecal contamination and then U-Net to precisely segment the areas of contamination. The EfficientNet-B0 model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discriminating clean and contaminated areas on carcasses. U-Net segmented areas with fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can improve food safety assurance by allowing the industry to use CSI-D fluorescence imaging to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero-tolerance plan.

show abstract

“…It finds directions in the space (called latent variables) that explain at the same time the variance of both the experimental data and measured variable of interest [ 15 ]. Moreover, in the last years, algorithms like artificial neural networks (ANNs) were applied to nearly every field of food science, thanks to their high computational power and a consequent ability to handle more complex tasks [ 16 ]. The reported techniques are summarized in Figure 1 , as well as the main statistical analyses used in these studies.…”

Section: Introductionmentioning

confidence: 99%

Sensing Technology for Fish Freshness and Safety: A Review

Franceschelli

Berardinelli

Dabbou

et al. 2021

Sensors

View full text Add to dashboard Cite

Standard analytical methods for fish freshness assessment are based on the measurement of chemical and physical attributes related to fish appearance, color, meat elasticity or texture, odor, and taste. These methods have plenty of disadvantages, such as being destructive, expensive, and time consuming. All these techniques require highly skilled operators. In the last decade, rapid advances in the development of novel techniques for evaluating food quality attributes have led to the development of non-invasive and non-destructive instrumental techniques, such as biosensors, e-sensors, and spectroscopic methods. The available scientific reports demonstrate that all these new techniques provide a great deal of information with only one test, making them suitable for on-line and/or at-line process control. Moreover, these techniques often require little or no sample preparation and allow sample destruction to be avoided.

show abstract

Intelligent food processing: Journey from artificial neural network to deep learning

Cited by 92 publications

References 169 publications

Application of bio-inspired optimization algorithms in food processing

Application of bio-inspired optimization algorithms in food processing

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses

Sensing Technology for Fish Freshness and Safety: A Review

Contact Info

Product

Resources

About