Technological solutions for intelligent data processing in the food industry
https://doi.org/10.20914/2310-1202-2018-2-256-263
Abstract
The article is devoted to the possibilities of application of artificial neural networks (ANN), which are a mathematical model, as well as its software or hardware implementation, built on the principle of organization and functioning of nerve cell networks of a living organism. Convolutional neural networks are arranged like the visual cortex of the brain and have achieved great success in image recognition, they are able to concentrate on a small area and highlight important features in it. The widespread use of ANN in medicine for the evaluation of radiographs, blood pressure and body mass index of patients on the analysis of their retina is noted. The use of ANN in the food industry for input quality control of raw materials is promising. In the world practice, various methods of remote control of raw materials are used, for this purpose ultrasonic scanning devices are mainly used. Such devices and analysis systems control raw materials by the ratio of meat tissues (muscle, connective, fat) in the carcass or half-carcass, without affecting the tissue structure, do not lead the quality at the cellular (microstructural) level. It is established that the structure of muscle (diameter of muscle fibers, the safety of the cellular elements, the porosity of the tissue, integrity of muscle fibers) reflects the quality of the raw material, its thermal state. Our work has begun on the creation of an expert system for quality control of meat raw materials at the microstructural level using modern intelligent technologies as ANN and computer vision. This direction is relevant and socially significant in the development of the meat industry, as it will significantly speed up the process of analysis of the quality of raw meat in the research laboratories of meat processing enterprises and testing centers and improve the objectivity of the results.
About the Authors
M. A. Nikitina
V.M. Gorbatov Federal Research Center for Food Systems of Russian Academy of Sciences
Cand. Sci. (Engin.), associate professor, leading scientific worker, the Head of the Direction of Information Technologies of the Center of Economic and Analytical Research and Information Technologies, Talalikhina Str., 26, Moscow, 109316, Russia
Cand. Sci. (Engin.), associate professor, leading scientific worker, the Head of the Direction of Information Technologies of the Center of Economic and Analytical Research and Information Technologies, Talalikhina Str., 26, Moscow, 109316, Russia
V. A. Pchelkina
V.M. Gorbatov Federal Research Center for Food Systems of Russian Academy of Sciences
Cand. Sci. (Engin.), leading scientific worker, Experimental clinic-laboratory of biological active substances of an animal origin, Talalikhina Str., 26, Moscow, 109316, Russia
Cand. Sci. (Engin.), leading scientific worker, Experimental clinic-laboratory of biological active substances of an animal origin, Talalikhina Str., 26, Moscow, 109316, Russia
O. A. Kuznetsova
V.M. Gorbatov Federal Research Center for Food Systems of Russian Academy of Sciences
Dr. Sci. (Engin.), director, Talalikhina Str., 26, Moscow, 109316, Russia
Dr. Sci. (Engin.), director, Talalikhina Str., 26, Moscow, 109316, Russia
References
1. Mak-Kallok U.S., Pitts V. A logical calculus of the ideas related to neural activity. Avtomaty [Automats] 1956. pp. 363–384. (in Russian)
2. Le Cun Y., Ranzato M. Deep Learning. Tutorial ICML, Atlanta. Available at: http://www.cs.nyu.edu/~yann/talks/lecun-ranzato-icml2013.pdf.
3. Bone X-Ray Deep Learning Competition. Available at: https://stanfordmlgroup.github.io/ competitions/mura.
4. Poplin R., Varadarajan A.V., Blumer K., Liu Y. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nature Biomedical Engineering volume. 2018. no. 2. pp. 158–164. DOI: 10.1038/s41551–018–0195–0.
5. Chinese farmers are using AI to help rear the world’s biggest pig population. Available at: https://www.theverge.com.
6. Deng J., Dong W., Socher R., Li L. – J. et al. Imagenet: A large-scale hierarchical image databaseю Computer Vision and Pattern Recognition. 2009. CVPR . IEEEConferenceon. 2009. pp. 248–255.
7. Hannun A., Case C., Casper J., Catanzaro B. et al. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXir:1412.5567, 2014.
8. Rajpurkar P., Zhang J., Lopyrev K., Liang P. Squad:100,000+ questions for machine comprehension of text. arXiv preprint arXiv: 1606.05250, 2016.
9. Gulshan V., Peng L., Coram M., Stumpe M.C. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs // Jama. 2016. no. 316(22). pp. 2402–2410.
10. Esteva A., Kuprel B., Novoa R.A., Ko J. et al. Dermatologist-level classification of skin cancer with deep neural networks // Nature. 2017. no. 542(7639). pp. 115–118.
11. Rajpurkar P., Hannun A.Y., Haghpanahi M., Bourn C. et al. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv preprint arXiv:1707.01836, 2017.
12. Grewal M., Srivastava M.M., Kumar P., Varadarajan S. Radnet: Radiologist level accuracy using deep learning for hemorrhage detection in ct scans. arXiv preprint arXiv:1710.04934, 2017.
13. Rajpurkar P., Irvin J., Zhu K., Yang B. et al. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv: 1711.05225, 2017.
14. Gale W., Oakden-Rayner L., Carneiro G., Bradley A.P. et al. Detecting hip fractures with radiologist-level performance using deep neuralnetworks/ arXiv e-prints, 2017.
15. Wang X., Peng Y., Lu L., Lu Z. et al. Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. arXiv preprint arXiv: 1705.02315, 2017.
16. Plyasheshnik P.I., Glebochev S.N., Shihow S.S. Raw materials under full control. Myasnaya industriya [Meat Industry]. 2015, no. 1, pp. 37–39. (in Russian).
17. The Best & Donovan Acra-Grade System. Operation and Maintenance Manual. Revision 4. Available at: http://www.bestanddonovan.com/acragrademanual.html#overview.
18. AutoFom III. Fully Automatic Ultrasonic Carcass Grading. Available at:http://www.carometec.com/products/item/autoform-III.
19. Kutsky J.A., Savell J.W., Johnson D.D., Smith G.C. et al. Predicting cutability of pork carcasses and hams using the Hennessy and Chong Fat Depth Indicator // Meat science. 1984. no. 11. pp. 13–26.
20. Listrat A., Lebret B., Louveau I. et al. How Muscle Structure and Composition Influence Meat and Flesh Quality // The Scientific World Journal. 2016. pp. 3182746. DOI: 10.1155/2016/3182746
21. Enikel D. Structure of muscle and meat quality //Fleischwirtschaft. 1987. no. 4. pp. 461–465.
22. Bendall I.R., Swatland H.J. A review of the relationships of pH with physical aspects of quality // Meat Science. 1988. no. 2(24). pp. 85–126.
23. Hvilia S.I. Comparative electronic histochemical analysis of meat with DFD and PSE defects //Technologija mesa. 1999. no. 1(40). pp. 13–16.
Review
For citations:
Nikitina M.A., Pchelkina V.A., Kuznetsova O.A. Technological solutions for intelligent data processing in the food industry. Proceedings of the Voronezh State University of Engineering Technologies. 2018;80(2):256-263. (In Russ.) https://doi.org/10.20914/2310-1202-2018-2-256-263
Views:
636
Email this article 
Post a Comment 
