Login | Register
Kazakh National Agrarian Research University ISSN 2304-3334 (Print)  ·  ISSN 2304-3334 (Online)
submit an article
Menu
submit an article
AGRICULTURE MECHANIZATION AND ELECTRIFICATION

DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING

E.T. Ramazanov* 1 , S.E. Sibanbaeva 1

1 Almaty Management University

doi.org/10.37884/1-2022/13 pp. 105-111 Admitted 16.03.2022 Published 30.03.2022

Abstract

The article discusses the results of the development of an intelligent classification system for ewes breeds based on machine learning (artificial intelligence, neural network). The architecture of an intelligent system is presented. In the architecture of the information system, convolutional neural networks CNN and a camera of a mobile device are used. In the photo of the camera of the mobile device, the object is located in the center, facing directly at the camera. The neural network identifies the object and classifies the object based on training.

The article outlines the main points of software - a windowed application such as a digital virtual assistant, which can be useful in the production of buying and selling sheep for unprepared participants in this process. The information system makes it possible to navigate sheep breeds according to the characteristics of a particular specimen and to determine the breed, as well as useful characteristics associated with a particular breed. The system can also be used as a reference system for decision-making in commercial activities related to the purchase or sale of sheep.

Machine Learning, Convolutional Neural Networks, Intelligent System, Neural Network Training, Detection, Classification

01 Introduction

The full text of the article is available for download in PDF format on the right panel.

02 References

  1. 1. Мониторинг количества зарегистрированных и действующих субъектов малого и среднего предпринимательства в Республике Казахстан [Электронный ресурс]/ Бюро национальной статистики. – Нур-Султан: 2021. – Режим доступа: http://stat.gov.kz/faces/wcnav_externalId/homeNumbersS.
  2. 2. Machine Learning Repository [Электронный ресурс]/ Center for Machine Learning and Intelligent Systems. – Режим доступа: https://www.kaggle.com/intelecai.
  3. 3. Moses Olafenwa, John Olafenwa Prediction Classes ResNet ImageAI [Электронный ресурс]/Moses Olafenwa, John Olafenwa – GitHub.: 2019. – Режим доступа: https://imageai.readthedocs.io/prediction/index.html
  4. 4. Mehdi S. M., Sajjadi Bernhard, Scholkopf Michael Hirsch. EnhanceNet: Single Image Super-Resolution Through Automated Texture [Электронный ресурс] / Mehdi S. M., Sajjadi Bernhard, Scholkopf Michael Hirsch. – Tubingen, Germany: Max Planck Institute for Intelligent Systems, 2017.– 19с. – Режим доступа: https://arxiv.org/pdf/1612.07919.pdf.
  5. 5. Бунин О. Введение в архитектуры нейронных сетей [Электронный ресурс]/ Бунин О. –Хабр.: 2017. – 15с. –Режим доступа: https://habr.com/ru/company/oleg-bunin/blog/340184/
  6. 6. Производственная классификация овец Республики Казахстан [Электронный ресурс]/ Семгу. – Режим доступа: http://ebooks.semgu.kz/content.php?cont=r;1256
  7. 7. Современные информационные технологии в сельском хозяйстве [Электронный ресурс]/Аграрный сектор. –М.: 2021. – Режим доступа: https://agrarnyisector.ru/category/zhivotnovodstvo.
  8. 8. Верхова Н.А. Информационные технологии в сельском хозяйстве [Электронный ресурс]/Верхова Н.А – Астрахань.: 2019. –7с. – Режим доступа: https://scienceforum.ru/2015/article/2015011544.
  9. 9. Куткова А. Н., Казьмина М. А., Польшакова Н. В. Обзор современных информационных решений автоматизации животноводческих предприятий / Куткова А. Н., Казьмина М. А. // Молодой ученый. — 2017. — №4. — С. 167-169.
  10. 10. Sugiharti E., Arifudin R., Putra A.T. C-means and fuzzy as base of cattle data collection from manual card system to online information system / Sugiharti E., Arifudin R., Putra A.T // Journal of Theoretical and Applied Information Technology. — 2018—Volume 96—2018. —Issue 21.-Pages 7176-7186.

Citation Links

[1]2022. DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING . Izdenister natigeler. 1 (93) (Mar. 2022), 105–111. DOI:https://doi.org/10.37884/1-2022/13.
(1)DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING . Izdenister natigeler 2022, No. 1 (93), 105-111. https://doi.org/10.37884/1-2022/13.
DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING . (2022). Izdenister Natigeler, 1 (93), 105-111. https://doi.org/10.37884/1-2022/13
DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING . Izdenister natigeler, [S. l.], n. 1 (93), p. 105–111, 2022. DOI: 10.37884/1-2022/13. Disponível em: https://agrosoil.kaznaru.edu.kz/index.php/research/article/view/80. Acesso em: 15 sep. 2026.
“DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING ”. 2022. Izdenister Natigeler, no. 1 (93) (March): 105-11. https://doi.org/10.37884/1-2022/13.
“DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING ” (2022) Izdenister natigeler, (1 (93), pp. 105–111. doi:10.37884/1-2022/13.
[1]“DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING ”, Izdenister natigeler, no. 1 (93), pp. 105–111, Mar. 2022, doi: 10.37884/1-2022/13.
“DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING ”. Izdenister Natigeler, no. 1 (93), Mar. 2022, pp. 105-11, https://doi.org/10.37884/1-2022/13.
“DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING ”. Izdenister natigeler, no. 1 (93) (March 30, 2022): 105–111. Accessed September 15, 2026. https://agrosoil.kaznaru.edu.kz/index.php/research/article/view/80.
1.DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING . Izdenister natigeler [Internet]. 2022 Mar. 30 [cited 2026 Sep. 15];(1 (93):105-11. Available from: https://agrosoil.kaznaru.edu.kz/index.php/research/article/view/80
1.DEVELOPMENT OF A MOBILE APP FOR SHEEP CLASSIFICATION BASED ON MACHINE LEARNING . Izdenister natigeler. 2022;(1 (93):105-111. doi:10.37884/1-2022/13