Machine learning and computer vision application in automated monitoring of the bee colonies in agriculture

Authors: Kochetkova A.A., Kochetkov A.A., Pushkin An.N., Pushkin Al.N.
Published in issue: #3(98)/2025
DOI:
Category: Informatics, Computer Engineering and Control | Chapter: Information Technology. Computer techologies. Theory of computers and systems
Keywords: machine learning, computer vision systems, YOLO, ultralytics, beekeeping, bee colony population management, innovative technologies in agriculture, Fourth Industrial Revolution
Published: 03.07.2025

The paper is devoted to application of the machine learning methods in implementation of the bee colony population monitoring system. It proposes an innovative method for using the computer vision systems and artificial neural networks in the beekeeping. The machine learning algorithms and software for analyzing dynamics in the bee population are developed. The empirical data confirm a possibility of the efficient bee population monitoring using the machine learning methods. The proposed approach allows for automated identification of the honeycombs state, detection of the pathologies, monitoring the brood development, and assessment of the food supply quality. The system is intended for use in agriculture and scientific research in the beekeeping.

References

[1] Seitov S.K. Innovative development of agriculture in Russia: current status and support measures. Proceedings of the Timiryazev Agricultural Academy, 2023, no. 5, pp. 134-150. (In Russ.). https://doi.org/10.26897/0021-342X-2023-5-134-150

[2] Vetchinnikov D.V., Kokurin D.I., Vorozheikina T.M. Analysis of the state of innovation policy in the infrastructural economy of the Russian Federation on the example of agriculture. Bulletin of the MFUA, 2023, no. 3, pp. 160-172. (In Russ.). https://doi.org/10.52210/2224669X_2023_3_160

[3] Afanasyev V.N. Effective management of beekeeping in the Russian Federation. Fundamental and applied solutions to the priority tasks of beekeeping. International Scientific and Practical Conference: collection of materials. Kazan, TIPKA Publ., 2023, vol. II, pp. 57-61. (In Russ.).

[4] Medvedeva N.I. Fundamentals of beekeeping. Moscow, AST Publ., 2015, 191 p. (In Russ.).

[5] Weiss G.M. Mining with Rare Cases. Data Mining and Knowledge Discovery Handbook. Springer, 2005, pp. 765–776.

[6] Chawla N.V., Bowyer K.W., Hall L.O., Kegelmeyer W.P. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 2002, vol. 16, pp. 321–357.

[7] Fawcett T. An Introduction to ROC Analysis. Pattern Recognition Letters, 2006, vol. 27, no. 8, pp. 861–874.

[8] Bishop C.M. Pattern Recognition and Machine Learning. Springer, 2006, 738 p.

[9] Shapiro L., Stockman J. Computer vision. Moscow, BINOMIAL. Laboratory of Knowledge, 2015, 763 p. (In Russ.).

[10] Ultralytics YOLOv8 Docs. URL: https://docs.ultralytics.com/ru (accessed December 26, 2024).