Designing a cloud architecture and mobile application for an agricultural pest identification system
Year: 2026
Type: article
Abstract: The article considers approaches to designinga cloud-based architecture for an intelligent agricultural pest identification system using a mobileapplication. An analysis of modern approaches to building mobile object recognition systems is conductedand the relevance of combining mobile technologies, cloud computing, and machine learning methods forsolving computer vision problems in conditions of limited mobile device resources is substantiated. Thesystem architecture based on the distribution of the computational load between the client and server partsis proposed. The mobile application performs the functions of receiving and transmitting images, whiledata processing is implemented on the server using the YOLOv11-N deep learning model. The architectureincludes an application server, a computer vision service, a mobile client, and external cloud services fordata storage and user authorization. The technological implementation of the system is described, inparticular, the use of Node.js and FastAPI for the server side, Docker containerization and the Google CloudRun platform for deployment, as well as Firebase for organizing data storage and user management. Theproposed solution provides scalability, efficient use of resources and the ability to centrally update machinelearning models. The results obtained can be used to create intelligent monitoring systems in the agriculturalsector and other industries that require real-time object recognition.Keywords: cloud computing, mobile application, computer vision, machine learning, pestidentification, YOLO, distributed architecture, microservices References1. Форкун Ю., Мартинюк В., Яшина О. Метод розробки та проєктування архітектурноїскладової програмного застосунку. Measuring and Computing Devices in Technological Processes.– 2023. – №4.– С.87–93.– DOI: https://doi.org/10.31891/2219-9365-2023-76-112. Бешта В. С., Комаричев А.В., Філімончук Т. В., Баранєй Д. І. Модель мобільногододатку, яка орієнтована на обробку даних. Системи управління, навігації та звʼязку. Збірникнаукових праць. – 2024. – Том 3, № 77. – С. 80–87. – DOI:https://doi.org/10.26906/SUNZ.2024.3.0803. Semerikov S. et al., Models and Technologies for Autoscaling Based on Machine Learningfor Microservices Architecture, Proceedings of the 8th International Conference on ComputationalLinguistics and Intelligent Systems. Volume I: Machine Learning Workshop, – 2024. –P. 316-330. –Електронний ресурс. – Режим доступу:: https://ceur-ws.org/Vol-3664/paper22.pdf4. Mamun, S. B., Payel, I. J., Ahad, M. T., Atkins, A. S., Song, B., Li, Y. Grape Guard: A YOLObased mobile application for detecting grape leaf diseases, Journal of Electronic Science andTechnology. –2025.– Vol. 23. – Issue 1. 100300. – DOI: https://doi.org/10.1016/j.jnlest.2025.100300.5. Zheng, H., Liu, C., Zhong, L., Yin, X., Zhang, H., Zhu, X., Yang, G., Zhu, Y. An androidsmartphone application for rice panicle detection and rice growth stage recognition using alightweight YOLO network. – Frontiers in Plant Science. – 2025. – Vol. 16. – Article 1561632. –DOI: https://doi.org/10.3389/fpls.2025.15616326. Yulita I.N., Rambe M.F.R., Sholahuddin A., Prabuwono A.S. A Convolutional NeuralNetwork Algorithm for Pest Detection Using GoogleNet. – AgriEngineering. – 2023. – Vol. 5, No. 4.– P. 2366–2380. – DOI: https://doi.org/10.3390/agriengineering50401457. Saeed A.T., Schonfeld D. Cloud-Based ImageNet Object Recognition for Mobile Devices.Proceedings of IMDC-SDSP 2020. – 2020. – DOI: http://dx.doi.org/10.4108/eai.28-6-2020.22979168. Karar M.E., Alsunaydi F., Albusaymi S., Alotaibi S. A new mobile application of agriculturalpests recognition using deep learning in cloud computing system. Alexandria Engineering Journal. –2021. – Vol. 60, Is. 4. – P. 4067–4082. – DOI: https://doi.org/10.1016/j.aej.2021.03.0099. Nugroho E.D., Verdiana M., Algifari M.H., Pramudita A.S., Adi S. Development of YOLOBased Mobile Application for Detection of Defect Types in Robusta Coffee Beans. Journal of AppliedInformatics and Computing. – 2025. – Vol. 9, No. 1. – P. 153–160. DOI:https://doi.org/10.30871/jaic.v9i1.888610.Chen, J.-W., Lin, W.-J., Cheng, H.-J., Hung, C.-L., Lin, C.-Y., & Chen, S.-P. A SmartphoneBased Application for Scale Pest Detection Using Multiple-Object Detection Methods. Electronics.– 2021. – 10(4). – P. 372. – DOI: https://doi.org/10.3390/electronics1004037211.Wong M.O., Abubacker N.F. YOLO-Driven Lightweight Mobile Real-Time Pest Detectionand Web-Based Monitoring for Sustainable Agriculture. International Journal of Advanced ComputerScience and Applications. – 2024. – Vol. 15, No. 12. – 12 p. DOI:https://dx.doi.org/10.14569/IJACSA.2024.015126712.Бердник, Ю. М., & Скотаренко, А. О. До проблеми розпізнавання об’єктів на пристрояхз обмеженими ресурсами. Проблеми програмування. – 2024. – 4 – С. 14-22. – DOI:https://doi.org/10.15407/pp2024.04.01413.Martinez-Alpiste, I., Golcarenarenji, G., Wang, Q., & Alcaraz-Calero, J. M. Smartphonebased real-time object recognition architecture for portable and constrained systems. Journal of RealTime Image Processing. – 2021. – Vol. 19. – P. 103–115 – DOI: https://doi.org/10.1007/s11554-021-01164-1
Authors: О.Є. П’ятикоп, А.Є. Шевченко, Т.О. Левицька
Institution: Pryazovskyi State Technical University
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
Open Access status: bronze
OpenAlex ID: W7163581982