The use of convolutional neural networks for automatic diseases detection tasks
M.A. Shereuzheva, M.A. Shereuzhev, Z.M. Albekova
Upload the full text
Abstract: This article provides an overview of existing convolutional neural network architectures and their application in the classification task for detecting diseases of fruits and plants. Diseases of plants and fruits are a serious problem in agriculture and horticulture, and their early detection can help in taking timely measures to prevent the spread and minimize damage. The results of the study can be useful for the development of automated systems for detecting diseases of fruits and plants, which helps to increase yields.
Keywords: neural networks, machine learning, convolutional network architecture, computer vision, image classification
For citation. Shereuzheva M.A., Shereuzhev M.A., Albekova Z.M. The use of convolutional neural networks for automatic diseases detection tasks. News of the Kabardino-Balkarian Scientific Center of RAS. 2023. No. 5(115). Pp. 41–51. DOI: 10.35330/1991-6639-2023-5-115-41-51
References
- Digital agriculture [Электронный ресурс]. URL: https://en.wikipedia.org/wiki/Digital_agriculture.
- Shereuzheva M.A., Shereuzhev M.A. Development of expert systems to improve the efficiency of growing plants in agriculture. News of the Kabardino-Balkarian Scientific Center of RAS. 2022. No. 5(109). Pp. 93–104. DOI: 10.35330/1991-6639-2022-5-109-93-104. (In Russian)
- Nagoev Z.V., Shuganov V.M., Bzhikhatlov K.Ch. et al. Prospects for increasing the productivity and efficiency of agricultural production with the use of an intelligent integrated environment. News of the Kabardino-Balkarian Scientific Center of RAS. 2021. No. 6(104). Pp. 155–165. DOI: 10.35330/1991-6639-2021-6-104-155-165. (In Russian)
- Krizhevsky A., Sutskever I., Hinton G.E. ImageNet classification with deep convolutional neural networks. Communications of the ACM. 2012. 60(6). Pp. 84–90.
- Pushkarev A., Yakubailik O. A web application for visualization, analysis, and processing of agricultural monitoring spatial-temporal data. CEUR Workshop Proceedings. 2021. Vol. 3006. Pp. 231–237. URL: http://ceur-ws.org/Vol-006/27_short_paper.pdf
- Skvortsov E.A., Skvortsova E.G., Sandu I.S. et al. Transition of Agriculture to Digital, Intellectual and Robotics Technologies. Ekonomika regiona [Economy of Region]. 2018. Vol. 14. No. 3. Pp. 1014–1028. (In Russian)
- He K. et al. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. Pp. 770–778.
- Iandola F. et al. Densenet. Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv. 2014. Pp. 1404–1869.
- Huang G., Liu Z., Van Der Maaten et al. Сonnected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. Pp. 4700–4708.
- Sandler M., Howard A., Zhu M. et al. MobileNetV2. Inverted residuals and linear bottlenecks. Proceedings of the IEEE conference on computer vision and pattern recognition. Pp. 4510–4520.
- Szegedy C. et al. Inception-v4, inception-resnet and the impact of residual connections on learning. Thirty-first AAAI conference on artificial intelligence. 2017.
- Tan M., Le Q. Efficientnet. Rethinking model scaling for convolutional neural networks. International conference on machine learning. PMLR. 2019. Pp. 6105–6114.
Information about the authors
Shereuzheva Milana Arturovna, master, Department “Information technologies and computing systems”, Moscow Technical University “STANKIN”;
127055, Russia, Moscow, 1 Vadkovsky lane;
trainee researcher of the Laboratory “Intellectual Habitats” of the Institute of Computer Science and Problems of Regional Management – branch of Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 37-a I. Armand street;
milana.shereuzheva@mail.ru, ORCID: https://orcid.org/0000-0002-6668-4703
Shereuzhev Madin Arturovich, senior lecturer, Department “Robotic systems and mechatronics”, Moscow State Technical University named after N.E. Bauman;
105005, Russia, Moscow, build. 5 corps 1 Baumanskaya street;
shereuzhev@bmstu.ru, ORCID: https://orcid.org/0000-0003-2352-992Х
Albekova Zamira Mukhamedalievna, Candidate of Pedagogical Sciences, Associate Professor, Department of Information Systems and Technologies, Institute of Digital Development, North Caucasus Federal University;
350029, Russia, Stavropol, 2 Kulakov avenue;
zalbekova@ncfu.ru, ORCID: https://orcid.org/0000-0002-7214-8114