Development of a method of applying neural and mivar networks for identification and selection of indoor and garden plants

In recent years, there has been a surge of gardeners' interest in growing plants both on farms and at home. The aim of the study is to develop a method for the integrated application of neural networks for plant identification from photos and mivar technologies to provide personalized recommendations. A residual convolutional neural network ResNet20, pre-trained on a dataset of plants, is used for image classification. The mivar expert system provides a personalized recommendation based on the growing conditions and parameters of the plant defined by the neural network. A model for describing the provision of recommendations is created, which helps users to get the desired result in the form of the name of the plant. A method of applying neural and mivar networks is developed to generate logically sound plant recommendations depending on environmental conditions and user preferences. According to the results of experiments, we can conclude that in order to increase the accuracy of image classification, it is necessary to increase the number of layers of the neural network by about 1.5 times when increasing the recognized plants from 3 to 9. The complex application of convolutional neural networks and mivar technologies allows to achieve high accuracy of plant detection and provide high-quality recommendations for users.

1. Varlamov O.O. Evolyutsionnye bazy dannykh i znanii dlya adaptivnogo sinteza intellektual'nykh sistem. Mivarnoe informatsionnoe prostranstvo. Moscow: Radio i svyaz'; 2002. 286 p. (In Russ.).

2. Platonov Yu.G. Analiz perspektiv perekhoda informatsionnykh sistem na servisno-orientirovannuyu arkhitekturu. Problemy informatiki. 2011;(4):56–65. (In Russ.).

3. Shen Q., Gun. Sh., Varlamov O.O, Adamova L.E., Balenko E.G. Dynamic Robot Path Planning Based on Semantic Object Detection Using Mivar Expert System. Problems of Artificial Intelligence. 2024;(4):164–176. (In Russ.). http://doi.org/10.24412/2413-7383-2024-4-164-176

4. Kotsenko A.A. Development of Models of Mivar Logic Space to Provide Three-Dimensional Movement of Autonomous Robots. In: MIVAR'24: sbornik nauchnykh statei, 18–20 April 2024, Moscow, Russia. Moscow: INFRA-M; 2024. P. 361–366.

5. Kovalenko A.V., Kondrahin S.S., Smyslov D.O., Loseva S.S. Mivar Expert Systems for Selecting a Game Training Device for Developing Driving Skills. In: MIVAR'24: sbornik nauchnykh statei, 18–20 April 2024, Moscow, Russia. Moscow: INFRA-M; 2024. P. 67–72. (In Russ.).

6. Vasyunin M.A., Dyachkov M.Yu., Plotnikov F.S., Udodova K.I., Burmistrova M.V. MES for the Selection of Dishes for Restaurants. In: MIVAR'23: sbornik studencheskikh statei. Moscow: INFRA-M; 2023. P. 33–38. (In Russ.).

7. Tislyuk D.A., Rozhnenko M.K., Bolshakov S.A., Kovaleva N.A., Bulatova I.G. MES for Selection of Candidates for IT Positions. In: MIVAR'22: sbornik nauchnykh statei. Moscow: INFRA-M; 2022. P. 98–104. (In Russ.).

8. Soboleva E.D., Popova I.A., Makarov D.A., Baldin A.V., Kovaleva N.A. The Method of Transformation from a Metagraph Model of Knowledge Representation to a Mivar Model. In: MIVAR'22: sbornik nauchnykh statei. Moscow: INFRA-M; 2022. P. 220–227. (In Russ.).

9. Abrosimova N.G., Arbuzov A.P., Savrasov P.A., Aksenova M.V., Antonov A.I. MES for the Organization of Project Management of the IT Company. In: MIVAR'22: sbornik nauchnykh statei. Moscow: INFRA-M; 2022. P. 6–12. (In Russ.).

10. Antsifrov N.S., Mukhanov E., Fedorov I.N., Bolshakov S.A., Eliseeva E.A., Myshenkov K.S. MES for the Selection of Transport for Public Utilities. In: MIVAR'23: sbornik studencheskikh statei. Moscow: INFRA-M; 2023. P. 7–14. (In Russ.).

11. Kotsenko A.A. Analysis of Application of Mivar Nets in the Format of Bipartite and Tripartite Graphs for Automated Process Control Systems. In: MIVAR'24: sbornik nauchnykh statei, 18–20 April 2024, Moscow, Russia. Moscow: INFRA-M; 2024. P. 432–438.

12. Pinskaya N.M., Fonkants R.V., Safin R.R., Semkin P.S., Shkuratova L.P. MES for Classification of Speech Defects. In: MIVAR'23: sbornik studencheskikh statei. Moscow: INFRA-M; 2023. P. 163–173. (In Russ.).

13. Andreev A., Kotsenko A., Varlamov O., Kim R., Goryachkin B. Text Processing Using LLM for Automatic Creation of Agricultural Crops Knowledge Bases. In: BIO Web of Conferences: Volume 130: International Scientific Conference on Biotechnology and Food Technology (BFT-2024), 03–06 September 2024, Saint Petersburg, Russia. EDP Sciences; 2024. http://doi.org/10.1051/bioconf/202413001029

14. Samsonova I.D., Plakhova A.A. New Approaches to the Issue of Classification of Honey Plants and Honey Collections. The North Caucasus Ecological Herald. 2024;20(1):40–47. (In Russ.).

15. Svetasheva T.Yu., Lakomov A.F., Privalova M.V., Smirnova E.V., Maximova T.V. International Internet Platform iNaturalist as an Observation Base of Plants Included in the Red Data Book of Tula Oblast. Phytodiversity of Eastern Europe. 2020;14(4):549–559. (In Russ.).

16. Golitsyna I.N. Kak gramotno ispol'zovat' veb-servisy? Narodnoe obrazovanie. 2017;(5):104–111. (In Russ.).

17. Dmitrienko V.D., Zakovorotnyi A.Yu. Solving the Problem of Additional Training of Classical Neural Networks. Automation of Technologies and Production. 2015;(4):32–40. (In Russ.).