Оценка и прогнозирование методами машинного обучения гниения плодовых растений на раннем этапе после сбора урожая (Early Postharvest Decay Assessment and Prediction in Fruit Plants by Machine Learning Methods) тема диссертации и автореферата по ВАК РФ 00.00.00, кандидат наук Стасенко Никита Андреевич

• Стасенко Никита Андреевич
• кандидат наук
• 2026

Оглавление диссертации кандидат наук Стасенко Никита Андреевич

Contents

Page

Introduction

Chapter 1. Literature Review

1.1 Background

1.1.1 Postharvest Losses in Apple Production

1.1.2 Convolutional Neural Networks

1.1.3 Generative Adversarial Networks

1.2 Related Works

1.2.1 Methods and Algorithms for Plant Quality Monitoring and Evaluation

1.2.2 Methods and Algorithms for Diseases Assessment and Prediction in Plants

1.2.3 Methods and Algorithms for Postharvest Losses Evaluation in Plants

1.2.4 Computer Vision and Machine Learning for NIR Data Analysis

1.2.5 Embedded Systems with AI based Approaches for Plant

Quality Estimation

1.3 Discussion

Chapter 2. Deep Learning for Decay Detection and Prediction in Stored

Apples at Postharvest Stage

2.1 Introduction

2.2 Methodology

2.2.1 Samples

2.2.2 Experimental Setup

2.2.3 Data Collection

2.2.4 Data Processing and Labeling

2.3 Convolutional Neural Networks for the Decayed and Non-decayed

Areas Segmentation

2.3.1 U-Net

Page

2.3.2 DeepLabV3

2.3.3 Mask R-CNN

2.3.4 Images Augmentation

2.4 Performance Metrics

2.5 Experimental Results and Discussion

Chapter 3. Dynamic Mode Decomposition and Deep Learning for

Postharvest Decay Prediction in Apples

3.1 Introduction

3.2 Materials and Methods

3.2.1 Dynamic Mode Decomposition

3.2.2 Samples and Data Collection

3.2.3 Experimental Testbed

3.2.4 Performance Metrics

3.3 Experimental Results and Discussion

3.3.1 DMD for Postharvest Decay Modeling

3.3.2 Mask R-CNN and Images Augmentation

3.3.3 DMD and Mask R-CNN for Postharvest Decay Prediction in Apples

3.3.4 Discussion

Chapter 4. Artificially Generated VNIR Images Segmentation for Early

Postharvest Decay Prediction in Apples

4.1 Introduction

4.2 Materials and Methods

4.2.1 Pix2Pix

4.2.2 CycleGAN

4.2.3 Pix2PixHD

4.2.4 Performance Metrics

4.2.5 Experimental Testbeds and Data Acquisition

4.2.6 Data Annotation

4.3 Results and Discussion

4.3.1 Image-to-Image Models Comparison for VNIR Images

Generation from RGB Images

Page

4.3.2 Segmentation of Generated VNIR Images for Early Postharvest Decay Detection in Apples

4.3.3 Early Postharvest Decay Detection in Stored Apples Using Generated VNIR Imaging Data on an Embedded System

4.3.4 Discussion

Conclusions

List of symbols, abbreviations

Acknowledgments

Author's publications on the disseratation topic

Bibliography

List of Figures

List of Tables

Appendix A. Appendix

Введение диссертации (часть автореферата) на тему «Оценка и прогнозирование методами машинного обучения гниения плодовых растений на раннем этапе после сбора урожая (Early Postharvest Decay Assessment and Prediction in Fruit Plants by Machine Learning Methods)»

Introduction

The growth of the human population demands the availability of high-quality food. The provision of affordable and renewable food sources has constituted a primary challenge for agriculture throughout the course of human history. The advent of computer science and remote sensing technologies has enabled the management and optimization of temporal and spatial variability in agricultural production, thereby enhancing crop performance and environmental quality. This new agricultural domain was called digital agriculture [1] which is also often referred to precision agriculture [2]. Digital agriculture involves a number of the state-of-the-art (SOTA) technologies including sensing technologies, machinery, and information systems to monitor food production and improve the sustainability of the food supply [3], [4]. There are new methods and solutions in digital and precision agriculture which are based on robotized systems [5], [6], wireless sensor networks [7], [8] Unmanned Aerial Systems and Unmanned Aerial Vehicles (UAS or UAVs) [9], [10].

Artificial intelligence (AI) and its subfields, such as machine learning (ML) and deep learning (DL) have already demonstrated their utility in a multitude of sectors, including agriculture [11] and food supply [12]. In the present day, agricultural producers may employ computer vision (CV) techniques based on AI to evaluate the quality of each plant by analyzing a considerable volume of data and parameters acquired in diverse settings. These include natural environments (such as agricultural fields) and controlled settings, such as greenhouses. The application of AI based technologies also provides novel opportunities for breeders and farmers to enhance the assessment of food quality at both the harvest and postharvest stages. These opportunities are as follows:

- The application of AI enables the automation of the process of delivering fruits and vegetables;

- AI technologies can provide more detailed information and facilitate human decision-making processes in the monitoring and assessment of fruit and vegetable quality during storage and transportation;

- The application of AI allows for the adaptation of CV methods and algorithms for intelligent embedded and distributed systems.

On the other hand, the real challenges caused by industry for adapting new solutions are:

1. The complexity of plant harvest and postharvest systems. In particular, the necessity for substantial computational resources and the associated time costs are particularly evident in the context of large harvest volumes. The challenge of implementing numerical modeling via the use of artificial intelligence is the necessity of integration across a multitude of systems and technologies, including but not limited to sensors, cameras, drones, and software. Additionally, there is a requirement for the training of personnel on the utilisation of new tools and technologies, in addition to addressing the potential resistance to change that may be encountered.

2. There are many risk factors at each stage of the postharvest system that should be considered. The occurrence of risk factors may be attributed to the utilisation of inadequate packaging, the adherence to unsuitable temperature and humidity conditions, and the transportation of incompatible loads.

The dissertation topic is relevant since plant spoilage at harvest and posthar-vest stage is significant and makes a negative impact on agricultural industry as well as food production. The relevance is also affected by the COVID-19 pandemic and challenges including insecurity, price volatility, and logistics. The implementation of artificial intelligence technologies, such as computer vision and machine learning, enables the automation of the procedure for evaluating postharvest decay areas and for predicting them at early stages. The research is aimed at implementation of new approaches based on artificial intelligence and computational technologies to ensure food safety and quality, which is an important task for the sustainable development of agriculture and the food tech industry. Harvested fruits and vegetables primarily undergo manual grading upon arrival at the distribution center. While large chain retailers use automated complexes to process substantial volumes of produce, fruit and vegetable write-offs remain quite significant. Therefore, there is a need to develop and implement new approaches and algorithms that will improve the accuracy of spoiled fruit assessment considering different types of damage.

Hence, the goal of this dissertation is to develop a computer vision based decision support system for early detection, assessment, and prediction of postharvest decay in fruits and vegetables. The proposed system integrates numerical modeling, machine learning, and embedded deployment to enable real-time quality assessment surpassing manual inspection capabilities.

The objectives of the present dissertation to achieve the aforementioned goal were the following:

1. Perform a comprehensive literature review of the state-of-the-art solutions and to identify research gaps devoted to postharvest losses evaluation in the agricultural and food technology domains. The review should concentrate on computer vision and machine learning based approaches that employ imaging data for the evaluation of stored fruits and vegetables. Collect and process datasets that contain imaging data of postharvest apple fruits of different varieties stored under various environmental conditions in order to consider postharvest decay growth and its dynamics.

2. Develop a research methodology for postharvest decay assessment in stored plant fruits using imaging data and considering various environmental conditions.

3. Develop machine learning based model that could detect and predict posthar-vest decayed zones and distinguish them from non-decayed areas in stored apples using the collected datasets.

4. Develop an approach based on numerical modeling method and computer vision algorithm for postharvest apples quality modeling and visualization and detection of decayed zones if they occur at various environmental conditions.

5. Develop an approach based on computer vision and machine learning to detect decayed and fungal areas in postharvest apples at very early stages which cannot be well seen by human experts in food distribution centers.

To achieve the aforementioned objectives, the following methods of the present research were identified in the dissertation:

- Machine learning and deep learning algorithms, particularly convolutional neural networks (CNNs) and generative adversarial networks (GANs);

- Dynamic modes decomposition (DMD) as numerical modeling method;

- Python and Bash programming languages;

- Pytorch and Tensorflow Keras frameworks, Detectron2 and PyDMD libraries;

- LogiTech 920 and SLR Canon M50 RGB cameras, SILIOS CMS-V1 multi-spectral camera, Arduino MEGA 2560 R3 platform, and NVIDIA Jetson Nano onboard computer with graphical computational capabilities.

The ensuing scientific novelty statements are presented in the dissertation:

1. A more precise detection and instance segmentation of spoiled areas in postharvest apple fruits using sequential RGB imaging data with computer vision approach based on CNN. The novel aspect of this approach is its abil-

ity to differentiate between regions exhibiting decay and those that are not, despite the presence of visual similarities in terms of form and shape.

2. Postharvest apples quality modeling based on sequential RGB imaging data, utilising DMD. The novelty covers not only the modeling of apple fruit quality but also its image visualization. Modeling and visualization of postharvest decayed areas were performed for apple fruits stored at various environmental conditions using DMD for the first time.

3. An approach for generating visible near infrared (VNIR) images of postharvest apples containing decayed and fungal areas from RGB images was developed. This approach employs image-to-image translation algorithms between RGB and VNIR images. The detection and segmentation of decayed and fungal regions in generated VNIR images of apples are conducted using a pre-trained CNN technique.

4. A computer vision based approach for RGB-to-VNIR images generation and segmentation of postharvest apples was evaluated on a powerful onboard embedded system.

The practical value of the study results became the basis for the startup project "AgroQualifier" supported by the Skolkovo Foundation. The startup project is focused on the development of software and hardware for early postharvest deterioration assessment of fruits and vegetables using AI based computer vision algorithms. For the implementation of the startup project, the company of the same name, "AgroQualifier" LLC (Skolkovo resident since 2024, PSRN 12477003865), headed by the author of the study, was established. The developed mathematical application became the basis for the created software product "AgroQualifier: program package for experiments on postharvest fruits and vegetables quality evaluation" protected by the certificate of software state registration for a program number 024683552, registered on October 14, 2024. The developed approach for data collection and processing was used for the database product "RGB images of postharvest healthy and damaged tangerines considering infrared light" protected by the certificate of database state registration for a program number 024624649, registered on October 23, 2024. The dissertation results were also presented in:

- Skolkovo Institute of Science and Technology "Modern Plant Breeding Workshop" course for MSc and PhD students in 2022, and in 2023.

- "Modern Plant Breeding Technologies" additional educational course delivered by Skoltech Project Center for Agro Technologies in 2023.

The theoretical value of the results obtained in the research consists in the introduction of a novel methodology for computer vision algorithms and numerical methods for the evaluation of postharvest damages in stored fruits and vegetables. The results offer a novel perspective on potential enhancements to quality control operations for fruits and vegetables throughout the food sorting, packaging, and transportation phases.

This dissertation submits the following propositions for defense:

1. A modified method based on computer vision algorithm with CNN technique for decay zones detection and assessment was developed, achieving 43.600 of Average Precision for decayed and 37.410 for non-decayed areas in sequential RGB images. Key innovations include: temporal feature integration, class-imbalance optimized loss function, and storage-condition-aware data augmentation.

2. A DMD-CNN hybrid method for apples fruits quality prediction was proposed, enabling image reconstruction with 68.813 of Peak Signal to Noise Ratio and 0.999 of Structural Similarity Index Measure. The method visualizes decay progression under varying storage conditions.

3. New method for predicting postharvest decayed and fungal zones in apple fruits based on image-to-image translation algorithms, in particular using generative adversarial GANs, and taking into account different illumination conditions was proposed. In this dissertation, image-to-image translation was reformulated as RGB-to-VNIR image translation. Additionally, VNIR images generated with GAN frameworks demonstrated comparable quality to the original VNIR images of stored apples, as evaluated through image quality metrics (46.859 of Peak Signal to Noise Ratio, and 0.972 of Structural Similarity Index Measure).

4. A new method based on computer vision algorithm with CNN technique for early postharvest decayed and fungal areas prediction in generated VNIR images was proposed. The method is able to distinguish between damaged and healthy postharvest apple fruits (98.350 of mean Average Precision and 94.375 of F1 score for non-damaged stored apples, and 93.997 of mean Average Precision and 94.800 of F1 score for damaged stored apples) based on the identification of decayed and fungal areas (57.562 of mean Average Precision and 58.861 of F1 for decayed areas, and 39.967 of mean Average Precision and 40.968 of F1 score for fungal areas).

The reliability and validity of the results and conclusions obtained through the methods outlined in the dissertation are in agreement with the methods and metrics currently employed by biotechnologists for the assessment of fruits and vegetables in the agricultural and food technology sectors. The suggested approaches and results have been discussed at specialized conferences, workshops and scientific seminars. The publications in leading international peer-reviewed scientific journals also confirm the validity of given results.

The author's personal contributions to the papers include the establishment of objectives, the conceptualization of ideas, the organization of data, the analysis of literature, the formulation of methodology, the collection and processing of data, the provision of experiments, the evaluation of models, the preparation of drafts, and the revision of manuscripts.

Validation of the research results. The results obtained in this dissertation were presented and discussed at the following conferences and seminars:

1. N. Stasenko, E. Chernova, D. Shadrin, G. Ovchinnikov, I. Krivolapov, M. Pukalchik. "Deep Learning for improving the storage process: Accurate and automatic segmentation of spoiled areas on apples". 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) (17-20 May, 2021, Glasgow, Scotland).

2. N. Stasenko. "Computer vision methods for apple fruits images analysis". Seminar "Current challenges in russian agro-industrial sector". (30 September, 2021, Federal Research Center "Nemchinovka", Moscow, Russia).

3. N. Stasenko, M. Savinov, V. Burlutskiy, M. Pukalchik, A. Somov. "Deep Learning for Postharvest Decay Prediction in Apples". IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society (13-16 October, 2021, Toronto, Canada).

4. N. Stasenko. "Application of machine learning methods for early posthar-vest decay and fungal infection prediction in fruits and vegetables". First Russian-Tunisian bilateral workshop "Prospects for the development of innovative plant biocontrol and biostimulation solutions" (6 July 2023, Skoltech, Moscow, Russia).

Publications. The results of the dissertation are presented in 2 journal publications published in Q1 and Q2 ranked journals and indexed in Scopus and Web of Science.

Dissertation structure. The dissertation contains an abstract, introduction, four chapters, conclusion, list of symbols, list of published papers, abbreviations, and appendix. It is written on 175 pages of typewritten text and includes a list of 307 references, 50 figures, and 24 tables.

Заключение диссертации по теме «Другие cпециальности», Стасенко Никита Андреевич

Conclusions

This dissertation presents new computer vision approaches based on numerical methods and deep learning methods for more precisely assessment and prediction of spoiled zones in postharvset fruit plants in order to save their healing properties for consumer.

The detailed literature review was performed. It presents and describes SOTA computer vision approaches based on artificial intelligence for fruits and vegetables quality control at harvest and postharvest stages. Furthermore, the review identifies the most crucial factors and demonstrates the use of wireless technologies and different embedded systems in agriculture and food production for the early detection of postharvest losses, employing RGB and NIR imaging techniques. The review of the literature, an analysis of existing datasets, and an evaluation of current SOTA solutions have demonstrated the necessity for the development of advanced computer vision algorithms based on artificial intelligence for the assessment of postharvest losses in a range of environmental conditions. The primary stages of data acquisition, pre-processing, and processing for the resolution of the aforementioned problem were illustrated. The number of unique datasets containing sequential RGB and VNIR images were collected and processed as part of the dissertation.

The computer vision approach based on deep learning technique for postharvest decayed zones detection and segmentation to improve quality control of stored apples fruits was firstly suggested and presented. Several deep learning models based on SOTA convolutional neural networks frameworks were selected and compared between each other to distinguish decayed and non-decayed zones in postharvest apples. The models were trained and validated on a dataset comprising 4440 sequential RGB images of eleven postharvest apples stored in a single location. The optimal model was constructed using the Mask R-CNN architecture, demonstrating remarkable performance in the detection and segmentation of postharvest apple fruits in images. It achieved an 98.810 Average Precision (AP) for the detection of apple fruits themselves, along with 43.600 AP for the identification of decayed areas and 37.410 AP for the distinction between decayed and non-decayed zones.

The proposed methodology for postharvest apple fruits quality modeling and visualization (reconstruction) with the Dynamic Mode Decomposition method, taking into account different environmental conditions, was initially demonstrated. The com-

parison of DMD reconstructed images with real RGB images showed that the DMD images demonstrated high quality in terms of several widely used image quality metrics, including peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM). The DMD images achieved PSNR values between 47.405 and 68.813, SSIM values between 0.983 and 0.999, and FSIM values between 0.528 and 0.714. The proposed methodology also includes deep learning technique based on CNN for postharvest decayed zones detection in stored apples using DMD reconstructed images. It also incorporates a Mask R-CNN model as CNN technique for the detection of postharvest decay in stored apples, utilizing DMD reconstructed images. For stored apples, the use of DMD reconstructed images and the implementation of Mask R-CNN resulted in the segmentation and prediction of postharvest decayed zones under extremely environmental conditions, with an AP of 75.550, and AP of 83.809 within the recommended temperature and humidity regimes.

The approach including the combination of image-to-image translation algorithms based on generative adversarial networks (GANs) and CNN technique for early postharvest decayed and fungal zones prediction in stored apple fruits was firstly proposed and demonstrated. Several SOTA image-to-image translation algorithms based on GANs for RGB-to-VNIR translation task on dataset containing 1305 paired RGB and VNIR images of postharvest apples. The VNIR images generated by the Pix2PixHD model exhibited the highest degree of quality when compared to authentic VNIR images, as assessed through the use of PSNR and SSIM metrics. The Pix2PixHD model demonstrated a PSNR of 46.859, and an SSIM of 0.972, respectively.

The computer vision algorithm utilising Mask R-CNN model as CNN technique for the detection and prediction of early decayed and fungal zones in postharvest apples was presented. Mask R-CNN model was trained on a dataset comprising 1029 sequential visible and near-infrared (VNIR) images of stored apples. The algorithm demonstrated a mean Average Precision (mAP) of 57.562 and an F1 score of 58.861 for the segmentation of decayed zones. For the segmentation of fungal zones in stored apples, the algorithm exhibited a mean Average Precision of 39.967 and an F1 score of 40.968. The presence of fungal and decayed zones, as identified by the algorithm, was proposed as a criterion for differentiating between damaged and non-damaged apples. The algorithm achieved an mAP of 93.997% and an F1 score of 94.800 for damaged apples and an mAP of 98.350 and an F1 score of 94.375 for non-damaged apples.

The proposed approach based on GAN and CNN techniques for early postharvest decayed and fungal zones assessment in stored apples was implemented on embedded

system with AI capabilities. The NVIDIA Jetson Nano onboard computer was utilized as an embedded system, and the approach was validated on a dataset consisting of 456 RGB images of postharvest apples. The Pix2iPxHD model generated 100 images with an average rate of 17 frames per second (FPS), while the Mask R-CNN model detected and segmented images at an average FPS of 0.420.

The aforementioned results of the dissertation have significant implications for the implementation of mathematical modeling and AI based algorithms for food quality assessment. The results of current research achievements can serve as a basement for future research directions. In particular, the field of AI is undergoing rapid and significant developments. As an illustration, an enhancement can be made to the proposed approach for generating VNIR images through the implementation of diffusion models and large language models as image-to-image translation algorithms. Moreover, research into video stream processing and individual fruits and vegetables tracking using the state-of-the-art CNN based models is of particular interest. Second, it is important to continue the collection of imaging data in accordance with the proposed approaches. This data should then be scaled to other plant fruits in order to assess and predict posthar-vest losses, in response to the demands of retail and food technology companies.

Список литературы диссертационного исследования кандидат наук Стасенко Никита Андреевич, 2026 год

Bibliography

1. Klerkx, L. A review of social science on digital agriculture, smart farming and agriculture 4.0: New contributions and a future research agenda / L. Klerkx, E. Jakku, P. Labarthe // NJAS-Wageningen Journal of Life Sciences. 2019. Vol.90. P. 100315.

2. Pierce, F. /.Aspects of precision agriculture / F. J. Pierce, P. Nowak // Advances in agronomy. 1999. Vol.67. P. 185.

3. Cisternas, I. Systematic literature review of implementations of precision agriculture / I. Cisternas, I. Velasquez, A. Caro // Computers and Electronics in Agriculture. 2020. Vol. 176. P. 105626.

4. Gebbers, R. Precision agriculture and food security / R. Gebbers, V. I. Adam-chuk//Science. 2010. Vol. 327, no. 5967. P. 828831.

5. Schor, ^.Development of a robotic detection system for greenhouse pepper plant diseases / N. Schor, S. Berman, A. Dombrovsky // Precision agriculture. 2017. Vol. 18, no. 3. P. 394409.

6. Atefi, A. In vivo human-like robotic phenotyping of leaf traits in maize and sorghum in greenhouse / A. Atefi, Y. Ge, S. Pitla // Computers and Electronics in Agriculture. 2019. Vol. 163. P. 104854.

7. Spachos, P. Integration of wireless sensor networks and smart uavs for precision viticulture / P. Spachos, S. Gregori // IEEE Internet Computing. 2019. Vol. 23, no. 3. P. 816.

8. Cama-Pinto, D. Path loss determination using linear and cubic regression inside a classic tomato greenhouse / D. Cama-Pinto, M. Damas, J. A. Holgado-Terriza// International journal of environmental research and public health. 2019. Vol. 16, no. 10. P. 1744.

9. Kim, /.Unmanned aerial vehicles in agriculture: A review of perspective of platform, control, and applications / J. Kim, S. Kim, C. Ju // IEEE Access. 2019. Vol. 7. P. 105100105115.

10. Menshchikov, A. Real-Time Detection of Hogweed: UAV Platform Empowered by Deep Learning / A. Menshchikov, D. Shadrin, A. Somov // IEEE Transactions on Computers. 2021. Vol. 70, no. 8. P. 11751188.

11. Ben Ayed, R. Artificial intelligence to improve the food and agriculture sector / R. Ben Ayed, M. Hanana // Journal of Food Quality. 2021. Vol. 2021, no. 1. P. 5584754.

12. Misra, N.IoT, big data, and artificial intelligence in agriculture and food industry / N. Misra, Y. Dixit, A. Martynenko // IEEE Internet of things Journal. 2020. Vol. 9, no. 9. P. 63056324.

13. FAOSTAT data about global food production. URL: https://www. fao.org/ aquastat/statistics/query/results.html ; visited on 2024-05-20.

14. Wing, I. S. Global vulnerability of crop yields to climate change /1. S. Wing, E. De Cian, M. N. Mistry // Journal of Environmental Economics and Management. 2021. Vol. 109. P. 102462.

15. Adnan, ^.The effects of knowledge transfer on farmers decision making toward sustainable agriculture practices: In view of green fertilizer technology / N. Adnan, S. M. Nordin, A. Noor // World Journal of Science, Technology and Sustainable Development. 2018. Vol. 15, no. 1. P. 98115.

16. Horng, G.-J. The smart image recognition mechanism for crop harvesting system in intelligent agriculture / G.-J. Horng, M.-X. Liu, C.-C. Chen // IEEE Sensors Journal. 2019. Vol. 20, no. 5. P. 27662781.

17. Kupriyanovsky, V. Agriculture 4.0: Synergy of the System of Systems, Ontology, the Internet of Things, and Space Technologies / V. Kupriyanovsky, Y. Lipuntsov, D. Namiot // International Journal of Open Information Technologies. 2018. Vol. 6, no. 10. P. 4667.

18. Stafford, J. V. Implementing precision agriculture in the 21st century / J. V. Stafford // Journal of Agricultural Engineering Research. 2000. Vol. 76, no. 3. P. 267275.

19. FAOSTAT data about world apple production. URL: https : //www. fao. org/ faostat/en/ ; visited on 2024-06-01.

20. Sambo, P. Hydroponic solutions for soilless production systems: issues and opportunities in a smart agriculture perspective / P. Sambo, C. Nicoletto, S. As-tolfi//Frontiers in plant science. 2019. Vol.10. P. 923.

21. Ayodele, T. O. Machine learning overview / T. O. Ayodele // New Advances in Machine Learning. 2010. Vol.2. P. 918.

22. Демидчик, В. Феномика растений: фундаментальные основы, программно-аппаратные платформы и методы машинного обучения / В. Демидчик, А. Шашко, и. д. Бондаренко // Физиология растений. 2020. 3 (67). P. 227245.

23. Zhou, H. An integrated WSN and mobile robot system for agriculture and environment applications / H. Zhou, H. Qi, T. Low // International Conference on Mobile and Ubiquitous Systems: Computing, Networking, and Services. Springer. 2013. P. 3036.

24. Kant, U. Internet of Things and Artificial Intelligence / U. Kant, M. Singh, V. M. Srivastava // From Visual Surveillance to Internet of Things: Technology and Applications. 2019. P. 111.

25. Sankaran, S. Low-altitude, high-resolution aerial imaging systems for row and field crop phenotyping: A review / S. Sankaran, L. R. Khot, N. R. Knowles // European Journal of Agronomy. 2015. Vol.70. P. 112123.

26. Молин, А. Е. Методы генерации синтетических данных для обучения нейросетей в задаче сегментации уровня азотного режима растений на снимках БПЛА с/х поля / А. Е. Молин, Е. П. Митрофанов, О. А. Митрофанова // Вестник Санкт-Петербургского университета. Прикладная математика. Информатика. Процессы управления. 2024. 1 (20). P. 2033.

27. Rizk, H. Robotized Early Plant Health Monitoring System / H. Rizk, M. K. Habib // IECON 2018-44th Annual Conference of the IEEE Industrial Electronics Society. IEEE. 2018. P. 37953800.

28. Zhang, / Monitoring plant diseases and pests through remote sensing technology: A review / J. Zhang, Y. Huang, R. Pu // Computers and Electronics in Agriculture. 2019. Vol. 165. P. 104943.

29. Pinho, T. M. An Overview on Visual Sensing for Automatic Control on Smart Farming and Forest Management / T. M. Pinho, J. Oliveira //2018 13th APCA International Conference on Automatic Control and Soft Computing (CONTROLO). IEEE. 2018. P. 419424.

30. Weiss, M. Remote sensing for agricultural applications: A meta-review / M. Weiss, F. Jacob, G. Duveiller // Remote Sensing of Environment. 2020. Vol.236. P. 111402.

31. Hassler, S. C. Unmanned Aircraft System (UAS) Technology and Applications in Agriculture / S. C. Hassler, F. Baysal-Gurel // Agronomy. 2019. Vol. 9, no. 10. P. 618.

32. Shakoor, N.High throughput phenotyping to accelerate crop breeding and monitoring of diseases in the field / N. Shakoor, S. Lee, T. C. Mockler // Current opinion in plant biology. 2017. Vol.38. P. 184192.

33. O'Donoghue, T. Digital Regenerative Agriculture / T. O'Donoghue, B. Minasny, A. McBratney // npj Sustainable Agriculture. 2024. Vol. 2, no. 1. P. 5.

34. Kourou, K. Machine learning applications in cancer prognosis and prediction / K. Kourou, K. P. Exarchos, D. I. Fotiadis // Computational and structural biotechnology journal. 2015. Vol. 13. P. 817.

35. Jang, H.-J.Applications of deep learning for the analysis of medical data / H.-J. Jang, K.-O. Cho // Archives of pharmacal research. 2019. Vol. 42, no. 6. P. 492504.

36. Ferreira, A. C. Deep learning-based methods for individual recognition in small birds / A. C. Ferreira, L. R. Silva, C. Doutrelant // Methods in Ecology and Evolution. 2020. Vol. 11, no. 9. P. 10721085.

37. Tabak, M. A. Machine learning to classify animal species in camera trap images: applications in ecology / M. A. Tabak // Methods in Ecology and Evolution. 2019. Vol. 10, no. 4. P. 585590.

38. Lucas, L. Machine learning for spacecraft operations support-The Mars Express power challenge / L. Lucas, R. Boumghar // 2017 6th International Conference on Space mission challenges for information technology (SMC-IT). IEEE. 2017. P. 8287.

39. Krizhevsky, A. Imagenet classification with deep convolutional neural networks / A. Krizhevsky, I. Sutskever, G. E. Hinton // Communications of the ACM. 2017. Vol. 60, no. 6. P. 8490.

40. Zhang, Z. Wheat lodging detection from UAS imagery using machine learning algorithms / Z. Zhang, P. Flores, J. K. Ransom // Remote Sensing. 2020. Vol. 12, no. 11. P. 1838.

41. Ofori, M. Towards deep learning for weed detection: Deep convolutional neural network architectures for plant seedling classification / M. Ofori, O. F. El-Gayar. 2020.

42. Gutiérrez, S. Deep learning for the differentiation of downy mildew and spider mite in grapevine under field conditions / S. Gutiérrez, I. Hernández, J. Tardaguila // Computers and Electronics in Agriculture. 2021. Vol. 182. P. 105991.

43. Dias, P. A. Apple flower detection using deep convolutional networks / P. A. Dias, A. Tabb, H. Medeiros // Computers in Industry. 2018. Vol. 99. P. 1728.

44. Bargoti, S. Image segmentation for fruit detection and yield estimation in apple orchards / S. Bargoti, J. P. Underwood// Journal of Field Robotics. 2017. Vol. 34, no. 6. P. 10391060.

45. Tian, Y. Detection of apple lesions in orchards based on deep learning methods of cyclegan and yolov3-dense / Y. Tian, G. Yang, Z. Liang // Journal of Sensors. 2019. Vol.2019.

46. Valdez, P. Apple Defect Detection Using Deep Learning Based Object Detection For Better Post Harvest Handling / P. Valdez. 2020. arXiv: 2005.06089. URL: https://arxiv.org/abs/2005.06089 ; visited on 2021-09-09.

47. Jana, S. Automatic fruit recognition from natural images using color and texture features / S. Jana, S. Basak, R. Parekh // 2017 Devices for Integrated Circuit (DevIC). IEEE. 2017. P. 620624.

48. Bhargava, A. Automatic Detection and Grading of Multiple Fruits by Machine Learning / A. Bhargava, A. Bansal // Food Analytical Methods. 2020. Vol. 13, no. 3. P. 751761.

49. Wang, A. A review on weed detection using ground-based machine vision and image processing techniques / A. Wang, W. Zhang, X. Wei // Computers and electronics in agriculture. 2019. Vol.158. P. 226240.

50. Patricio, D. I. Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review / D. I. Patricio, R. Rieder // Computers and electronics in agriculture. 2018. Vol.153. P. 6981.

51. Mochida, K. Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective / K. Mochida, K. Inoue, F. Melgani // GigaScience. 2019. Vol. 8, no. 1. giy153.

52. Chouhan, S. S. Applications of computer vision in plant pathology: a survey / S. S. Chouhan, U. P. Singh, S. Jain // Archives of computational methods in engineering. 2020. Vol. 27, no. 2. P. 611632.

53. Paturkar, A. Overview of image-based 3D vision systems for agricultural applications / A. Paturkar, G. S. Gupta, D. Bailey //2017 International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE. 2017. P. 16.

54. Cubero, S. Automated systems based on machine vision for inspecting citrus fruits from the field to postharvest—a review / S. Cubero, W. S. Lee, J. Blasco // Food and Bioprocess Technology. 2016. Vol. 9, no. 10. P. 16231639.

55. Blum, A. L. Selection of relevant features and examples in machine learning / A. L. Blum, P. Langley // Artificial intelligence. 1997. Vol. 97, no. 1/ 2. P. 245271.

56. Behmann, J. A review of advanced machine learning methods for the detection of biotic stress in precision crop protection / J. Behmann, A.-K. Mahlein, L. Plumer//Precision Agriculture. 2015. Vol. 16, no. 3. P. 239260.

57. Elavarasan, D. Forecasting yield by integrating agrarian factors and machine learning models: A survey / D. Elavarasan, A. Y. Zomaya, K. Srinivasan // Computers and electronics in agriculture. 2018. Vol.155. P. 257282.

58. Verma, S. Prediction models for identification and diagnosis of tomato plant diseases / S. Verma, A. Chug, A. P. Singh // 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE. 2018. P. 15571563.

59. Chlingaryan, A. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review / A. Chlingaryan, S. Sukkarieh, B. Whelan // Computers and electronics in agriculture. 2018. Vol. 151. P. 6169.

60. Rehman, T. U. Current and future applications of statistical machine learning algorithms for agricultural machine vision systems / T. U. Rehman, M. S. Mahmud, J. Shin // Computers and electronics in agriculture. 2019. Vol. 156. P. 585605.

61. Sharma, R. A systematic literature review on machine learning applications for sustainable agriculture supply chain performance / R. Sharma, V. Kumar, A. Ku-mar//Computers & Operations Research. 2020. P. 104926.

62. Mekonnen, Y. Machine Learning Techniques in Wireless Sensor Network Based Precision Agriculture / Y. Mekonnen, S. Namuduri, S. Bhansali // Journal of The Electrochemical Society. 2020. Vol. 167, no. 3. P. 037522.

63. Bourne, M. Postharvest food losses—The neglected dimension in increasing the world food supply. Cornell Inst: tech. rep. / M. Bourne ; Agr. Mimeo 53. New York State College Agr. Life Sci., Cornell Univ., Ithaca. 1977.

64. Prange, R. Pre-harvest, harvest and post-harvest strategies for organic production of fruits and vegetables / R. Prange // XXVIII International Horticultural Congress on Science and Horticulture for People (IHC2010): International Symposium on 933. 2010. P. 4350.

65. Silva, R N.Trichoderma/pathogen/plant interaction in pre-harvest food security / R. N. Silva, V. N. Monteiro, C. J. Ulhoa // Fungal biology. 2019. Vol. 123, no. 8. P. 565583.

66. Mitra, D. Emerging plant diseases: Research status and challenges / D. Mitra // Emerging Trends in Plant Pathology. 2021. P. 117.

67. Elik, A. Strategies to reduce post-harvest losses for fruits and vegetables / A. Elik,

D. K. Yanik, F. Gogus // Strategies. 2019. Vol. 5, no. 3. P. 2939.

68. Меделяева, А. Ю. Средняя масса и биохимические показатели яблок при хранении в условиях обычной и регулируемой атмосфер / А. Ю. Меделяева, С. А. Брюхина, Ю. В. Трунов // Совет научных редакторов. 2024. 1 (76). P. 3539.

69. Astacio, J. D. Monilinia fructicola Response to White Light / J. D. Astacio,

E. A. Espeso, A. De Cal // Journal of Fungi. 2023. Vol. 9, no. 10. P. 988.

70. Хоконова, М. Пути повышения лежко сти яблок и груш / М. Хоконова // Биология в сельском хозяйстве. 2021. 3 (32). P. 3538.

71. Betchem, G. The application of chitosan in the control of post-harvest diseases: A review / G. Betchem, N. A. N. Johnson, Y. Wang // Journal of Plant Diseases and Protection. 2019. Vol. 126, no. 6. P. 495507.

72. Chen, Y. Exogenous melatonin attenuates post-harvest decay by increasing antioxidant activity in wax apple (Syzygium samarangense) / Y. Chen, Y. Zhang, Z. Li // Frontiers in plant science. 2020. P. 1411.

73. Kabelitz, T. Effects of hot water dipping on apple heat transfer and post-harvest fruit quality / T. Kabelitz, B. Schmidt, K. Hassenberg // LWT. 2019. Vol. 108. P. 416420.

74. Jain, C. Post-harvest processing of custard apple (Annona squamosa L.): A review / C. Jain, P. Champawat, S. Jain// International Journal of Chemical Studies. 2019. Vol. 7, no. 3. P. 16321637.

75. Fatchurrahman, D. Early discrimination of mature-and immature-green tomatoes (Solanum lycopersicum L.) using fluorescence imaging method / D. Fatchurrahman, M. M. A. Chaudhry, G. Colelli // Postharvest Biology and Technology. 2020. Vol. 169. P. 111287.

76. Jiang, Q. Application of ultrasonic technology in postharvested fruits and vegetables storage: A review / Q. Jiang, M. Zhang, B. Xu // Ultrasonics Sono-chemistry. 2020. Vol. 69. P. 105261.

77. Malvandi, A. Application of NIR spectroscopy and multivariate analysis for Non-destructive evaluation of apple moisture content during ultrasonic drying / A. Malvandi, H. Feng, M. Kamruzzaman// Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2022. Vol.269. P. 120733.

78. Raju, R Wireless passive sensors for food quality monitoring: Improving the safety of food products / R. Raju, G. E. Bridges, S. Bhadra // IEEE antennas and propagation magazine. 2020. Vol. 62, no. 5. P. 7689.

79. Pullanagari, R. R. Uncertainty assessment for firmness and total soluble solids of sweet cherries using hyperspectral imaging and multivariate statistics / R. R. Pullanagari, M. Li//Journal of Food Engineering. 2021. Vol.289. P. 110177.

80. Ghosh, A. Development of Electronic Nose for early spoilage detection of potato and onion during post-harvest storage / A. Ghosh, T. K. Ghosh, S. Tiwari // Journal of Materials NanoScience. 2022. Vol. 9, no. 2. P. 101114.

81. Morales-Cedeno, L. R. Plant growth-promoting bacterial endophytes as biocontrol agents of pre-and post-harvest diseases: Fundamentals, methods of application and future perspectives / L. R. Morales-Cedeno, M. del Carmen Orozco-Mosqueda, G. Santoyo // Microbiological Research. 2021. Vol.242. P. 126612.

82. Sharafudeen, M. FruitNet and FruitBox Dataset / M. Sharafudeen, V. Chandra. 2023. URL: https://www.kaggle.com/datasets/mirlab/annotated-fruitnet-and-fruitbox ; visited on 2024-05-17.

83. Kalluri, S. R. Fruits fresh and rotten for classification / S. R. Kalluri. 2018. URL: https : / / www. kaggle. com / datasets / sriramr / fruits - fresh - and - rotten - for -classification/data ; visited on 2024-05-20.

84. Karn, S. Spot detection Dataset : Open Source Dataset / S. Karn. 01/2024. visited on 2024-05-20. https : //universe. roboflow. com/shubham- karn-jb3zo/spot_ detection-0kcew.

85. Infected Apple Dataset : Open Source Dataset. 05/2024. visited on 2024-05-17. https://universe.roboflow.com/capstone-ja85u/infected- apple.

86. Anthracnoseapple Disease Dataset : Open Source Dataset. 01/2024. visited on 2024-05-17. https : / / universe . roboflow . com / apple - disease - srevu / anthracnoseapple-disease.

87. Whiterot Dataset : Open Source Dataset. 11/2023. visited on 2024-05-17. https: //universe.roboflow.com/apple-disease-srevu/whiterot-rtl8f.

88. Apple-Disease-Detection Dataset : Open Source Dataset. 05/2023. visited on 2024-05-17. https://universe.roboflow.com/pfe-o6ixg/apple-disease-detection-fqwzp.

89. Apple Disease Classification Dataset : Open Source Dataset. 03/2023. visited on 2024-05-20. https : / / universe. roboflow. com / cv1 - bfpzp / apple - disease -classification-ppc5r.

90. Shan, K. Apple Fruit Disease / K. Shan. 2021. URL: https://www.kaggle.com/ datasets/kaivalyashah/apple-disease-detection/data ; visited on 2024-05-17.

91. Dataset: Region Aggregated Attention CNN for Disease Detection in Fruit Images. 2021. URL: https://github.com/QuIIL/Dataset-Region-Aggregated-Attention-CNN-for-Disease-Detection-in-Fruit-Images ; visited on 2024-0517.

92. Apple Scab Dataset : Open Source Dataset. 11/2023. visited on 2024-05-17. https://universe.roboflow.com/apple- disease- srevu/apple- scab- xxpgy.

93. Apple disease: Full Dataset : Open Source Dataset. 11/2023. visited on 202405-20. https://universe.roboflow.com/gffgg/apple_disease_full.

94. Goodfellow, I. Generative adversarial nets / I. Goodfellow, J. Pouget-Abadie, Y. Bengio // Advances in neural information processing systems. 2014. P. 26722680.

95. Mirza, M. Conditional generative adversarial nets / M. Mirza, S. Osin-dero. 2014. arXiv: 1411. 1784 [cs.LG]. URL: https ://arxiv. org/abs/ 1411.1784 ; visited on 2021-08-10.

96. Illarionova, S. Generation of the nir spectral band for satellite images with convolutional neural networks / S. Illarionova, D. Shadrin, I. Oseledets // Sensors. 2021. Vol. 21, no. 16. P. 5646.

97. Lu, Y. Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review / Y. Lu, D. Chen, Y. Huang // Computers and Electronics in Agriculture. 2022. Vol.200. P. 107208.

98. Khatri, K. Detection of Animals in Thermal Imagery for Surveillance using GAN and Object Detection Framework / K. Khatri, C. Asha, J. M. D'Souza // 2022 International Conference for Advancement in Technology (ICONAT). IEEE. 2022. P. 16.

99. Valerio Giuffrida, M. Arigan: Synthetic arabidopsis plants using generative adversarial network / M. Valerio Giuffrida, H. Scharr, S. A. Tsaftaris // Proceedings of the IEEE international conference on computer vision workshops. 2017. P. 20642071.

100. Tang, H. Multi-channel attention selection gans for guided image-to-image translation/H. Tang, J. J. Corso, N. Sebe. 2020. arXiv: 2002.01048. URL: https: //arxiv.org/abs/2002.01048 ; visited on 2021-08-10.

101. Guo, Z. Image-to-image translation using an offset-based multi-scale codes GAN encoder / Z. Guo, M. Shao, S. Li // The Visual Computer. 2023. P. 117.

102. Fard, A. S. From CNNs to GANs for cross-modality medical image estimation / A. S. Fard, D. C. Reutens, V. Vegh // Computers in Biology and Medicine. 2022. P. 105556.

103. Saharia, C. Palette: Image-to-image diffusion models / C. Saharia, W. Chan, M. Norouzi // ACM SIGGRAPH 2022 Conference Proceedings. 2022. P. 110.

104. Kshatriya, B. S. Semantic Map Injected GAN Training for Image-to-Image Translation / B. S. Kshatriya, S. R. Dubey, S. Manchanda // Proceedings of the Satellite Workshops of ICVGIP 2021. Springer. 2022. P. 235249.

105. Sa, I. deepNIR: Datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques /1. Sa, J. Y. Lim, B. MacDon-ald//Sensors. 2022. Vol. 22, no. 13. P. 4721.

106. Dimensions Data base. URL: https://www.dimensions.ai/; visited on 2020-0202.

107. Web of Sceince Data base. URL: https://www.webofknowledge.com/; visited on 2020-02-02.

108. Scopus Data base. URL: https://www.scopus.com/ ; visited on 2020-02-02.

109. eLibrary Data base. URL: https://elibrary.ru/; visited on 2020-02-02.

110. Fan, K.-J. Applications of Fluorescence Spectroscopy, RGB-and MultiSpec-tral Imaging for Quality Determinations of White Meat: A Review / K.-J. Fan, W.-H. Su//Biosensors. 2022. Vol. 12, no. 2. P. 76.

111. Zou, X. Pixel-level Bayer-type colour router based on metasurfaces / X. Zou,

G. Gong, Z. Wang//Nature Communications. 2022. Vol. 13, no. 1. P. 3288.

112. Rivero Mesa, A. Non-invasive grading system for banana tiers using RGB imaging and deep learning / A. Rivero Mesa, J. Chiang // 2021 7th International Conference on Computing and Artificial Intelligence. 2021. P. 113118.

113. Nasiri, A. Image-based deep learning automated sorting of date fruit / A. Nasiri, A. Taheri-Garavand, Y.-D. Zhang // Postharvest biology and technology. 2019. Vol. 153. P. 133141.

114. Yalcin, H. Plant phenology recognition using deep learning: Deep-Pheno /

H. Yalcin //2017 6th International Conference on Agro-Geoinformatics. IEEE. 2017. P. 15.

115. Ghosal, S. An explainable deep machine vision framework for plant stress phe-notyping / S. Ghosal, D. Blystone, S. Sarkar // Proceedings of the National Academy of Sciences. 2018. Vol. 115, no. 18. P. 46134618.

116. Silver, D. L. In Vino Veritas: Estimating Vineyard Grape Yield from Images Using Deep Learning / D. L. Silver, T. Monga // Canadian Conference on Artificial Intelligence. Springer 2019. P. 212224.

117. Bresilla, K. Single-shot convolution neural networks for real-time fruit detection within the tree / K. Bresilla, G. D. Perulli, L. Manfrini // Frontiers in plant science. 2019. Vol. 10. P. 611.

118. Redmon, J. You only look once: Unified, real-time object detection / J. Redmon, S. Divvala, A. Farhadi // Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. P. 779788.

119. Huang, J. Speed/accuracy trade-offs for modern convolutional object detectors / J. Huang, V. Rathod, S. Guadarrama // Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. P. 73107311.

120. Wu, F. Rachis detection and three-dimensional localization of cut off point for vision-based banana robot / F. Wu, J. Duan, X. Zou // Computers and Electronics in Agriculture. 2022. Vol. 198. P. 107079.

121. Baheti, B. Semantic scene segmentation in unstructured environment with modified DeepLabV3+ / B. Baheti, S. Innani, S. Talbar // Pattern Recognition Letters. 2020. Vol. 138. P. 223229.

122. Santos, T. T. Grape detection, segmentation, and tracking using deep neural networks and three-dimensional association / T. T. Santos, L. L. de Souza, S. Avila// Computers and Electronics in Agriculture. 2020. Vol. 170. P. 105247.

123. He, K. Mask r-cnn / K. He, R. Girshick. 2020. arXiv: 1703 . 06870. URL: https://arxiv.org/abs/1703.06870 ; visited on 2021-08-10.

124. SpikeSegNet-a deep learning approach utilizing encoder-decoder network with hourglass for spike segmentation and counting in wheat plant from visual imaging / T. Misra [et al.]//Plant methods. 2020. Vol. 16, no. 1. P. 120.

125. Veeramani, B. DeepSort: deep convolutional networks for sorting haploid maize seeds / B. Veeramani, J. W. Raymond, P. Chanda // BMC bioinformat-ics. 2018. Vol. 19, no. 9. P. 289.

126. Li, Y. DeepCotton: in-field cotton segmentation using deep fully convolu-tional network / Y. Li, Z. Cao, A. B. Cremers // Journal of Electronic Imaging. 2017. Vol. 26, no. 5. P. 053028.

127. Achanta, R. SLIC superpixels compared to state-of-the-art superpixel methods / R. Achanta, K. Smith, S. Susstrunk // IEEE transactions on pattern analysis and machine intelligence. 2012. Vol. 34, no. 11. P. 22742282.

128. Viola, P. Robust real-time face detection / P. Viola, M. J. Jones // International journal of computer vision. 2004. Vol. 57, no. 2. P. 137154.

129. Yahata, S. A hybrid machine learning approach to automatic plant phenotyping for smart agriculture / S. Yahata, T. Onishi, H. Tsuji // 2017 International Joint Conference on Neural Networks (IJCNN). IEEE. 2017. P. 17871793.

130. Espejo-Garcia, B. Towards weeds identification assistance through transfer learning / B. Espejo-Garcia, L. Athanasakos, I. Vasilakoglou // Computers and Electronics in Agriculture. 2020. Vol. 171. P. 105306.

131. Dias, P. A. Multispecies fruit flower detection using a refined semantic segmentation network / P. A. Dias, A. Tabb, H. Medeiros // IEEE Robotics and Automation Letters. 2018. Vol. 3, no. 4. P. 30033010.

132. Chen, L.-C. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs / L.-C. Chen, G. Papandreou, A. L. Yuille // IEEE transactions on pattern analysis and machine intelligence. 2017. Vol. 40, no. 4. P. 834848.

133. Dias, P. A. Semantic segmentation refinement by Monte Carlo region growing of high confidence detections / P. A. Dias, H. Medeiros // Asian Conference on Computer Vision. Springer. 2018. P. 131146.

134. Do, D. Machine learning techniques for the assessment of citrus plant health using UAV-based digital images / D. Do, F. Pham, S. Bhandari // Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping III. Vol. 10664. International Society for Optics, Photonics. 2018. 1066400.

135. Sabzi, S. Machine vision system for the automatic segmentation of plants under different lighting conditions / S. Sabzi, Y. Abbaspour-Gilandeh, H. Javadikia // Biosystems Engineering. 2017. Vol. 161. P. 157173.

136. Sabzi, S. Designing a Fruit Identification Algorithm in Orchard Conditions to Develop Robots Using Video Processing and Majority Voting Based on Hybrid Artificial Neural Network / S. Sabzi, R. Pourdarbani, T. Panagopoulos // Applied Sciences. 2020. Vol. 10, no. 1. P. 383.

137. Lee, K. S. A new meta-heuristic algorithm for continuous engineering optimization: harmony search theory and practice / K. S. Lee, Z. W. Geem // Computer methods in applied mechanics and engineering. 2005. Vol. 194, no. 3638. P. 39023933.

138. Hussein, W. A. A fast scheme for multilevel thresholding based on a modified bees algorithm / W. A. Hussein, S. Sahran, S. N. H. S. Abdullah // Knowledge-Based Systems. 2016. Vol. 101. P. 114134.

139. Simon, D. Biogeography-based optimization / D. Simon // IEEE transactions on evolutionary computation. 2008. Vol. 12, no. 6. P. 702713.

140. Rodríguez-Gómez, J. P. Mapping Infected Crops Through UAV Inspection: The Sunflower Downy Mildew Parasite Case / J. P. Rodríguez-Gómez, M. Di Ci-cco, D. Nardi // International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems. Springer. 2019. P. 495503.

141. Sadeghi-Tehran, P. Automated method to determine two critical growth stages of wheat: heading and flowering / P. Sadeghi-Tehran, K. Sabermanesh, M. J. Hawkesford//Frontiers in Plant Science. 2017. Vol. 8. P. 252.

142. Le, V. N. T. A novel method for detecting morphologically similar crops and weeds based on the combination of contour masks and filtered Local Binary Pattern operators / V. N. T. Le, S. Ahderom, K. Alameh // Giga-Science. 2020. Vol. 9, no. 3. giaa017.

143. Conliu, §. Improving remote sensing crop classification by argumentation-based conflict resolution in ensemble learning / §. Confiu, A. Groza // Expert Systems with Applications. 2016. Vol.64. P. 269286.

144. Zermas, D. Automation solutions for the evaluation of plant health in corn fields / D. Zermas, D. Teng, N. Papanikolopoulos //2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE. 2015. P. 65216527.

145. Heim, R. Detecting myrtle rust (Austropuccinia psidii) on lemon myrtle trees using spectral signatures and machine learning / R. Heim, I. Wright, J. Oldeland // Plant Pathology. 2018. Vol. 67, no. 5. P. 11141121.

146. Choi, D. Detection of dropped citrus fruit on the ground and evaluation of decay stages in varying illumination conditions / D. Choi, W. S. Lee, F. Roka // Computers and Electronics in Agriculture. 2016. Vol. 127. P. 109119.

147. Nan, L. Crop positioning for robotic intra-row weeding based on machine vision / L. Nan, C. Ziwen, Z. Junxiong // International Journal of Agricultural and Biological Engineering. 2015. Vol. 8, no. 6. P. 2029.

148. Montalvo, M. Identification of plant textures in agricultural images by principal component analysis / M. Montalvo, M. Guijarro, Á. Ribeiro // International Conference on Hybrid Artificial Intelligence Systems. Springer. 2016. P. 391401.

149. Нитяговский, Н. Н. Учредители: Дальневосточное отделение РАН, Центральная научная библиотека ДВО РАН / Н. Н. Нитяговский, А. П. Тюнин, Н. М. Санина // Вестник Дальневосточного отделения Российской академии наук.. No. 5. P. 516.

150. Singh, U. P. Multilayer convolution neural network for the classification of mango leaves infected by anthracnose disease / U. P. Singh, S. S. Chouhan, S. Jain//IEEE Access. 2019. Vol.7. P. 4372143729.

151. Karlekar, A. SoyNet: Soybean leaf diseases classification / A. Karlekar, A. Seal // Computers and Electronics in Agriculture. 2020. Vol. 172. P. 105342.

152. Arsenovic, M. Solving current limitations of deep learning based approaches for plant disease detection / M. Arsenovic, M. Karanovic, D. Stefanovic // Symmetry. 2019. Vol. 11, no. 7. P. 939.

153. Deng, L. Online defect detection and automatic grading of carrots using computer vision combined with deep learning methods / L. Deng, J. Li, Z. Han // Lwt. 2021. Vol. 149. P. 111832.

154. Zhang, X. ShuffleNet: an extremely efficient convolutional neural network for mobile devices. /X. Zhang, J. Sun. 2017. arXiv: 1707.01083. URL: https: //arxiv.org/abs/1707.01083 ; visited on 2021-08-10.

155. Pantazi, X. E. Automated leaf disease detection in different crop species through image features analysis and One Class Classifiers / X. E. Pantazi, D. Moshou, A. A. Tamouridou // Computers and electronics in agriculture. 2019. Vol. 156. P. 96104.

156. Souza, J. R. Automatic detection of ceratocystis wilt in eucalyptus crops from aerial images / J. R. Souza, C. C. Mendes, D. F. Wolf //2015 IEEE international conference on robotics and automation (ICRA). IEEE. 2015. P. 34433448.

157. Pineda, M. Use of multicolour fluorescence imaging for diagnosis of bacterial and fungal infection on zucchini by implementing machine learning / M. Pineda, M. L. Pérez-Bueno, M. Barón // Functional plant biology. 2017. Vol. 44, no. 6. P. 563572.

158. AlSuwaidi, A. Combining spectral and texture features in hyperspectral image analysis for plant monitoring / A. AlSuwaidi, B. Grieve, H. Yin // Measurement Science and Technology. 2018. Vol. 29, no. 10. P. 104001.

159. Blake, A. Markov random fields for vision and image processing / A. Blake, P. Kohli, C. Rother. 55 Hayward Street, Cambridge, MA 02142-1493, USA : MIT Press, 2011. P. 472.

160. Billones, R. K. C. Image-Based Macroscopic Classification of Aspergillus Fungi Species Using Convolutional Neural Networks / R. K. C. Billones, E. J. Calilung, N. Santiago // 2020 IEEE 12th International Conference on Humanoid, Nan-otechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM). IEEE. 2020. P. 14.

161. Wongsila, S. Machine Learning Algorithm Development for detection of Mango infected by Anthracnose Disease / S. Wongsila, P. Chantrasri, P. Sureephong //

2021 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering. IEEE. 2021. P. 249252.

162. Mendigoria, C. H. Vision-based Postharvest Analysis of Musa Acuminata Using Feature-based Machine Learning and Deep Transfer Networks / C. H. Mendigo-ria, H. Aquino, E. Sybingco // 2021 IEEE 9th Region 10 Humanitarian Technology Conference (R10-HTC). IEEE. P. 0106.

163. Tawakal, H. A. The Development of Methods for Detecting Melon Maturity Level Based on Fruit Skin Texture Using the Histogram of Oriented Gradients and the Support Vector Machine / H. A. Tawakal, A. Prayoga //2019 Fourth International Conference on Informatics and Computing (ICIC). IEEE. 2019. P. 14.

164. Chen, Y. Non-destructive Fruit Firmness Evaluation Using Vision-Based Tactile Information / Y. Chen, B. Fang, S. Li // 2022 International Conference on Robotics and Automation (ICRA). IEEE. 2022. P. 23032309.

165. Koufatzis, A. Visual Quality Inspection of Pomegranate Crop Using a Novel Dataset and Deep Learning / A. Koufatzis, E. Vrochidou, G. A. Papakostas //

2022 29th International Conference on Systems, Signals and Image Processing (IWSSIP). CFP2255EART. 2022. P. 14.

166. Ashtiani, S.-H. M. Detection of mulberry ripeness stages using deep learning models / S.-H. M. Ashtiani, S. Javanmardi, A. Martynenko // IEEE Access. 2021. Vol. 9. P. 100380100394.

167. Gupta, S. K. Disease problems in vegetable production / S. K. Gupta, T. Thind. 4806/24, Ansari Road, Darya Ganj, New Delhi, 110002, INDIA : Scientific Publishers, 2018. P. 586.

168. Graves, A. Long short-term memory / A. Graves, A. Graves // Supervised sequence labelling with recurrent neural networks. 2012. P. 3745.

169. Buyukarikan, B. Classification of physiological disorders in apples fruit using a hybrid model based on convolutional neural network and machine learning methods / B. Buyukarikan, E. Ulker // Neural Computing and Applications. 2022. P. 116.

170. Fox, G. The brewing industry and the opportunities for real-time quality analysis using infrared spectroscopy / G. Fox // Applied Sciences. 2020. Vol. 10, no. 2. P. 616.

171. Li, J. Deep unsupervised blind hyperspectral and multispectral data fusion / J. Li, K. Zheng, D. Hong // IEEE Geoscience and Remote Sensing Letters. 2022. Vol. 19. P. 15.

172. Liang, J. Hyperspectral reflectance imaging combined with multivariate analysis for diagnosis of Sclerotinia stem rot on Arabidopsis thaliana leaves / J. Liang, X. Li, Y. He // Applied Sciences. 2019. Vol. 9, no. 10. P. 2092.

173. Vashpanov, Y. Detecting green mold pathogens on lemons using hyperspectral images / Y. Vashpanov, G. Heo, J.-Y. Son // Applied Sciences. 2020. Vol. 10, no. 4. P. 1209.

174. Fahrentrapp, J.Detection of gray mold leaf infections prior to visual symptom appearance using a five-band multispectral sensor / J. Fahrentrapp, F. Ria, B. Panassiti//Frontiers in plant science. 2019. Vol.10. P. 628.

175. Wan, L. Hyperspectral Sensing of Plant Diseases: Principle and Methods / L. Wan, H. Li, P. Wang // Agronomy. 2022. Vol. 12, no. 6. P. 1451.

176. Blaszczyk, U. Application of Bioactive Coatings with Killer Yeasts to Control Post-Harvest Apple Decay Caused by Botrytis cinerea and Penicillium italicum / U. Blaszczyk, S. Wyrzykowska, M. G^stol // Foods. 2022. Vol. 11, no. 13. P. 1868.

177. Amaral Carneiro, G. Cadophora luteo-olivacea isolated from apple (Malus domestica) fruit with post-harvest side rot symptoms in northern Italy / G. Amaral Carneiro, M. Walcher, S. Baric // European Journal of Plant Pathology. 2022. P. 19.

178. Ghooshkhaneh, N. G. VIS-NIR spectroscopy for detection of citrus core rot caused by Alternaria alternata / N. G. Ghooshkhaneh, M. R. Golzarian, K. Mol-lazade//Food Control. 2023. Vol. 144. P. 109320.

179. Jiang, B. Fusion of machine vision technology and AlexNet-CNNs deep learning network for the detection of postharvest apple pesticide residues / B. Jiang, J. He, D. He//Artificial Intelligence in Agriculture. 2019. Vol. 1. P. 18.

180. Nondestructive detection of codling moth infestation in apples using pixel-based nir hyperspectral imaging with machine learning and feature selection / N. Ekramirad [et al.] //Foods. 2022. Vol. 11, no. 1. P. 8.

181. Kadoic Balasko, M. Pest management challenges and control practices in codling

V

moth: A review / M. Kadoic Balasko, R. Bazok, I. Pajac Zivkovic // Insects. 2020. Vol. 11, no. 1. P. 38.

182. Scherrer, B. Hyperspectral imaging and neural networks to classify herbicide-resistant weeds / B. Scherrer, J. Sheppard, J. A. Shaw // Journal of Applied Remote Sensing. 2019. Vol. 13, no. 4. P. 044516.

183. Shirzadifar, A. Development of spectral indices for identifying glyphosate-resistant weeds / A. Shirzadifar, S. Bajwa, J. Shojaeiarani // Computers and Electronics in Agriculture. 2020. Vol. 170. P. 105276.

184. Tamouridou, A. A. Spectral identification of disease in weeds using multilayer perceptron with automatic relevance determination / A. A. Tamouridou, X. E. Pantazi, D. Moshou// Sensors. 2018. Vol. 18, no. 9. P. 2770.

185. Nasi, R. Estimating biomass and nitrogen amount of barley and grass using UAV and aircraft based spectral and photogrammetric 3D features / R. Nasi, N. Vilja-nen, E. Honkavaara//Remote Sensing. 2018. Vol. 10, no. 7. P. 1082.

186. Viljanen, N. A novel machine learning method for estimating biomass of grass swards using a photogrammetric canopy height model, images and vegetation indices captured by a drone / N. Viljanen, E. Honkavaara, R. Nasi // Agriculture. 2018. Vol. 8, no. 5. P. 70.

187. Maimaitijiang, M. Unmanned Aerial System (UAS)-based phenotyping of soybean using multi-sensor data fusion and extreme learning machine / M. Maimaitijiang, A. Ghulam, S. Kadam // ISPRS Journal of Photogrammetry and Remote Sensing. 2017. Vol. 134. P. 4358.

188. Pineda, M. Detection of bacterial infection in melon plants by classification methods based on imaging data / M. Pineda, M. L. Pérez-Bueno, M. Barón // Frontiers in plant science. 2018. Vol.9. P. 164.

189. Glasner, J. D. Genome sequence of the plant-pathogenic bacterium Dickeya dadantii 3937 / J. D. Glasner, C.-H. Yang, D. Expert. 1752 N St NW, Washington, D.C. 20036-2904, USA, 2011.

190. Zhang, D. Detection of rice sheath blight using an unmanned aerial system with high-resolution color and multispectral imaging / D. Zhang, X. Zhou, D. Liang // PloSone. 2018. Vol. 13, no. 5. e0187470.

191. Sun, Y. Detecting decayed peach using a rotating hyperspectral imaging testbed / Y. Sun, H. Xiao, K. Sun // LWT. 2018. Vol. 87. P. 326332.

192. Hyperspectral Imaging Systems Market Size Report. Accessed on 26 June 2023. https: //www. grandviewresearch. com/industry- analysis/hyperspectral- imaging-systems-market.

193. Shadrin, D. Designing future precision agriculture: Detection of seeds germination using artificial intelligence on a low-power embedded system / D. Shadrin, A. Menshchikov, A. Somov//IEEE Sensors Journal. 2019. Vol. 19, no. 23. P. 1157311582.

194. Gasanov, M. Sensitivity analysis of soil parameters in crop model supported with high-throughput computing / M. Gasanov, A. Petrovskaia, I. Oseledets // International Conference on Computational Science. Springer. 2020. P. 731741.

195. Nalwanga, R. Design of an embedded machine learning based system for an environmental-friendly crop prediction using a sustainable soil fertility management / R. Nalwanga, J. Nsenga, I. Gatare // 2021 IEEE 19th Student Conference on Research and Development (SCOReD). IEEE. 2021. P. 251256.

196. Gasanov, M. A New Multi-objective Approach to Optimize Irrigation Using a Crop Simulation Model and Weather History / M. Gasanov, D. Merkulov, I. Oseledets // International Conference on Computational Science. Springer. 2021. P. 7588.

197. Adami, D. Design, development and evaluation of an intelligent animal repelling system for crop protection based on embedded edge-AI / D. Adami, M. O. Ojo, S. Giordano//IEEE Access. 2021. Vol.9. P. 132125132139.

198. Moysiadis, T. Use of IoT technologies for irrigation and plant protection: The case for Cypriot fruits and vegetables / T. Moysiadis, A. Stylianou, M. Gian-nakopoulou//Bio-Economy and Agri-Production. Elsevier, 2021. P. 175194.

199. Meribout, M. State of art IoT and Edge embedded systems for real-time machine vision applications / M. Meribout, M. O. Khaoua, J. P. Pena // IEEE Access. 2022. Vol. 10. P. 5828758301.

200. Chakraborty, S. K. Development of an optimally designed real-time automatic citrus fruit grading-sorting machine leveraging computer vision-based adaptive deep learning model / S. K. Chakraborty, A. Subeesh, D. Kumar // Engineering Applications of Artificial Intelligence. 2023. Vol. 120. P. 105826.

201. Wang, Q. Enterprise human resource management system monitoring based on embedded system and 5G big data platform / Q. Wang // Wireless Networks. 2021. P. 115.

202. Shadrin, D. Enabling precision agriculture through embedded sensing with artificial intelligence / D. Shadrin, A. Menshchikov, M. Fedorov // IEEE Transactions on Instrumentation and Measurement. 2019. Vol. 69, no. 7. P. 41034113.

203. Villalobos, F. J.FertiliCalc: A decision support system for fertilizer management / F. J. Villalobos, A. Delgado, M. Quemada // International Journal of Plant Production. 2020. Vol. 14. P. 299308.

204. Mazzia, V. Real-time apple detection system using embedded systems with hardware accelerators: An edge AI application / V. Mazzia, A. Khaliq, M. Chi-aberge//IEEE Access. 2020. Vol. 8. P. 91029114.

205. Kayikci, Y. Data-driven optimal dynamic pricing strategy for reducing perishable food waste at retailers / Y. Kayikci, S. Demir, N. Subramanian // Journal of CleanerProduction. 2022. Vol.344. P. 131068.

206. Mahbub, M. A smart farming concept based on smart embedded electronics, internet of things and wireless sensor network / M. Mahbub // Internet of Things. 2020. Vol. 9. P. 100161.

207. Venkateshwari, P. A Survey and Challenges: Embedded System on IoT / P. Venkateshwari, S. Subramaniam // IoT Based Smart Applications. Springer, 2022. P. 113129.

208. Zaidi, A. Smart implementation of industrial internet of things using embedded mechatronic system / A. Zaidi, I. Keshta, M. Soni // IEEE Embedded Systems Letters. 2023. Vol. 16, no. 2. P. 190193.

209. Bevilacqua, M. Digital twin reference model development to prevent operators' risk in process plants / M. Bevilacqua, E. Bottani, M. Ortenzi // Sustainabil-ity. 2020. Vol. 12, no. 3. P. 1088.

210. Khattab, A. An IoT-based cognitive monitoring system for early plant disease forecast / A. Khattab, S. E. Habib, M. M. Khairy // Computers and Electronics in Agriculture. 2019. Vol. 166. P. 105028.

211. Araby, A. A. Smart IoT Monitoring System for Agriculture with Predictive Analysis / A. A. Araby, M. M. Abd Elhameed, H. Mostafa //2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST). IEEE. 2019. P. 14.

212. Hossam, M. PLANTAE: an IoT-based predictive platform for precision agriculture / M. Hossam, M. Kamal, A. Khattab //2018 International Japan-Africa Conference on Electronics, Communications and Computations (JAC-ECC). IEEE. 2018. P. 8790.

213. Arakeri, M. P. Computer vision based robotic weed control system for precision agriculture / M. P. Arakeri, B. V. Kumar, S. Barsaiya // 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE. 2017. P. 12011205.

214. Cenggoro, T. W Information System Design for Deep Learning Based Plant Counting Automation / T. W. Cenggoro, A. Budiarto, B. Pardamean // 2018 Indonesian Association for Pattern Recognition International Conference (IN-APR). IEEE. 2018. P. 329332.

215. Diedrichs, A. L. Prediction of frost events using machine learning and IoT sensing devices / A. L. Diedrichs, F. Bromberg, T. Watteyne // IEEE Internet of Things Journal. 2018. Vol. 5, no. 6. P. 45894597.

216. Chawla, N. V. SMOTE: synthetic minority over-sampling technique / N. V. Chawla, K. W. Bowyer, W. P. Kegelmeyer // Journal of artificial intelligence research. 2002. Vol. 16. P. 321357.

217. Agostini, A. A cognitive architecture for automatic gardening / A. Agostini, A. Fischbach, C. Torras // Computers and Electronics in Agriculture. 2017. Vol. 138. P. 6979.

218. Bellman, R. A Markovian decision process / R. Bellman // Journal of mathematics and mechanics. 1957. P. 679684.

219. Agostini, A. Learning weakly correlated cause-effects for gardening with a cognitive system / A. Agostini, C. Torras, F. Wórgótter // Engineering Applications of Artificial Intelligence. 2014. Vol.36. P. 178194.

220. Chou, Y.-C. Deep-learning-based defective bean inspection with GAN-structured automated labeled data augmentation in coffee industry / Y.-C. Chou, C.-J. Kuo, Y.-C. Chen//Applied Sciences. 2019. Vol. 9, no. 19. P. 4166.

221. Cardim Ferreira Lima, M. Monitoring Plant Status and Fertilization Strategy through Multispectral Images / M. Cardim Ferreira Lima, A. Krus, J. J. Roldán-Gómez // Sensors. 2020. Vol. 20, no. 2. P. 435.

222. Raja, R. Real-time weed-crop classification and localisation technique for robotic weed control in lettuce / R. Raja, T. T. Nguyen, S. A. Fennimore // biosystems engineering. 2020. Vol. 192. P. 257274.

223. Bender, A. A high-resolution, multimodal data set for agricultural robotics: A Ladybird's-eye viewofBrassica/ A. Bender, B. Whelan, S. Sukkarieh// Journal of Field Robotics. 2020. Vol. 37, no. 1. P. 7396.

224. Alonso, R. S. An intelligent Edge-IoT platform for monitoring livestock and crops in a dairy farming scenario / R. S. Alonso, I. Sittón-Candanedo, S. Rodríguez-González//Ad Hoc Networks. 2020. Vol.98. P. 102047.

225. Gao, W. A survey of blockchain: Techniques, applications, and challenges / W. Gao, W. G. Hatcher, W. Yu// 2018 27th international conference on computer communication and networks (ICCCN). IEEE. 2018. P. 111.

226. Fu, Z. Wheat growth monitoring and yield estimation based on multi-rotor unmanned aerial vehicle / Z. Fu // Remote Sensing. 2020. Vol. 12, no. 3. P. 508.

227. Choi, H. Open source computer-vision based guidance system for UAVs onboard decision making / H. Choi, M. Geeves, F. Gonzalez // 2016 IEEE Aerospace Conference. IEEE. 2016. P. 15.

228. Kyaw, A. K. Low-Cost Computing Using Raspberry Pi 2 Model B. / A. K. Kyaw, H. P. Truong, J. Joseph// J. Comput. 2018. Vol. 13, no. 3. P. 287299.

229. Saha, A. K. IOT-based drone for improvement of crop quality in agricultural field / A. K. Saha, S. Sircar, H. N. Saha //2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC). IEEE. 2018. P. 612615.

230. Pi, R. Raspberry pi 3 model b / R. Pi // [Online].(https://www. raspberrypi. org. 2015. visited on 2023-02-02.

231. Pandey, A. A hybrid classifier approach to multivariate sensor data for climate smart agriculture cyber-physical systems / A. Pandey, P. Tiwary, S. K. Das // Proceedings of the 20th International Conference on Distributed Computing and Networking. 2019. P. 337341.

232. Reina, G. All-terrain estimation for mobile robots in precision agriculture / G. Reina, R. Galati, A. Milella // 2018 IEEE International Conference on Industrial Technology (ICIT). IEEE. 2018. P. 6368.

233. Stasenko, N.Deep Learning for improving the storage process: Accurate and automatic segmentation of spoiled areas on apples / N. Stasenko, E. Chernova, M. Pukalchik // 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE. 2021. P. 9460071.

234. Stasenko, ^.Deep Learning for Postharvest Decay Prediction in Apples / N. Stasenko, M. Savinov, A. Somov // IECON 2021-47th Annual Conference of the IEEE Industrial Electronics Society. IEEE. 2021. P. 9589498.

235. Velasco, R The genome of the domesticated apple (Malusx domestica Borkh.) / R. Velasco, A. Zharkikh, D. Pruss // Nature genetics. 2010. Vol. 42, no. 10. P. 833839.

236. Ghinea, C. Physico-chemical and sensory quality of oven-dried and dehydrator-dried apples of the Starkrimson, Golden Delicious and Florina cultivars / C. Ghinea, A. E. Prisacaru, A. Leahu // Applied Sciences. 2022. Vol. 12, no. 5. P. 2350.

237. Fujii, J. A. Seasonal changes in the photosynthetic rate in apple trees: A comparison between fruiting and nonfruiting trees / J. A. Fujii, R. A. Kennedy // Plant Physiology. 1985. Vol. 78, no. 3. P. 519524.

238. Shadrin, D. System Identification-Soilless Growth of Tomatoes / D. Shadrin, A. Chashchin, A. Somov // 2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE. 2019. P. 16.

239. Stasenko, ^.Spoiled Apples / N. Stasenko. 2020. URL: https://github.com/ NikitaStasenko/PostharvestDecayApples (visited on 11/30/2020).

240. Supervisely Data Annotator. URL: %7Bhttps://app.supervise.ly%7D ; [Online: accessed: 2023-08-30].

241. Ronneberger, O. U-net: Convolutional networks for biomedical image segmentation / O. Ronneberger, P. Fischer, T. Brox // International Conference on Medical image computing and computer-assisted intervention. Springer. 2015. P. 234241.

242. Goldsborough, P. A tour of tensorflow / P. Goldsborough. 2016. arXiv: 1610. 01178. URL: https://arxiv.org/abs/1610.01178 ; visited on 2020-08-07.

243. Yurtkulu, S. C. Semantic Segmentation with Extended DeepLabv3 Architecture / S. C. Yurtkulu, Y. H. §ahin, G. Unal //2019 27th Signal Processing and Communications Applications Conference (SIU). IEEE. 2019. P. 14.

244. Chen, L.-C. Rethinking atrous convolution for semantic image segmentation / L.-C. Chen, G. Papandreou, H. Adam. 2017. arXiv: 1706.05587. URL: https: //arxiv.org/abs/1706.05587 ; visited on 2020-09-09.

245. Imambi, S. PyTorch / S. Imambi, K. B. Prakash, G. Kanagachidambaresan // Programming with TensorFlow: solution for edge computing applications. Springer, 2021. P. 87104.

246. He, K. Mask r-cnn / K. He, G. Gkioxari, R. Girshick // Proceedings of the IEEE international conference on computer vision. 2017. P. 29612969.

247. Girshick, R. Rich feature hierarchies for accurate object detection and semantic segmentation / R. Girshick, J. Donahue, J. Malik // Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. P. 580587.

248. Girshick, R. Fast r-cnn / R. Girshick // Proceedings of the IEEE international conference on computer vision. 2015. P. 14401448.

249. Ren, S. Faster r-cnn: Towards real-time object detection with region proposal networks / S. Ren, K. He, R. Girshick // Advances in neural information processing systems. 2015. Vol. 28. P. 9199.

250. Li, B. High performance visual tracking with siamese region proposal network / B. Li, J. Yan, X. Hu // Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. P. 89718980.

251. Ghiani, L. In-Field Automatic Detection of Grape Bunches under a Totally Uncontrolled Environment / L. Ghiani, A. Sassu, F. Gambella // Sensors. 2021. Vol. 21, no. 11. P. 3908.

252. Gee, C. RGB image-derived indicators for spatial assessment of the impact of broadleaf weeds on wheat biomass / C. Gee, E. Denimal // Remote Sensing. 2020. Vol. 12, no. 18. P. 2982.

253. Huang, Y.-P. Using Fuzzy Mask R-CNN Model to Automatically Identify Tomato Ripeness / Y.-P. Huang, T.-H. Wang, H. Basanta // IEEE Access. 2020. Vol. 8. P. 207672207682.

254. Lee, J. Artificial intelligence approach for tomato detection and mass estimation in precision agriculture / J. Lee, H. Nazki, M. Lee//Sustainability. 2020. Vol. 12, no. 21. P. 9138.

255. Hu, C. Influence of Image Quality and Light Consistency on the Performance of Convolutional Neural Networks for Weed Mapping / C. Hu, B. B. Sapkota, M. V. Bagavathiannan//Remote Sensing. 2021. Vol. 13, no. 11. P. 2140.

256. Chu, P. DeepApple: Deep Learning-based Apple Detection using a Suppression Mask R-CNN / P. Chu, Z. Li, X. Liu. 2020. arXiv: 2010.09870. URL: https: //arxiv.org/abs/2010.09870 ; visited on 2021-07-07.

257. Detectron2 / Y. Wu [et al.]. 2019. visited on 2023-06-24. https://github.com/ facebookresearch/detectron2.

258. Hussain, Z. Differential data augmentation techniques for medical imaging classification tasks / Z. Hussain, F. Gimenez, D. Rubin // AMIA annual symposium proceedings. Vol. 2017. American Medical Informatics Association. 2017. P. 979.

259. Talukdar, J. Data augmentation on synthetic images for transfer learning using deep CNNs / J. Talukdar, A. Biswas, S. Gupta // 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN). IEEE. 2018. P. 215219.

260. Takahashi, R. Data augmentation using random image cropping and patching for deep CNNs / R. Takahashi, T. Matsubara, K. Uehara // IEEE Transactions on Circuits and Systems for Video Technology. 2019. Vol. 30, no. 9. P. 29172931.

261. Arslan, M. SMOTE and gaussian noise based sensor data augmentation / M. Ar-slan, M. Demirci, S. Ozdemir //2019 4th International Conference on Computer Science and Engineering (UBMK). IEEE. 2019. P. 15.

262. Kandel, I. Brightness as an augmentation technique for image classification / I. Kandel, M. Castelli, L. Manzoni // Emerging Science Journal. 2022. Vol. 6, no. 4. P. 881892.

263. Wenzel, F. Efficient Gaussian process classification using Polya-Gamma data augmentation / F. Wenzel, T. Galy-Fajou, M. Opper // Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 33. 2019. P. 54175424.

264. Olut, S. Adversarial data augmentation via deformation statistics / S. Olut, Z. Shen, S. Gerber // Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28,2020, Proceedings, Part XXIX 16. Springer. 2020. P. 643659.

265. Mu, D. Random blur data augmentation for scene text recognition / D. Mu, W. Sun, W. Li//IEEE Access. 2021. Vol.9. P. 136636136646.

266. Fan, S. On line detection of defective apples using computer vision system combined with deep learning methods / S. Fan, J. Li, W. Huang // Journal of Food Engineering. 2020. Vol.286. P. 110102.

267. Stasenko, ^.Dynamic Mode Decomposition and Deep Learning for Postharvest Decay Prediction in Apples / N. Stasenko, D. Shadrin, A. Somov // IEEE Transactions on Instrumentation and Measurement. 2023. Vol.72. P. 2518411.

268. Schmid, P. J. Dynamic mode decomposition of numerical and experimental data / P. J. Schmid//Journal of fluid mechanics. 2010. Vol.656. P. 528.

269. Abdi, H. Singular value decomposition (SVD) and generalized singular value decomposition / H. Abdi // Encyclopedia of measurement and statistics. 2007. Vol. 907, no. 912. P. 44.

270. Dotto, A. Dynamic mode decomposition and Koopman spectral analysis of boundary layer separation-induced transition / A. Dotto, D. Lengani, A. Tac-chella//Physics of Fluids. 2021. Vol. 33, no. 10. P. 104104.

271. Golub, G. H. Matrix computations / G. H. Golub, C. F. Van Loan. P.O. Box 19966, Baltimore, MD 21211-0966, USA. : JHU press, 2013. P. 756.

272. Demo, N.PyDMD: Python Dynamic Mode Decomposition / N. Demo, M. Tezzele, G. Rozza // The Journal of Open Source Software. 2018. Vol. 3, no. 22. P. 530.

273. Schmid, P. J. Dynamic mode decomposition and its variants / P. J. Schmid // Annual Review of Fluid Mechanics. 2022. Vol.54. P. 225254.

274. Mohan, N. A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model / N. Mohan, K. Soman, S. S. Kumar // Applied energy. 2018. Vol.232. P. 229244.

275. Shiraishi, Y. Neural decoding of electrocorticographic signals using dynamic mode decomposition / Y. Shiraishi, Y. Kawahara, T. Yanagisawa // Journal of Neural Engineering. 2020. Vol. 17, no. 3. P. 036009.

276. Haggerty, D. A. Modeling, reduction, and control of a helically actuated iner-tial soft robotic arm via the Koopman operator / D. A. Haggerty, M. J. Banks, E. W. Hawkes. 2020. arXiv: 2011.07939. URL: https://arxiv.org/abs/2011. 07939 ; visited on 2021-08-10.

277. Wang, H. Real-time states estimation of a farm tractor using dynamic mode decomposition / H. Wang, N. Noguchi // GPS Solutions. 2021. Vol. 25, no. 1. P. 112.

278. Stasenko, N.Deep Learning for improving the storage process: Accurate and automatic segmentation of spoiled areas on apples / N. Stasenko, E. Chernova, M. Pukalchik // 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE. 2021. P. 16.

279. Stasenko, N.SpoiledApples / N. Stasenko. 2020. URL: https://github.com/ NikitaStasenko/PostharvestDecayApples (visited on 11/30/2020).

280. Saletnik, B. Method for Prolonging the Shelf Life of Apples after Storage / B. Saletnik, G. Zagula, C. Puchalski // Applied Sciences. 2022. Vol. 12, no. 8. P. 3975.

281. Arcel, M. M. The application of LED illumination and intelligent control in plant factory, a new direction for modern agriculture: A Review / M. M. Arcel, X. Lin, S. Zheng // Journal of Physics: Conference Series. Vol. 1732. IOP Publishing. 2021. P. 012178.

282. Martínez-Zamora, L. Postharvest UV-B and photoperiod with blue+ red LEDs as strategies to stimulate carotenogenesis in bell peppers / L. Martínez-Zamora, N. Castillejo, F. Artés-Hernández // Applied Sciences. 2021. Vol. 11, no. 9. P. 3736.

283. Sara, U. Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study / U. Sara, M. Akter, M. S. Uddin // Journal of Computer and Communications. 2019. Vol. 7, no. 3. P. 818.

284. Kanupuru, P. A Deep Learning Approach to detect the spoiled fruits. / P. Kanupuru, N. Reddy // WSEAS Transactions on Computer Research. 2022. Vol. 10, no. 24151521. P. 7487.

285. Dhiman, B. A general purpose multi-fruit system for assessing the quality of fruits with the application of recurrent neural network / B. Dhiman, Y. Kumar, Y.-C. Hu//Soft Computing. 2021. Vol. 25, no. 14. P. 92559272.

286. Srinivas, R. Deep Learning based Fruit Quality Inspection / R. Srinivas, B. Ya-diah// Int. J. Res. Appl. Sci. Eng. Technol. 2022. Vol. 10. P. 45354539.

287. Redmon, J. Yolov3: An incremental improvement / J. Redmon, A. Farhadi. 2018. arXi 1804.02767. URL: https://arxiv.org/abs/1804.02767 ; visited on 2021-08-10.

288. Liu, W SSD: single shot multibox detector. / W. Liu, D. E. Dragomir Anguelov, C. Szegedy. 2015. arXiv: 1512.02325. URL: https://arxiv.org/abs/1512.02325 ; visited on 2021-09-09.

289. Kang, H. Fast implementation of real-time fruit detection in apple orchards using deep learning / H. Kang, C. Chen // Computers and Electronics in Agriculture. 2020. Vol. 168. P. 105108.

290. Chu, P. Deep learning-based apple detection using a suppression mask R-CNN / P. Chu, Z. Li, K. Lammers // Pattern Recognition Letters. 2021. Vol. 147. P. 206211.

291. Hung, C. A feature learning based approach for automated fruit yield estimation / C. Hung, J. Underwood, J. Nieto // Field and Service Robotics: Results of the 9th International Conference. Springer. 2015. P. 485498.

292. Ishii, I. 2000 fps real-time vision system with high-frame-rate video recording / I. Ishii, T. Tatebe, T. Takaki //2010 IEEE International Conference on Robotics and Automation. IEEE. 2010. P. 15361541.

293. Stasenko, N.Deep Learning in Precision Agriculture: Artificially Generated VNIR Images Segmentation for Early Postharvest Decay Prediction in Apples / N. Stasenko, I. Shukhratov, A. Somov//Entropy. 2023. Vol. 25, no. 7. P. 987.

294. Isola, P. Image-to-Image Translation with Conditional Adversarial Networks / P. Isola, J.-Y. Zhu, A. A. Efros. 2018. arXiv: 1611.07004. URL: https://arxiv. org/abs/1611.07004 ; visited on 2021-09-10.

295. Li, C. Precomputed real-time texture synthesis with markovian generative adversarial networks / C. Li, M. Wand // European conference on computer vision. Springer. 2016. P. 702716.

296. Zhu, J.-Y. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks / J.-Y. Zhu, P. Isola, A. A. Efros. 2020. arXiv: 1703 . 10593. URL: https://arxiv.org/abs/1703.10593 ; visited on 2021-09-10.

297. Wang, T.-C. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs / T.-C. Wang, J. Kautz, B. Catanzaro. 2018. arXiv: 1711. 11585. visited on 2021-05-03.

298. Simonyan, K. Very deep convolutional networks for large-scale image recognition / K. Simonyan, A. Zisserman. 2014. arXiv: 1409.1556. URL: https: //arxiv.org/abs/1409.1556 ; visited on 2021-08-10.

299. NVIDIA. Jetson modules technical specificatons / NVIDIA. 2023. Accessed on 26 June 2023. https://developer.nvidia.com/embedded/jetson-modules.

300. Fan, S. Real-time defects detection for apple sorting using NIR cameras with pruning-based YOLOV4 network / S. Fan, X. Liang, C. Zhang // Computers and Electronics in Agriculture. 2022. Vol. 193. P. 106715.

301. Tang, Y. Multi-Band-Image Based Detection of Apple Surface Defect Using Machine Vision and Deep Learning / Y. Tang, L. Sun, R. Min // Horticul-turae. 2022. Vol. 8, no. 7. P. 666.

302. Yuan, Y. Detection of early bruise in apple using near-infrared camera imaging technology combined with deep learning / Y. Yuan, Z. Yang, L. Zhao // Infrared Physics & Technology. 2022. Vol. 127. P. 104442.

303. Zhang, Z. Combination of interactance and transmittance modes of Vis/NIR spectroscopy improved the performance of PLS-DA model for moldy apple core / Z. Zhang, Y. Pu, J. Hu // Infrared Physics & Technology. 2022. Vol. 126. P. 104366.

304. Hu, Q.-X. Detection of moldy cores in apples with near-infrared transmission spectroscopy based on wavelet and BP network / Q.-X. Hu, J. Tian, Y. Fang // International Journal of Pattern Recognition and Artificial Intelligence. 2019. Vol. 33, no. 12. P. 1950020.

305. Sadek, M. E. Antifungal activities of sulfur and copper nanoparticles against cucumber postharvest diseases caused by Botrytis cinerea and Sclerotinia sclerotiorum / M. E. Sadek, Y. M. Shabana, A. H. Abou Tabl // Journal of Fungi. 2022. Vol. 8, no. 4. P. 412.