Alexey Kutyrev

Mr. Alexey Kutyrev

Technologies and machines for industrial horticulture, Federal Scientific Agroengineering Center VIM, Moscow, Moskva, Russia
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 November 2022 in Horticulturae
Verified
Journal Article
Open access
PDF file
BSBoris Shurygin
Boris Shurygin
ISIgor Smirnov
Igor Smirnov
ACAndrey Chilikin
Andrey Chilikin
DKDmitriy Khort
Dmitriy Khort
AKAlexey Kutyrev
Alexey Kutyrev
ASAlexei Solovchenko
Alexei Solovchenko
Non-invasive techniques for the detection of apple fruit damages are central to the correct operation of sorting lines ensuring storability of the collected fruit batches. The choice of optimal method of fruit imaging and efficient image processing method is still a subject of debate. Here, we have dissected the information content of hyperspectral images focusing on either spectral component, spatial component, or both. We have employed random forest (RF) classifiers using different parameters as inputs: reflectance spectra, vegetation indices (VIs), and spatial texture descriptors (local binary patterns, or LBP), comparing their performance in the task of damage detection in apple fruit. The amount of information in raw hypercubes was found to be over an order of magnitude excessive for the end-to-end problem of classification. Converting spectra to vegetation indices has resulted in a 60-fold compression with no significant loss of information relevant for phenotyping and more robust performance with respect to varying illumination conditions. We concluded that the advanced machine learning approaches could be more efficient if complemented by spectral information about the objects in question. We discuss the potential advantages and pitfalls of the different approaches to the machine learning-based processing of hyperspectral data for fruit grading.

17 November 2022 in Sensors
Verified
Journal Article
Open access
PDF file
AKAlexey Kutyrev
Alexey Kutyrev
Nikolay KiktevNikolay Kiktev
Nikolay Kiktev
MJMarcin Jewiarz
Marcin Jewiarz
DKDmitriy Khort
Dmitriy Khort
ISIgor Smirnov
Igor Smirnov
MBMykola Biliuk
Mykola Biliuk
The relevance of the study is confirmed by the rapid development of automation in agriculture, in particular, horticulture; the lack of methodological developments to assess the effectiveness of the introduction of robotic technologies; and the need to expand the functionality of mobile robots. The purpose of the study was to increase the level of autonomy of a robotic platform for picking apple fruits based on a new method, develop a system of factors to determine the effectiveness of the introduction of robots in horticulture, and develop a control system using integrated processing of onboard data. The article discussed the efficiency factors for the introduction of robotic systems and technologies in agricultural enterprises specializing in horticulture within the framework of projects with different budgets. The study sample consisted of 30 experts—enterprises that have implemented robotic platforms and scientists specializing in this field. Based on an expert survey of enterprise specialists, a ranked list of 18 efficiency factors was obtained. To select an evaluation factor that determines the effectiveness of robotization and the developed control system, a method for calculating the concordance coefficient (method of expert analysis) was applied as a measure of the consistency of a group of experts for each group of factors. An analysis of the results of the expert evaluation showed that three factors are the most significant: the degree of autonomy of work; positioning accuracy; and recognition accuracy. The generalized indicator of local autonomy of task performance was estimated based on the analysis of a set of single indicators. A system for controlling the movement of an autonomous robotic wheeled platform based on inertial and satellite navigation and calculation of the path to be overcome was developed. The developed software allows for the design of a route for the robotic platform in apple horticulture to automatically perform various technological operations, such as fertilization, growth and disease control, and fruit harvesting. With the help of the software module, the X, Y coordinates, speed and azimuth of movement were given, and the movement of the platform along the given typical turn trajectories in an intensive horticulture environment was visualized.

19 November 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
DKDmitriy Khort
Dmitriy Khort
AKAlexey Kutyrev
Alexey Kutyrev
ISIgor Smirnov
Igor Smirnov
Nikita AndriyanovNikita Andriyanov
Nikita Andriyanov
RFRostislav Alexandrovich Filippov
Rostislav Alexandrovich Filippov
Sergey V. GudkovSergey V. Gudkov
Sergey V. Gudkov
Recognizing and classifying localized lesions on apple fruit surfaces during automated sorting is critical for improving product quality and increasing the sustainability of fruit production. This study is aimed at developing sustainable methods for fruit sorting by applying hyperspectral analysis and machine learning to improve product quality and reduce losses. The employed hyperspectral technologies and machine learning algorithms enable the rapid and accurate detection of defects on the surface of fruits, enhancing product quality and reducing the number of rejects, thereby contributing to the sustainability of agriculture. This study seeks to advance commercial fruit quality control by comparing hyperspectral image classification algorithms to detect apple lesions caused by pathogens, including sunburn, scab, and rot, on three apple varieties: Honeycrisp, Gala, and Jonagold. The lesions were confirmed independently using expert judgment, real-time PCR, and 3D fluorimetry, providing a high accuracy of ground truth data and allowing conclusions to be drawn on ways to improve the sustainability and safety of the agrocenosis in which the fruits are grown. Hyperspectral imaging combined with mathematical analysis revealed that Venturia inaequalis is the main pathogen responsible for scab, while Botrytis cinerea and Penicillium expansum are the main causes of rot. This comparative study is important because it provides a detailed analysis of the performance of both supervised and unsupervised classification methods for hyperspectral imagery, which is essential for the development of reliable automated grading systems. Support Vector Machines (SVM) proved to be the most accurate, with the highest average adjusted Rand Index (ARI) scores for sunscald (0.789), scab (0.818), and rot (0.854), making it the preferred approach for classifying apple lesions during grading. K-Means performed well for scab (0.786) and rot (0.84) classes, but showed limitations with lower metrics for other lesion types. A design and technological scheme of an optical system for identifying micro- and macro-damage to fruit tissues is proposed, and the dependence of the percentage of apple damage on the rotation frequency of the sorting line rollers is obtained. The optimal values for the rotation frequency of the rollers, at which the damage to apples is less than 5%, are up to 6 Hz. The results of this study confirm the high potential of hyperspectral data for the non-invasive recognition and classification of apple diseases in automated sorting systems with an accuracy comparable to that of human experts. These results provide valuable insights into the optimization of machine learning algorithms for agricultural applications, contributing to the development of more efficient and accurate fruit quality control systems, improved production sustainability, and the long-term storage of fruits.

1 October 2019
Verified
Conference Paper
Closed access
DKDmitry Khort
Dmitry Khort
AKAlexey Kutyrev
Alexey Kutyrev
RFRostislav Filippov
Rostislav Filippov
Nikolay KiktevNikolay Kiktev
Nikolay Kiktev
DKDmytro Komarchuk
Dmytro Komarchuk
Agricultural units technological capabilities utilization level optimization cannot be achieved without production processes wide automation and use of computer-controlled systems on the units. Study purpose is to develop an algorithm for recognizing the coordinates of the location and ripeness of strawberry in different lighting conditions and describe the technological process of their harvesting in the field using a robotic manipulator mounted on a self-propelled platform. As a research result, we developed a self-propelled platform with an automatic manipulator for harvesting strawberries, including a manipulator with six degrees of freedom, coaxial grip, servo drives, a controller, a computer vision camera, a single-board computer, laser sensors, a voltage regulator, a lithium-polymer battery. In programming language Python 3.7.2, an automatic manipulator control algorithm was developed. We concluded that in order to establish optimal operating modes and successful implementation of this technology, additional research is needed to fully optimize technology for a wide range of conditions in agricultural production of horticultural crops.

22 May 2022 in Plants
Verified
Journal Article
Open access
PDF file
EKEvgeny Konchekov
Evgeny Konchekov
LKLeonid V. Kolik
Leonid V. Kolik
YDYury K. Danilejko
Yury K. Danilejko
SBSergey V. Belov
Sergey V. Belov
KAKonstantin V. Artem’ev
Konstantin V. Artem’ev
Sergey V. GudkovSergey V. Gudkov
Sergey V. Gudkov
A garden plant grafting technique enhanced by cold plasma (CAP) and plasma-treated solutions (PTS) is described for the first time. It has been shown that CAP created by a dielectric barrier discharge (DBD) and PTS makes it possible to increase the growth of Pyrus communis L. by 35–44%, and the diameter of the root collar by 10–28%. In this case, the electrical resistivity of the graft decreased by 20–48%, which indicated the formation of a more developed vascular system at the rootstock–scion interface. The characteristics of DBD CAP and PTS are described in detail.

20 April 2022 in Sensors
Verified
Journal Article
Open access
PDF file
DKDmitriy Khort
Dmitriy Khort
AKAlexey Kutyrev
Alexey Kutyrev
Nikolay KiktevNikolay Kiktev
Nikolay Kiktev
Taras HutsolTaras Hutsol
Taras Hutsol
Szymon GłowackiSzymon Głowacki
Szymon Głowacki
Zofia Gródek-SzostakZofia Gródek-Szostak
Zofia Gródek-Szostak
The study relates to the use of automated plant protection systems in agriculture. The article presents a proprietary automated mobile platform with an aerosol generator of hot mist. Furthermore, the cause of the loss of a chemical preparation in the spraying of plant protection products on the tree crown was determined in the course of field research. A statistical analysis of the results of experiment was carried out and the effect of droplet size on leaf coating density was determined. The manuscript presents a diagram of the degree of penetration of the working solution as it drops into the crown of the tree, as well as a cross-sectional graph of the permeability of the spray from the projection of the fruit tree crown. The most effective modes of operation of the automated mobile platform for spraying plant protection products with a mist generator aggregate were established. Analysis of the results shows that the device meets the spraying requirements of the procedure for spraying plant protection products. The novelty of this research lies in the optimal modes identified by movement of the developed automated mobile platform and the parameters of plant treatment with protective equipment when using a hot mist generator. The following mode parameters were established: the speed of the automated platform was 3.4 km/h, the distance to the crown of the tree was 1.34 m, and the flow rate of the working fluid was 44.1 L/h. Average fuel consumption was 2.5 L/h. Effective aerosol penetration reduced the amount of working fluid used by up to 50 times.