Informacionnye TehnologiiInformacionnye TehnologiiИнформационные технологии1684-6400New Technologies Publishing House70213110.17587/it.31.243-257Intelligent systems and technologiesИнтеллектуальные системы и технологииResearch ArticleThe method of classifying objects by indistinctly expressed features in the intelligent control system of the robotМетод классификации объектов по нечетко выраженным признакам в интеллектуальной системе управления роботаhttps://orcid.org/0000-0002-9969-3139RomanovP. S.РомановП. С.
Russian Federation

Dr. of Eng. Sc., Professor

д-р техн. наук, проф.

romanov_p_s@mail.ruhttps://orcid.org/0000-0001-5883-9907RomanovaI. P.РомановаИ. П.
Russian Federation

Cand. of Eng. Sc., Associate Professor

канд. техн. наук, доц.

i-p-romanova@yandex.ruKolomna Institute (branch) of Moscow Polytechnical UniversityКоломенский институт (филиал) ФГАОУ ВО "Московский политехнический университет"Moscow Witte UniversityМосковский университет им. С. Ю. Витте150520253152432570302202603022026Copyright ©; 2025, Informacionnye TehnologiiCopyright ©; 2025, Информационные технологии2025Informacionnye TehnologiiИнформационные технологииhttps://journals.eco-vector.com/1684-6400/article/view/702131

The article considers the problem of classifying objects according to indistinctly expressed features in the intelligent control system (ICS) of a robot. A method and algorithm for classifying objects with indistinctly expressed features in the intelligent control system of the robot have been developed. It is proposed to solve the problem on the basis of a complex indicator that takes into account both the degrees of belonging of the features of the recognized object to the features of one of the classes of objects, and the weight coefficients of each feature. An improved weighted Mahalanobis distance was chosen as an indicator, taking into account the fuzziness of the features by which objects are classified. The proposed method is considered by the example of solving the problem of classification (sorting) of ceps in the ICS of a mushroom sorter robot. The efficiency of the proposed method is confirmed by the results of a computational experiment. This method can be implemented in the development of software for classifying objects according to indistinctly expressed features when controlling intelligent robots in areas where there is disorganization of the operating environment.

Рассмотрена задача классификации объектов по нечетко выраженным признакам в интеллектуальной системе управления (ИСУ) робота. Разработаны метод и алгоритм классификации объектов с нечетко выраженными признаками в ИСУ робота. Предложено решать задачу на основе комплексного показателя, учитывающего как степени принадлежности признаков распознаваемого объекта признакам одного из классов объектов, так и весовые коэффициенты каждого признака. В качестве показателя выбрано усовершенствованное взвешенное расстояние Махаланобиса, учитывающее нечеткость признаков, по которым проводится классификация объектов. Предлагаемый метод рассмотрен на примере решения задачи классификации (сортировки) белых грибов в ИСУ робота-сортировщика грибов. Работоспособность предложенного метода подтверждена результатами вычислительного эксперимента. Данный метод может быть реализован при разработке программного обеспечения для классификации объектов по нечетко выраженным признакам при управлении интеллектуальными роботами в тех областях, где имеет место неорганизованность среды функционирования.

classificationcepsrobotartificial intelligenceintelligent control systemquantitative and qualitative characteristics of an objectMahalanobis distancelinguistic variablesmembership functionклассификацияискусственный интеллектинтеллектуальная система управленияроботколичественные и качественные признаки объектарасстояние Махаланобисалингвистические переменныефункция принадлежностибелый грибWakchaure M., Patle B. K., Mahindrakar A. K. Application of AI techniques and robotics in agriculture, Artificial Intelligence in the Life Sciences, 2023, vol. 3, p. 100057.Wakchaure M., Patle B. K., Mahindrakar A. K. Application of AI techniques and robotics in agriculture // Artificial Intelligence in the Life Sciences. 2023. Vol. 3. P. 100057.Xie Q. Visual sorting technology and graphic defect detection of external quality of fresh Lentinus edodes, Edible Fungi of China, 2020, vol. 39, pp. 153—156.Xie Q. Visual sorting technology and graphic defect detection of external quality of fresh Lentinus edodes // Edible Fungi of China. 2020. Vol. 39. P. 153—156.Xu Y. M., Zhang Q. R. Analysis on the present situation and future development of lentinus edodes industry in China, Edible Fungi of China, 2021, vol. 40, pp. 89—92.Xu Y. M., Zhang Q. R. Analysis on the present situation and future development of lentinus edodes industry in China // Edible Fungi of China. 2021. Vol. 40. P. 89—92.Gao Y., Xue X., Qin G., Li K., Liu J., Zhang Y., Li X. Application of machine learning in automatic image identification of insects — a review, Ecological Informatics, 2024, vol. 80, p. 102539.Gao Y., Xue X., Qin G., Li K., Liu J., Zhang Y., Li X. Application of machine learning in automatic image identification of insects — a review// Ecological Informatics. 2024. Vol. 80. P. 102539.Yao J., Qi J., Zhang J., Shao H., Yang J., Li X. A real-time detection algorithm for Kiwifruit defects based on YOLOv5, Electronics, 2021, vol. 10 (14), p. 1711.Yao J., Qi J., Zhang J., Shao H., Yang J., Li X. A real-time detection algorithm for Kiwifruit defects based on YOLOv5 // Electronics. 2021. Vol. 10 (14). P. 1711.Khattar S., Bajaj R. Enhancement of Multiclass Dermoscopic Image Classification with a Fusion Model and Fine-Tuned Deep Neural Networks, Procedia Computer Science, 2024, vol. 233, pp. 204—214.Khattar S., Bajaj R. Enhancement of Multiclass Dermoscopic Image Classification with a Fusion Model and Fine-Tuned Deep Neural Networks // Procedia Computer Science. 2024. Vol. 233. P. 204—214.Dingle K., Batlle P., Owhadi H. Multiclass classification utilising an estimated algorithmic probability prior, Physica D: Nonlinear Phenomena, 2023, vol. 448, p. 133713.Dingle K., Batlle P., Owhadi H. Multiclass classification utilising an estimated algorithmic probability prior // Physica D: Nonlinear Phenomena. 2023. Vol. 448. P. 133713.Patgiri C., Ganguly A. Adaptive thresholding technique based classification of red blood cell and sickle cell using Naive Bayes Classifier and K-nearest neighbor classifier, Biomedical Signal Processing and Control, 2021, vol. 68, p. 102745.Patgiri C., Ganguly A. Adaptive thresholding technique based classification of red blood cell and sickle cell using Naive Bayes Classifier and K-nearest neighbor classifier // Biomedical Signal Processing and Control. 2021. Vol. 68. P. 102745.Alizadeh S. H., Hediehloo A., Harzevili N. S. Multi independent latent component extension of naive Bayes classifier, Knowledge-Based Systems, 2021, vol. 213, p. 106646.Alizadeh S. H., Hediehloo A., Harzevili N. S. Multi independent latent component extension of naive Bayes classifier // Knowledge-Based Systems. 2021. Vol. 213. P. 106646.Ali J., Aldhaifallah M., Nisar K. S., Aljabr A. A., Tanveer M. Regularized Least Squares Twin SVM for Multiclass Classification, Big Data Research, 2022, vol. 27, p. 100295.Ali J., Aldhaifallah M., Nisar K. S., Aljabr A. A., Tanveer M. Regularized Least Squares Twin SVM for Multiclass Classification // Big Data Research. 2022. Vol. 27. P. 100295.Shao J.-H., Lv X.-J., Huang L.-W., Bai l. Twin SVM for conditional probability estimation in binary and multiclass classification, Pattern Recognition, 2023, vol. 136, p. 109253.Shao J.-H., Lv X.-J., Huang L.-W., Bai l. Twin SVM for conditional probability estimation in binary and multiclass classification // Pattern Recognition. 2023. Vol. 136. P. 109253.Joelianto E., Mandasari M. I., Marpaung D. B., Hafizhan N. D., Heryono T., Prasetyo M. E., Tjahjani D. S., Anggraeni T., Ahmad I. Convolutional neural network-based real-time mosquito genus identification using wingbeat frequency: A binary and multiclass classification approach, Ecological Informatics , 2024, vol. 80, p. 102495.Joelianto E., Mandasari M. I., Marpaung D. B., Hafizhan N. D., Heryono T., Prasetyo M. E., Tjahjani D. S., Anggraeni T., Ahmad I. Convolutional neural network-based real-time mosquito genus identification using wingbeat frequency: A binary and multiclass classification approach // Ecological Informatics. 2024. Vol. 80. P. 102495.Kafiev I. R., Romanov P. S., Romanova I. P. The selecting of artificial intelligence technology for control of mobile robots, 2018 International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon). IEEE Xplore: 07 January 2019.2019, available at: ieeexplore.ieee.org/document/8602796.Kafiev I. R., Romanov P. S., Romanova I. P. The selecting of artificial intelligence technology for control of mobile robots // 2018 International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon). IEEE Xplore: 07 January 2019.2019. URL: ieeexplore.ieee.org/document/8602796.Kafiev I. R., Romanov P. S., Romanova I. P., Galiullin R. R. The technique of recognizing fuzzy situations in the management of agricultural mobile robots, Vestnik Bashkirskogo gosudarstvennogo agrarnogo universiteta, 2019, no. 3 (51), pp.106—114.Кафиев И. Р., Романов П. С., Романова И. П., Галиуллин Р. Р. Методика распознавания нечетких ситуаций при управлении сельскохозяйственными мобильными роботами // Вестник Башкирского государственного аграрного университета. 2019. № 3 (51). С.106—114.Ge F., Hou X., Chen D., Shen L., Liu H. A dynamic multi-objective evolutionary algorithm based on Mahalanobis distance and intra-cluster individual correlation rectification, Information Sciences, 2024, vol. 678, p. 120922.Ge F., Hou X., Chen D., Shen L., Liu H. A dynamic multi-objective evolutionary algorithm based on Mahalanobis distance and intra-cluster individual correlation rectification // Information Sciences. 2024. Vol. 678. P. 120922.Ouyang J., Wang Y., Li Q. Secure delegated quantum algorithms for solving Mahalanobis distance, Physica A: Statistical Mechanics and its Applications, 2023, vol. 625, p. 129025.Ouyang J., Wang Y., Li Q. Secure delegated quantum algorithms for solving Mahalanobis distance // Physica A: Statistical Mechanics and its Applications. 2023. Vol. 625. P. 129025.Chen Q., Yu W., Zhao X., Nie., Li X. Rooted Mahalanobis distance based Gustafson-Kessel fuzzy C-means, Information Sciences, 2023, vol. 644, p. 118878.Chen Q., Yu W., Zhao X., Nie., Li X. Rooted Mahalanobis distance based Gustafson-Kessel fuzzy C-means // Information Sciences. 2023. Vol. 644. P. 118878.Sun Y., Jiang L., Pan J., Sheng S., Hao L. A satellite imagery smoke detection framework based on the Mahalanobis distance for early fire identification and positioning, International Journal of Applied Earth Observation and Geoinformation, 2023, vol. 118, p. 103257.Sun Y., Jiang L., Pan J., Sheng S., Hao L. A satellite imagery smoke detection framework based on the Mahalanobis distance for early fire identification and positioning // International Journal of Applied Earth Observation and Geoinformation. 2023. Vol. 118. P. 103257.Garaa-Santillan I. D., Pajares G. On-line crop/weed discrimination through the Mahalanobis distance from images in maize fields, Biosystems Engineering, 2018, vol. 166, pp. 28—43.Garaa-Santillan I. D., Pajares G. On-line crop/weed discrimination through the Mahalanobis distance from images in maize fields // Biosystems Engineering. 2018. Vol. 166. P. 28—43.Zhao X., Li Y., Zhao Q. Mahalanobis distance based on fuzzy clustering algorithm for image segmentation, Digital Signal Processing, 2015, vol. 43, pp. 8—16.Zhao X., Li Y., Zhao Q. Mahalanobis distance based on fuzzy clustering algorithm for image segmentation // Digital Signal Processing. 2015. Vol. 43. P. 8—16.Glazkova A. V. Evaluation of the effectiveness of using Euclid and Mahalanobis distances to solve one of the problems of text classification, Vestnik Dagestanskogo gosudarstvennogo texnicheskogo universiteta. Texnicheskie nauki, 2017, vol. 44, no. 1, pp. 86—93.Глазкова А. В. Оценка результативности применения расстояний Евклида и Махаланобиса для решения одной из задач классификации текстов // Вестник Дагестанского государственного технического университета. Технические науки. 2017. Т. 44, № 1. C.86—93.Averkin A. N., Batyrshin I. Z., Blishun A. F., Silov V. B., Tarasov V. B. Fuzzy sets in control and artificial intelligence models, Moscow, Nauka, 1986, 312 p.Аверкин А. Н., Батыршин И. З., Блишун А. Ф., Силов В. Б., Тарасов В. Б. Нечеткие множества в моделях управления и искусственного интеллекта / Под ред. Поспелова Д. А. М.: Наука, 1986. 312 с.Romanov P. S., Romanova I. P. Decision-making methodology for choosing the best technical system based on a set of its characteristics, Informacionnye Tehnologii, 2018, vol. 24, no. 7, pp. 445—453.Романов П. С., Романова И. П. Методика принятия решений по выбору наилучшей технической системы по набору ее характеристик // Информационные технологии. 2018. Т. 24, № 7. С. 445—453.Melixov A. N., Bershtejn L. S., Korovin S. Ya. Situational advising systems with fuzzy logic, Moscow, Nauka, Gl. red. fiz.-mat. lit., 1990, 272 p.Мелихов А. Н., Берштейн Л. С., Коровин С. Я. Ситуационные советующие системы с нечеткой логикой. М.: Наука. Гл. ред. физ.-мат. лит. 1990. 272 с.Liu Q., Fang M., Li Y., Gao M. Deep learning based research on quality classification of shiitake mushrooms, LWT, 2022, vol. 168, p. 113902.Liu Q., Fang M., Li Y., Gao M. Deep learning based research on quality classification of shiitake mushrooms // LWT. 2022. Vol. 168. P. 113902.Dubey S. R., Jalal A. Apple disease classification using color, texture and shape features from images, SIViP, 2016, vol. 10, pp. 819—826.Dubey S. R., Jalal A. Apple disease classification using color, texture and shape features from images // SIViP. 2016. Vol. 10. P. 819—826.Aghajani P. F., Firouz M. S., Bohlol P. Revolutionizing Mushroom Identification: Improving efficiency with ultrasound-assisted frozen sample analysis and deep learning techniques, Journal of Agriculture and Food Research, 2024, vol. 15, p. 100946.Aghajani P. F., Firouz M. S., Bohlol P. Revolutionizing Mushroom Identification: Improving efficiency with ultrasound-assisted frozen sample analysis and deep learning techniques // Journal of Agriculture and Food Research. 2024. Vol. 15. P. 100946.Firouz S. M., Sardari H. Defect detection in fruit and vegetables by using machine vision systems and image processing, Food Eng. Rev., 2022, vol. 14 (3), pp. 353—379.Firouz S. M., Sardari H. Defect detection in fruit and vegetables by using machine vision systems and image processing // Food Eng. Rev. 2022. Vol. 14 (3). P. 353—379.Zaid F., Gazder U, Barbieri D. M. Multi-criteria analysis for freight transport decision-making with fuzzy analytic hierarchy process: A top management’s perspective for Bahrain, Transportation Research Interdisciplinary Perspectives, 2024, vol. 23, p. 101017.Zaid F., Gazder U., Barbieri D. M. Multi-criteria analysis for freight transport decision-making with fuzzy analytic hierarchy process: A top management’s perspective for Bahrain // Transportation Research Interdisciplinary Perspectives. 2024. Vol. 23. P. 101017.Ransikarbum K., Pitakaso R. Multi-objective optimization design of sustainable biofuel network with integrated fuzzy analytic hierarchy process, Expert Systems with Applications, 2024, vol. 240, p. 122586.Ransikarbum K., Pitakaso R. Multi-objective optimization design of sustainable biofuel network with integrated fuzzy analytic hierarchy process // Expert Systems with Applications.