Lesnoy Vestnik / Forestry BulletinLesnoy Vestnik / Forestry BulletinЛесной вестник / Forestry Bulletin2542-1468Eco-Vector70678610.18698/2542-1468-2024-2-150-155Math modelingМатематическое моделированиеResearch ArticleCluster analysis of Z-information based on a reference system of fuzzy identificationКластерный анализ Z-информации на основе эталонной системы нечетких определений принадлежностиPoleshchukOl’ga M.ПолещукОльга Митрофановна
Russian Federation

Dr. Sci. (Tech.), Professor, Head of Higher Mathematics and Physics Department

д-р техн. наук, профессор, зав. кафедрой «Высшая математика и физика»

poleshchuk@mgul.ac.ruBMSTU (Mytishchi branch)ФГБОУ ВО «Московский государственный технический университет имени Н.Э. Баумана (национальный исследовательский университет)» (Мытищинский филиал)150420242821501552604202626042026Copyright ©; 2024, Poleshchuk O.M.Copyright ©; 2024, Полещук О.М.2024Poleshchuk O.M.Полещук О.М.https://creativecommons.org/licenses/by/4.0https://journals.eco-vector.com/2542-1468/article/view/706786

The paper develops an algorithm for clustering Z-information based on reference fuzzy identification of objects belonging to clusters. The information is represented by linguistic Z-numbers, both components of which (object evaluation and their validity) are values of linguistic variables. Reference fuzzy identification of affiliation is based on information about the importance of the characteristics assessed by objects, formalized on the basis of a linguistic variable. The object evaluation and fuzzy reference identification were used to determine fuzzy rankings of the degree to which objects belong to clusters. The algorithm developed in the article improves the clustering algorithm presented by the author earlier, since it preserves more initial information due to a new approach to data formalization and reduces the fuzziness of rating objects, thereby reducing the risks of errors in decision support tasks.

Разработан алгоритм кластеризации данных, представленных лингвистическими Z-числами. Обе компоненты чисел (оценки объектов и их достоверность) являются значениями лингвистических переменных. Кластеризация информации осуществлялась на основе нечетких эталонных высказываний о важности характеристик объектов, формализованных на основе лингвистических переменных. Оценки объектов и нечеткие эталонные высказывания использованы для определения нечетких рейтинговых оценок степени принадлежности объектов к кластерам. Разработанный в статье алгоритм улучшает алгоритм кластеризации, представленный автором ранее, поскольку сохраняет больше исходной информации из-за нового подхода к формализации данных и уменьшает нечеткость рейтинговых оценок объектов, тем самым уменьшая риски ошибок в задачах поддержки принятия решений.

Z-informationclustering algorithmrating estimatelinguistic variableZ-информацияалгоритм кластеризациирейтинговая оценкалингвистическая переменнаяZadeh L.A. Fuzzy logic and approximate reasoning // Synthese, 1975, v. 80, pp. 407–428.Hwang C.L., Lin N.J. Group decision making under multiple criteria. Berlin: Springer, 1987, 400 p.Borisov A.N., Krumberg O.A., Fedorov I.P. Decision making on the basis of fuzzy models: Examples of use. Riga: Zinatne, 1990, 184 p.Poleshchuk O., Komarov E. Expert Fuzzy Information Processing. Studies in Fuzziness and Soft Computing, 2011, v. 268, pp. 1–239.Ryjov A. Fuzzy Linguistic Scales: Definition, Properties and Applications. In: Reznik L., Kreinovich V. (eds) Soft Computing in Measurement and Information Acquisition. Studies in Fuzziness and Soft Computing, 2003, v. 127.Poleshchuk O.M. Creation of linguistic scales for expert evaluation of parameters of complex objects based on semantic scopes // International Russian Automation Conference (RusAutoCon – 2018), 2018, pp. 1–6.Bezdek J.C. Selected applications in classifier design // Pattern recognition with fuzzy objective function algorithms, 1981, v. 2, pp. 203–239.Bezdek J.C., Hathaway R.J. Optimization of fuzzy clustering criteria using genetic algorithm // Proceedings of the IEEE Conference on Evolutionary Computation, 1994, v. 2, pp. 589–594.Runkler T.A., Katz C. Fuzzy clustering by particle swarm optimization // Proceedings of the IEEE International Conference on Fuzzy Systems, 2006, pp. 34–41.Liu H.C., Yih J.M., Wu D.B., Liu S.W.: Fuzzy C-mean clustering algorithms based on Picard iteration and particle swarm optimization // Proceedings of the International Workshop on Geoscience and Remote Sensing (ETT and GRS-2008), 2008, pp. 75–84.Kennedy J., Eberhart R.C. Particle swarm optimization // Proceedings of the IEEE International Joint Conference on Neural Networks, 1995, v. 4, pp. 1942–1948.Chen M., Ludwig A. Particle swarm optimization based fuzzy clustering approach to identify optimal number of clusters // J. of Artificial Intelligence and Soft Computing Research, 2014, v. 4, no. 1, pp. 43–56.Phyo O., Chaw E.: Comparative Study of Fuzzy PSO (FPSO) Clustering Algorithm and Fuzzy C-Means (FCM) Clustering Algorithm // National J. of Parallel and Soft Computing, 2019, v. 1, no. 1, pp. 62–67.Ruspini E.H. Numerical methods for fuzzy clustering // Information Sciences, 1970, v. 2, pp. 319–350.Tamura S., Higuchi S., Tanaka K. Pattern classification based on fuzzy relations // IEEE Transactions on Systems, Man and Cybernetics, 1971, v. 1, pp. 61–66.Zadeh L.A.: Similarity relations and fuzzy orderings // Information Sciences, 1971, v. 3, pp. 177–200.Dunn J.C. A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters // J. of Cybernatics, 1973, v. 3, pp. 32–57.Poleshchuk O, Komarov E. The determination of rating points of objects with qualitative characteristics and their usage in decision making problems // International J. of Computational and Mathematical Sciences, 2009, v. 3, no. 7, pp. 360–364.Darwish A., Poleshchuk O. New models for monitoring and clustering of the state of plant species based on sematic spaces // J. of Intelligent and Fuzzy Systems, 2014, v. 3, no. 26, pp. 1089–1094.Poleshchuk O.M., Komarov E.G., Darwish A. Assessment of the state of plant species in urban environment based on fuzzy information of the expert group // Proceedings of the XX IEEE International Conference on Soft Computing and Measurements, (SCM-2017), 2017, pp. 651–654.Zadeh L.A. A Note on Z-numbers // Information Sciences, 2011, v. 14, no. 181, pp. 2923–2932.Jamal M., Khalif K., Mohamad S. The implementation of Z-numbers in fuzzy clustering algorithm for wellness of chronic kidney disease patients // J. of Physics: Conference Series, 2018, v. 1366, p. 012058.Aliev R.A., Pedrycz W., Guirimov B.G., Huseynov O.H. Clustering method for production of Z-numbers based if-then rules // Information Sciences, 2020, v. 520, pp. 155–176.Aliev R., Guirimov B. Z-number clustering based on general Type-II fuzzy sets // Advances in Intelligent Systems and Computing, 2018, v. 896, pp. 270–278.Полещук О.М. Кластерный анализ экспертной информации на основе Z-чисел // Лесной вестник / Forestry Bulletin, 2022. Т. 26. № 1. С. 143–148. DOI: 10.18698/2542-1468-2022-1-143-148 Poleshchuk O.M. Klasternyy analiz ekspertnoy informatsii na osnove Z-chisel [Cluster analysis of expert information based on Z-numbers]. Lesnoy vestnik / Forestry Bulletin, 2022, vol. 26, no. 1, pp. 143–148. DOI: 10.18698/2542-1468-2022-1-143-148Poleshchuk O. Clustering Z-information based on a system of fuzzy reference requirements // E3S Web of Conferences, 2023, v. 420, p. 06022.Poleshchuk O.M. Expert group information formalization based on Z-numbers // J.of Physics: Conference Series, 2020, v. 1703, p. 012010.