Fuzzy Systems and its Applications

Fuzzy Systems and its Applications

Clustering of data extracted from fuzzy population by hierarchical algorithm and its application in modern robotics

Document Type : Original Article

Authors
Marzieh Rezaei 1
Abbas Parchami 2
Ayyub Sheikhi 1
1 Department of Statistics, Faculty of Mathematics and Computer, Shahid Bahonar University of Kerman, Kerman, Iran
2 Department of Statistic, University of Kerman
10.22034/jfsa.2026.563812.1295
Abstract
Hierarchical clustering is an unsupervised learning method in data mining that evaluates the similarity between data, groups them in a hierarchical structure, and creates clusters with the highest intra-cluster similarity. The existing methods in this field are designed for data extracted from precise populations. However, in many real-world applications, the populations under study are imprecise or fuzzy in nature; such populations can be referred to as talented students, healthy agricultural products, useful training courses, and high-paying jobs. In such populations, each observation, in addition to its numerical value, also has a degree of membership in the fuzzy population. In this paper, the hierarchical clustering method is generalized to the clustering algorithm for data obtained from fuzzy populations. Also, by generalizing the two silhouette and Dunn indices from the classical case to the fuzzy population, the number of optimal clusters is determined based on the similarity criteria between clusters, and the quality of clustering in the practical use of the proposed method on modern robotic data is explained.
Keywords
Clustering
hierarchical algorithm
membership function
data extracted from fuzzy population
weighting
[6]    C. C. Aggarwal, & C. K. Reddy. (2014) Data clustering algorithms and applications, Data Mining and Knowledge Discovery Series.
[7]    G. J. Klir, & B. Yuan. (1995) Fuzzy sets and fuzzy logic: theory and applications, Upper Saddle River, NJ, USA: Prentice Hall.
 
[8]    J. Byrd, & Z. Lipton. (2019) What is the effect of importance weighting in deep learning? Proceedings of the 36th International Conference on Machine Learning (PMLR 97), 872–881.
[9]    J. Mohammadi, & S. M. Taheri. (2004) Pedomodels fitting with fuzzy least squares regression, Ira- nian Journal of Fuzzy Systems, 1, 45-61.
[10]    M. Eftekhari, A. Mehrpooya, F. Saberi-Movahed, & V. Torra. (2022) How fuzzy concepts contribute to machine learning. Studies in Fuzziness and Soft Computing, 416, Springer.
[11]    M. Kimura, & H. Hino. (2024) A short survey on importance weighting for machine learning. arXiv preprint arXiv:2403.10175.
[12]    M. Namdari, J. H. Yoon, A. R. Abadi, S. M. Taheri, & S. H. Choi. (2014) Fuzzy logistic regression with least absolute deviations estimators, Soft Computing, 19, 909-917.
[13]    M. S. Yang, & W. L. Hung. (2021) Advances in Fuzzy Clustering and Its Applications, John Wiley Sons.
[14]    P. N. Tan, M. Steinbach, & V. Kumar. (2018) Introduction to Data Mining, (2nd ed.), Pearson.
[15]    S. M. S. Hussain, & T. S. B. Sudhakar. (2019) A Comparative Analysis of Hierarchical Clustering Algorithms, International Journal of Computer Sciences and Engineering (IJCSE), 7(5), 266-271.
Fuzzy Systems and its Applications
Volume 9, Issue 1 - Serial Number 18
Open Access Statement
June 2026
Pages 93-114

  • Receive Date 02 December 2025
  • Revise Date 16 February 2026
  • Accept Date 03 May 2026