Abstract
It remains challenging in characterizing uncertain and imprecise information when clustering fuzzy number data. To solve such a problem, this paper investigates a new credal-based fuzzy number data clustering (CFNDC) method based on the theory of belief functions (TBF). The CFNDC method attempts to learn a general and flexible credal partition to gain deeper insights into fuzzy number data. Specifically, the CFNDC can provide the behavior (support degrees) for each fuzzy number in different clusters to characterize uncertainty. Additionally, it can reasonably assign the fuzzy numbers in overlapping regions to related meta-clusters, defined as the disjunction of several close specific clusters, to characterize imprecision. Doing so allows prudent decision-making and reduces the risk of errors. We evaluate the performance of different methods using various evaluation indexes and introduce a new measure called evidential purity (EPU). The proposed CFNDC method achieves an average EPU of 0.8330, which demonstrates that CFNDC is a promising tool for effectively handling fuzzy number data.
Similar content being viewed by others
Data availability
All data information is included in this paper.
Notes
Here uncertainty refers to the lack of certainty caused by insufficient information. For example, I am not sure that the student got full marks in both subjects. In comparison, imprecision refers to the lack of precision caused by the fuzziness of knowledge. For example, the student got full marks in at least two subjects.
Some works regard fuzzy numbers as fuzzy data to represent imprecise or fuzzy information, see (Dubois 1980), He et al. (2018). In contrast, some works also define fuzzy data as a set of fuzzy membership functions, see (Han et al. 2013), Yang et al. (2016). From our point of view, fuzzy number is essentially a generalization of real number, which means only knowing around a certain and precise value. Fuzzy number data can be considered as a set of fuzzy numbers. Therefore, to avoid ambiguity, we use fuzzy number data to represent this case in this paper.
LR fuzzy number (data) can also be transformed to triangular fuzzy number, interval number and crisp one in some specific cases (D’Urso and De Giovanni 2014).
So far, there is no work on credal partition of fuzzy number data, so we take object data as an example to explain credal partition.
In this paper, in order to avoid ambiguity, we use “center” to represent the center of fuzzy number data and “prototype” to represent the center of cluster.
The weighted distance in Coppi et al. (2012) uses an appropriate weighting system to consider the center and spread distance of fuzzy numbers, respectively.
Here, we only show the optimization process of \(\mathcal {V}^{Z_1}\), and the optimization process of \(\mathcal {V}^{Z_2}\), \(\mathcal {V}^{L}\) and \(\mathcal {V}^{R}\) is similar to that of \(\mathcal {V}^{Z_1}\).
For credal partition, we can also employ pignistic probabilities (Smets and Kennes 1994) to adapt the clustering results to these indexes.
For visualization, each fuzzy number \(\tilde{\textbf{x}}_{i}\) is represented by a rectangle with the rectangle box representing the 0-level of the membership function (Ramos-Guajardo and Ferraro 2020).
Basic information about the dataset can be found at: https://archive.ics.uci.edu.
References
Askari S (2021) Noise-resistant fuzzy clustering algorithm. Granul Comput 6(4):815–828
Barni M, Cappellini V, Mecocci A (1996) Comments on" a possibilistic approach to clustering". IEEE Trans Fuzzy Syst 4(3):393–396
Bezdek JC, Ehrlich R, Full W (1984) Fcm: The fuzzy c-means clustering algorithm. Comput Geosci 10(2–3):191–203
Chen SJ, Chen SM (2001) A new method to measure the similarity between fuzzy numbers. IEEE Int Conf Fuzzy Syst 3:1123–1126
Chen SM, Jian WS (2017) Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups, similarity measures and pso techniques. Inf Sci 391:65–79
Chen SM, Niou SJ (2011) Fuzzy multiple attributes group decision-making based on fuzzy preference relations. Expert Syst Appl 38(4):3865–3872
Chen SM, Wang NY (2010) Fuzzy forecasting based on fuzzy-trend logical relationship groups. IEEE Trans Syst Man Cybern B Cybern 40(5):1343–1358
Chen SM, Ko YK, Chang YC et al. (2009) Weighted fuzzy interpolative reasoning based on weighted increment transformation and weighted ratio transformation techniques. IEEE Trans Fuzzy Syst 17(6):1412–1427
Coppi R, D’Urso P, Giordani P (2012) Fuzzy and possibilistic clustering for fuzzy data. Comput Stat Data Anal 56(4):915–927
Denoeux T (2021) Nn-evclus: Neural network-based evidential clustering. Inf Sci 572:297–330
Denœux T, Masson MH (2004) Evclus: evidential clustering of proximity data. IEEE Trans Syst Man Cybern B Cybern 34(1):95–109
Dubois DJ (1980) Fuzzy sets and systems: theory and applications, vol 144. Academic press
Dubois D, Prade H (1978) Operations on fuzzy numbers. Int J Syst Sci 9(6):613–626
D’Urso P, Giordani P (2006) A weighted fuzzy c-means clustering model for fuzzy data. Comput Stat Data Anal 50(6):1496–1523
D’Urso P, De Giovanni L (2014) Robust clustering of imprecise data. Chemometr Intell Lab Syst 136:58–80
D’Urso P, Leski JM (2020) Fuzzy clustering of fuzzy data based on robust loss functions and ordered weighted averaging. Fuzzy Sets Syst 389:1–28
Ferraro MB, Giordani P (2017) Possibilistic and fuzzy clustering methods for robust analysis of non-precise data. Int J Approx Reason 88:23–38
Fowlkes EB, Mallows CL (1983) A method for comparing two hierarchical clusterings. J Am Stat Assoc 78(383):553–569
Han D, Han C, Deng Y (2013) Novel approaches for the transformation of fuzzy membership function into basic probability assignment based on uncertainty optimization. Int J Uncertain Fuzziness Knowlege-Based Syst 21(02):289–322
He Y, Wei C, Long H et al (2018) Random weight network-based fuzzy nonlinear regression for trapezoidal fuzzy number data. Appl Soft Comput 70:959–979
Huang J, Song X, Xiao F et al (2023) Belief f-divergence for eeg complexity evaluation. Inf Sci 643:119189
Hung WL, Yang MS (2005) Fuzzy clustering on lr-type fuzzy numbers with an application in taiwanese tea evaluation. Fuzzy Sets Syst 150(3):561–577
Hung WL, Yang MS, Lee ES (2010) A robust clustering procedure for fuzzy data. Comput Math Appl 60(1):151–165
Hwang CM, Yang MS, Hung W (2018) New similarity measures of intuitionistic fuzzy sets based on the jaccard index with its application to clustering. Int J Intell Syst 33(8):1672–1688
Ikotun AM, Ezugwu AE, Abualigah L et al (2022) K-means clustering algorithms: a comprehensive review, variants analysis, and advances in the era of big data. Inf Sci 622:178–210
Jiang B, Pei J, Tao Y et al (2011) Clustering uncertain data based on probability distribution similarity. IEEE Trans Knowl Data Eng 25(4):751–763
Karczmarek P, Kiersztyn A, Pedrycz W et al (2021) K-medoids clustering and fuzzy sets for isolation forest. IEEE Int Conf Fuzzy Syst. https://doi.org/10.1109/FUZZ48607.2020.9177718
Khan I, Luo Z, Huang JZ et al (2019) Variable weighting in fuzzy k-means clustering to determine the number of clusters. IEEE Trans Knowl Data Eng 32(9):1838–1853
Krishnapuram R, Keller JM (1993) A possibilistic approach to clustering. IEEE Trans Fuzzy Syst 1(2):98–110
Li MJ, Ng MK, Ym Cheung et al (2009) Agglomerative fuzzy k-means clustering algorithm with selection of number of clusters. IEEE Trans Knowl Data Eng 20(11):1519–1534
Li Y, Chen J, Feng L (2012) Dealing with uncertainty: a survey of theories and practices. IEEE Trans Knowl Data Eng 25(11):2463–2482
Liu Z (2023) An effective conflict management method based on belief similarity measure and entropy for multi-sensor data fusion. Artif Intell Rev. https://doi.org/10.1007/s10462-023-10533-0
Liu Z, Huang H (2023) Comment on new cosine similarity and distance measures for fermatean fuzzy sets and topsis approach. Knowl Inf Syst. https://doi.org/10.1007/s10115-023-01926-2
Liu Z, Pan Q, Dezert J et al (2015) Credal c-means clustering method based on belief functions. Knowl Based Syst 74:119–132
Liu Z, Huang H, Sukumar L (2023) Adaptive weighted multi-view evidential clustering. In: Int Conf Artif Neural Netw, pp 1–12, (In press)
Luqman A, Shahzadi G (2023) Multi-attribute decision-making for electronic waste recycling using interval-valued fermatean fuzzy hamacher aggregation operators. Granul Comput. https://doi.org/10.1007/s41066-023-00363-4
Masson MH, Denoeux T (2008) Ecm: An evidential version of the fuzzy c-means algorithm. Pattern Recognit 41(4):1384–1397
Oyewole GJ, Thopil GA (2023) Data clustering: application and trends. Artif Intell Rev 56(7):6439–6475
Peters G, Weber R (2016) Dcc: a framework for dynamic granular clustering. Granul Comput 1:1–11
Ramos-Guajardo AB, Ferraro MB (2020) A fuzzy clustering approach for fuzzy data based on a generalized distance. Fuzzy Sets Syst 389:29–50
Rand WM (1971) Objective criteria for the evaluation of clustering methods. J Am Stat Assoc 66(336):846–850
Rodriguez SI, de Carvalho FdA (2021) Soft subspace clustering of interval-valued data with regularizations. Knowl Based Syst 227:107191
Rodríguez SIR, de Carvalho FdAT (2022) Clustering interval-valued data with adaptive euclidean and city-block distances. Expert Syst Appl 198:116774
Saha A, Das S (2018) Clustering of fuzzy data and simultaneous feature selection: A model selection approach. Fuzzy Sets Syst 340:1–37
Salsabeela V, Athira T, John SJ et al (2023) Multiple criteria group decision making based on q-rung orthopair fuzzy soft sets. Granul Comput. https://doi.org/10.1007/s41066-023-00369-y
Sato M, Sato Y (1995) Fuzzy clustering model for fuzzy data. IEEE Int Conf Fuzzy Syst 4:2123–2128
Schütze H, Manning CD, Raghavan P (2008) Introduction to information retrieval, Cambridge University Press Cambridge
Shafer G (1976) A mathematical theory of evidence, vol 42. Princeton University Press
Shen VR, Chung YF, Chen SM et al (2013) A novel reduction approach for petri net systems based on matching theory. Expert Syst Appl 40(11):4562–4576
Sivaguru M (2023) Dynamic customer segmentation: a case study using the modified dynamic fuzzy c-means clustering algorithm. Granul Comput 8(2):345–360
Smets P, Kennes R (1994) The transferable belief model. Artif Intell 66(2):191–234
Su Z, Denoeux T (2019) Bpec: Belief-peaks evidential clustering. IEEE Trans Fuzzy Syst 27(1):111–123
Xiao F, Pedrycz W (2023) Negation of the quantum mass function for multisource quantum information fusion with its application to pattern classification. IEEE Trans Pattern Anal Mach Intell 45(2):2054–2070
Xu D, Tian Y (2015) A comprehensive survey of clustering algorithms. Annals Data Sci 2:165–193
Yager RR (2019) Generalized dempster-shafer structures. IEEE Trans Fuzzy Syst 27(3):428–435
Yang Y (1999) An evaluation of statistical approaches to text categorization. Inf Retr 1(1–2):69–90
Yang Y, Li XR, Han D (2016) An improved \(\alpha \)-cut approach to transforming fuzzy membership function into basic belief assignment. Chinese J Aeronaut 29(4):1042–1051
Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353
Zhang C, Gao R, Qin H et al (2021) Three-way clustering method for incomplete information system based on set-pair analysis. Granul Comput 6:389–398
Zhou K, Guo M, Martin A (2022) Evidential prototype-based clustering based on transfer learning. Int J Approx Reason 151:322–343
Funding
None.
Author information
Authors and Affiliations
Contributions
ZL: Conceptualization, Methodology, Writing—review & editing.
Corresponding author
Ethics declarations
Conflict of interest
None.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, Z. Credal-based fuzzy number data clustering. Granul. Comput. 8, 1907–1924 (2023). https://doi.org/10.1007/s41066-023-00410-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41066-023-00410-0