@article{MTMT:31056733,
	title = {Self-Tuning Possibilistic c-Means Clustering Models},
	url = {https://m2.mtmt.hu/api/publication/31056733},
	author = {Szilágyi, László and Lefkovits, Szidónia and Szilágyi, Sándor Miklós},
	doi = {10.1142/S0218488519400075},
	journal-iso = {INT J UNCERTAIN FUZZ},
	journal = {INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS},
	volume = {27},
	unique-id = {31056733},
	issn = {0218-4885},
	abstract = {The relaxation of the probabilistic constraint of the fuzzy c-means clustering model was proposed to provide robust algorithms that are insensitive to strong noise and outlier data. These goals were achieved by the possibilistic c-means (PCM) algorithm, but these advantages came together with a sensitivity to cluster prototype initialization. According to the original recommendations, the probabilistic fuzzy c-means (FCM) algorithm should be applied to establish the cluster initialization and possibilistic penalty terms for PCM. However, when FCM fails to provide valid cluster prototypes due to the presence of noise, PCM has no chance to recover and produce a fine partition. This paper proposes a two-stage c-means clustering algorithm to tackle with most problems enumerated above. In the first stage called initialization, FCM with two modifications is performed: (1) extra cluster added for noisy data; (2) extra variable and constraint added to handle clusters of various diameters. In the second stage, a modified PCM algorithm is carried out, which also contains the cluster width tuning mechanism based on which it adaptively updates the possibilistic penalty terms. The proposed algorithm has less parameters than PCM when the number of clusters is c > 2. Numerical evaluation involving synthetic and standard test data sets proved the advantages of the proposed clustering model.},
	keywords = {Clustering; c-means clustering; probabilistic partition; possibilistic partition; self-tuning algorithms; parameter reduction},
	year = {2019},
	eissn = {1793-6411},
	pages = {142-158},
	orcid-numbers = {Lefkovits, Szidónia/0000-0002-7903-1111}
}

@article{MTMT:2992199,
	title = {Application of fuzzy and possibilistic c-means clustering models in blind speaker clustering},
	url = {https://m2.mtmt.hu/api/publication/2992199},
	author = {Gosztolya, Gábor and Szilágyi, László},
	doi = {10.12700/aph.12.7.2015.7.3},
	journal-iso = {ACTA POLYTECH HUNG},
	journal = {ACTA POLYTECHNICA HUNGARICA},
	volume = {12},
	unique-id = {2992199},
	issn = {1785-8860},
	year = {2015},
	eissn = {1785-8860},
	pages = {41-56},
	orcid-numbers = {Gosztolya, Gábor/0000-0002-2864-6466}
}

@article{MTMT:2698866,
	title = {Generalization rules for the suppressed fuzzy c-means clustering algorithm},
	url = {https://m2.mtmt.hu/api/publication/2698866},
	author = {Szilágyi, László and Szilágyi, Sándor Miklós},
	doi = {10.1016/j.neucom.2014.02.027},
	journal-iso = {NEUROCOMPUTING},
	journal = {NEUROCOMPUTING},
	volume = {139},
	unique-id = {2698866},
	issn = {0925-2312},
	abstract = {Intending to achieve an algorithm characterized by the quick convergence of hard c-means (HCM) and finer partitions of fuzzy c-means (FCM), suppressed fuzzy c-means (s-FCM) clustering was designed to augment the gap between high and low values of the fuzzy membership functions. Suppression is produced via modifying the FCM iteration by creating a competition among clusters: for each input vector, lower degrees of membership are proportionally reduced, being multiplied by a previously set constant suppression rate, while the largest fuzzy membership grows to maintain the probabilistic constraint. Even though so far it was not treated as an optimal algorithm, it was employed in a series of applications, and reported to be accurate and efficient in various clustering problems. In this paper we introduce some generalized formulations of the suppression rule, leading to an infinite number of new clustering algorithms. Further on, we identify the close relation between s-FCM clustering models and the so-called FCM algorithm with generalized improved partition (GIFP-FCM). Finally we reveal the constraints under which the generalized s-FCM clustering models minimize the objective function of GIFP-FCM, allowing us to call our suppressed clustering models optimal. Based on a large amount of numerical tests performed in multidimensional environment, several generalized forms of suppression proved to give more accurate partitions than earlier solutions, needing significantly less iterations than the conventional FCM.},
	year = {2014},
	eissn = {1872-8286},
	pages = {298-309}
}

@inproceedings{MTMT:3344749,
	title = {Fuzzy-possibilistic product partition: A novel robust approach to c-means clustering},
	url = {https://m2.mtmt.hu/api/publication/3344749},
	author = {Szilágyi, László},
	booktitle = {Modeling Decisions for Artificial Intelligence},
	doi = {10.1007/978-3-642-22589-5_15},
	unique-id = {3344749},
	abstract = {One of the main challenges in the field of c-means clustering 
		models is creating an algorithm that is both accurate and 
		robust. In the absence of outlier data, the conventional 
		probabilistic fuzzy c-means (FCM) algorithm, or the latest 
		possibilistic-fuzzy mixture model (PFCM), provide highly 
		accurate partitions. However, during the 30-year history of 
		FCM, the researcher community of the field failed to produce 
		an algorithm that is accurate and insensitive to outliers at 
		the same time. This paper introduces a novel mixture 
		clustering model built upon probabilistic and possibilistic 
		fuzzy partitions, where the two components are connected to 
		each other in a qualitatively different way than they were in 
		earlier mixtures. The fuzzy-possibilistic product partition c-
		means (FP3CM) clustering algorithm seems to fulfil the initial 
		requirements, namely it successfully suppresses the effect of 
		outliers situated at any finite distance and provides 
		partitions of high quality.},
	year = {2011},
	pages = {150-161}
}