An evidential clustering algorithm by finding belief-peaks and disjoint neighborhoods

Gong, Chaoyu; Su, Zhi‐gang; Wang, Peihong; Wang, Qian

doi:10.1016/j.patcog.2020.107751

Cited by 21 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering is an important task of pattern recognition and machine learning, which divides objects into diferent clusters based on the similarity between patterns [14]. Hard clustering and fuzzy clustering methods have been used in many felds by their universality [15][16][17], but the clustering methods based on a single view ignore the information from multiple views [18].…”

Section: Introductionmentioning

confidence: 99%

A Belief Two-Level Weighted Clustering Method for Incomplete Pattern Based on Multiview Fusion

Zhao

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Incomplete pattern clustering is a challenging task because the unknown attributes of the missing data introduce uncertain information that affects the accuracy of the results. In addition, the clustering method based on the single view ignores the complementary information from multiple views. Therefore, a new belief two-level weighted clustering method based on multiview fusion (BTC-MV) is proposed to deal with incomplete patterns. Initially, the BTC-MV method estimates the missing data by an attribute-level weighted imputation method with k-nearest neighbor (KNN) strategy based on multiple views. The unknown attributes are replaced by the average of the KNN. Then, the clustering method based on multiple views is proposed for a complete data set with estimations; the view weights represent the reliability of the evidence from different source spaces. The membership values from multiple views, which indicate the probability of the pattern belonging to different categories, reduce the risk of misclustering. Finally, a view-level weighted fusion strategy based on the belief function theory is proposed to integrate the membership values from different source spaces, which improves the accuracy of the clustering task. To validate the performance of the BTC-MV method, extensive experiments are conducted to compare with classical methods, such as MI-KM, MI-KMVC, KNNI-FCM, and KNNI-MFCM. Results on six UCI data sets show that the error rate of the BTC-MV method is lower than that of the other methods. Therefore, it can be concluded that the BTC-MV method has superior performance in dealing with incomplete patterns.

show abstract

Section: Introductionmentioning

confidence: 99%

A Belief Two-Level Weighted Clustering Method for Incomplete Pattern Based on Multiview Fusion

Zhao

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…[25] to deal with the uncertain cluster structure by introducing imprecise (meta) classes. Many evidential clustering methods have been designed for credal partitions [26][27][28]. Evidential c-means (ECM) [26] is a direct generalization of FCM in the framework of belief functions.…”

Section: Introductionmentioning

confidence: 99%

Evidential prototype-based clustering based on transfer learning

Zhou

Guo

Atkinson

2022

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

“…The concept of credal partitions defined in the framework of belief functions is first proposed by Denoeux et.al. [3] to deal with the uncertain cluster structure, and following many evidential clustering methods have been designed and widely applied [8,5]. In this paper, we combine the idea of evidential clustering and transfer learning to develop a new clustering method, named transfer evidential c-means (TECM), for insufficient and uncertain data.…”

Section: Introductionmentioning

confidence: 99%

Evidential Clustering Based on Transfer Learning

Zhou

Guo

Atkinson

2021

Belief Functions: Theory and Applications

View full text Add to dashboard Cite

Clustering is an essential part of data mining, which can be used to organize data into sensible groups. Among the various clustering algorithms, the prototype-based methods have been most popularly applied due to the easy implementation, simplicity and efficiency. However, most of them such as the c-means clustering are no longer effective when the data is insufficient and uncertain. While the data for the current clustering task may be sparse, there is usually some useful knowledge available in the related scenes. Transfer learning can be adopted to address such cross domain learning problems by using information from data in a related domain and transferring that data/knowledge to the target task. The inconsistency between different domains can increase the uncertainty in the data. To handle the insufficiency and uncertainty problems in the clustering task simultaneously, a prototype-based evidential transfer clustering algorithm, named transfer evidential c-means (TECM), is introduced in the framework of belief functions. The proposed algorithm employs the cluster prototypes of the source data as references to guide the clustering process of the target data. The experimental studies are presented to demonstrate the advantages of TECM in both synthetic and real-world data sets.

show abstract

An evidential clustering algorithm by finding belief-peaks and disjoint neighborhoods

Cited by 21 publications

References 29 publications

A Belief Two-Level Weighted Clustering Method for Incomplete Pattern Based on Multiview Fusion

A Belief Two-Level Weighted Clustering Method for Incomplete Pattern Based on Multiview Fusion

Evidential prototype-based clustering based on transfer learning

Evidential Clustering Based on Transfer Learning

Contact Info

Product

Resources

About