Fuzzy Order Statistics and Their Application to Fuzzy Clustering

Kersten, P.R.

doi:10.21236/ada368624

Cited by 12 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we have addressed this issue by reducing the influence of outliers and noisy DOA observations through the use of observation weights. Alternatively, the non-robust Euclidean L 2 -norm distance could be replaced with more robust L p -norm distances [56], such as the L 1 -norm [57] or kernel-based distance measures [58]. One important point that we have not addressed so far is the question of computational complexity.…”

Section: Discussionmentioning

confidence: 99%

A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separation

2010

View full text Add to dashboard Cite

Time-frequency masking has evolved as a powerful tool for tackling blind source separation problems. In previous work, mask estimation was performed with the help of well-known standard cluster algorithms. Spatial observation vectors, extracted from a set of microphones, were grouped into separate clusters, each representing a particular source. However, most off-the-shelf clustering methods are not very robust to outliers or noise in the data. This lack of robustness often leads to incorrect localization and partitioning results, particularly for reverberant speech mixtures. To address this issue, we investigate the use of observation weights and context information as means to improve the clustering performance under reverberant conditions. While the observation weights improve the localization accuracy by ignoring noisy observations, context information smoothes the cluster membership levels by exploiting the highly structured nature of speech signals in the time-frequency domain. In a number of experiments, we demonstrate the superiority of the proposed method over conventional fuzzy clustering, both in terms of localization accuracy as well as speech separation performance.

show abstract

Section: Discussionmentioning

confidence: 99%

A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separation

2010

View full text Add to dashboard Cite

show abstract

“…Fuzzy order statistics and its applications, specially in fuzzy clustering, is studied by Kersten (1999). Chen (1995Chen ( , 2000 introduces a general framework of fuzzy analysis of statistical evidence methodologies for pattern classification and knowledge discovery.…”

Section: Some Other Fieldsmentioning

confidence: 99%

Trends in Fuzzy Statistics

Taheri

2016

AJS

View full text Add to dashboard Cite

show abstract

“…The well known Fuzzy c-Means (FCM) [3] algorithm can be used in the procedure of the adaptive threshold adjustment [4,5]. However, the resulting FCM cluster representatives (prototypes) are the linear statistics of data points which are known to be vulnerable to outliers [7]. Hence, in the presented approach we applied the robust partitioning method based on the fuzzy median (Fuzzy c-Medians, FCMed) [8].…”

Section: Estimation Of Amplitude Threshold With Median Fuzzy Clusteringmentioning

confidence: 99%

The Application of Median Fuzzy Clustering and Robust Weighted Averaging for Electronystagmography Signal Processing

Pander

Czabański

Przybyła

et al. 2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Abstract. The purpose of this paper is to present a robust approach to processing of electronystagmography (ENG) signal which contain saccades. The accurate saccade detection and localization allows for recognition of the optokinetic nystagmus (OKN), which is regarded as one of the important phenomena to be evaluated by ophthalmologists. The robust ENG processing consists in robust filtering of the signal to suppress outliers, robust fuzzy clustering to determine the amplitude threshold level for automatic saccade detection and robust averaging of similar optokinetic nystagmus cycles to estimate the nystagmus parameters. The proposed method was tested using the artificial as well as the real signals. The results show the usefulness of the proposed solution in the process of the OKN modeling.

show abstract

Fuzzy Order Statistics and Their Application to Fuzzy Clustering

Cited by 12 publications

References 0 publications

A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separation

A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separation

Trends in Fuzzy Statistics

The Application of Median Fuzzy Clustering and Robust Weighted Averaging for Electronystagmography Signal Processing

Contact Info

Product

Resources

About