A new iterative fuzzy clustering approach for incomplete data

Cluster Analysis of Mixed and Missing Chronic Kidney Disease Data in KwaZulu-Natal Province, South Africa

“…Under multi-stage approaches, Zhang and Fang [30] carried out a study which showed the superiority of MI over SI or nonimputation in fuzzy clustering accuracy, while Goel and Tushir [31] showed the superiority of linear interpolation (single) imputation combined with the incorporation of the Mahalanobis distance in the clustering step over some other fuzzy clustering approaches. In a similar vein, Tuikkala et al [32] had earlier reported the superiority of advanced imputation techniques to basic ones like mean imputation in clustering gene expression data.…”

Fuzzy clustering‐based image segmentation techniques used to segment magnetic resonance imaging/computed tomography scan brain tissues: Comparative analysis

“…Various similarity measures like distance, connectivity, and intensity of a pixel can be used to cluster the data. Due to the vague definitions of the computed tomography (CT) scan/magnetic resonance imaging (MRI) images, fuzzy clustering approach has been successfully applied in the field of medical image segmentation 1‐8 . Fuzzy clustering, also known as soft clustering, is a form of clustering in which each data point present in the space can be a part of more than one cluster based on certain membership values.…”

“…In the same year, Jiang et al proposed a negative‐transfer resistant fuzzy clustering method with a shared cross‐domain transfer latent space 26 to successfully segment CT scan brain images It is the integration of negative‐transfer resistant and maximum mean discrepancy into the framework of FCM clustering. In the same year, an iterative Mahalanobis distance‐based fuzzy clustering was proposed to detect nonspherical clusters 8 …”