Fuzzy c-means clustering of incomplete data

Abstract

The problem of clustering a real s-dimensional data set X={x(1 ),,,,,x(n)} subset R(s) is considered. Usually, each observation (or datum) consists of numerical values for all s features (such as height, length, etc.), but sometimes data sets can contain vectors that are missing one or more of the feature values. For example, a particular datum x(k) might be incomplete, having the form x(k)=(254.3, ?, 333.2, 47.45, ?)(T), where the second and fifth feature values are missing. The fuzzy c-means (FCM) algorithm is a useful tool for clustering real s-dimensional data, but it is not directly applicable to the case of incomplete data. Four strategies for doing FCM clustering of incomplete data sets are given, three of which involve modified versions of the FCM algorithm. Numerical convergence properties of the new algorithms are discussed, and all approaches are tested using real and artificially generated incomplete data sets.

Linear Fuzzy Clustering Techniques With Missing Values and Their Application to Local Principal Component Analysis

“…Timm et al [11] also proposed similar techniques and reported that the simple approach of ignoring the missing values gave fuzzier membership assignments than the strategy of replacing the missing values with the averages. Other observations such as the convergence property and the initialization problem are discussed in [12].…”

Three-Dimensional Joint Inversion of Gravity and Magnetic Anomalies Using Fuzzy C-means Clustering

“…The parameter q controls the degree of fuzziness of the resulting membership functions. In this study, we set q = 2.0, which is widely accepted as a good choice (Hathaway and Bezdek, 2001). Teranishi et al (2013) formulated the joint inversion algorism by incorporateing equation (1) with (2) and considered a coupling measure based on the FCM clustering as a petrophysical similarity regularization term which combined two model parameters and they obtained the following equation;…”

Fuzzy Kernel k-Medoids algorithm for anomaly detection problems

“…It is believed to be more robust to outliers than traditional k-means technique and it also can deal with overlapping clusters. One of the most popular fuzzy clustering method is Fuzzy C-Means (FCM), proposed by Dunn in [10] and later modified in [7,[11][12][13][14]. FCM classifies object where each of them has relative membership value for each group.…”