K-means clustering: a half-century synthesis.

By D. Steinley. British Journal of Mathematical & Statistical Psychology, 2006

1,042 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e25df10f4a150ca1f6a760601bd07d20378f3a89

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Work-nonwork boundary management profiles: A person-centered approach (2012, neutral): “K-means clustering (Steinley, 2006) requires that the number of clusters be specified.”
Performance Profiles based on Archetypal Athletes (2012, methodology): “Archetypal analysis is part of the class of k-prototypes-like algorithms (k-means, k-median, fuzzy k-means, etc.; see, e.g., Steinley, 2006; Leisch, 2006).”
Clustering algorithms: A comparative approach (2016, background): “In addition, the k-means is not particularly recommended in cases where the clusters do not show convex distribution or have very different sizes [59, 60].”
Analysis of Multivariate Social Science Data (2nd ed.) (2011, methodology): “For example, in Chapter 2 on cluster analysis the authors state that nonhierarchical methods “are more difficult to carry out and are less commonly used” (p. 20) even though K-means cluster analysis is clearly an extremely popular nonhierarchical method nowadays (e.g., Steinley, 2006).”
Grouped Patterns of Heterogeneity in Panel Data (2015, background): “This implies that the estimator is asymptotically equivalent to an infeasible least-squares target, even when T diverges (polynomially) more slowly than N .”
A Distributional Framework for Matched Employer Employee Data (2019, methodology): “clustering algorithm we rely on is widely used in a number of fields, and efficient computational routines exist (Steinley, 2006).”
A measure of spatial stratified heterogeneity (2016, methodology): “Examples include Kmeans rouping (Steinhaus, 1957; MacQueen, 1967; Steinley, 2006) and egression trees (Breiman et al., 1984), which are implemented n extensively used software packages, ARCGIS (©Esri Inc.) and /SPODT.”
Recovering the number of clusters in data sets with noise features using feature rescaling factors (2015, methodology): “active field of research [7, 1, 22, 29], but due to the lack of a generally accepted definition of what a “cluster” is there are no unified standards against which it can be assessed.”
Ecologically based definition of seasons clarifies predator–prey interactions (2013, methodology): “Range standardisation (i.e. zi 5 (xi 2 min(x))/(max(x) 2 min(x))) is the recommended standardisation procedure for clustering (Steinley 2006).”