A<i>k</i>-mean-directions Algorithm for Fast Clustering of Data on the Sphere

Maitra, Ranjan; Ramler, Ivan

doi:10.1198/jcgs.2009.08155

Cited by 32 publications

(30 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This requires package kmndirs (available from R-Forge, Maitra, Ramler, and Hornik 2012), which provides an R interface to a suitable modification of the C code for the k-meandirections algorithm made available as supplementary material to Maitra and Ramler (2010) at http://pubs.amstat.org/doi/suppl/10.1198/jcgs.2009.08155. This algorithm fol-lows the Hartigan-Wong approach to efficiently obtaining k-means partitions by repeatedly considering suitable single object moves (to clusters in the "live set") in an optimal transfer stage, and potentially updating prototypes and memberships of recently reallocated clusters in a quick transfer stage.…”

Section: Methods "Kmndirs"mentioning

confidence: 99%

“…In addition we use the two datasets "20 Newsgroups" and "Waveform" as employed by Tunali et al (2010), and the abstracts from the 2008 Joint Statistical Meetings as used by Maitra and Ramler (2010 …”

Section: Datamentioning

confidence: 99%

“…Note that these are not exact solvers: following common optimization terminology, a solver is an algorithm/code attempting to minimize the criterion function, and a "solution" is what a solver delivers, which is not even guaranteed to deliver a value close to the true minimum (see Section 4 for a performance comparison of the available solvers on a collection of benchmark data sets). Argument method can be a character string specifying one of the built-in solvers (a fixed-point and a genetic algorithm, and interfaces to two standalone solvers (CLUTO and Gmeans) and the C code implementing the k-mean-directions algorithm of Maitra and Ramler (2010)) which are discussed in detail below, a function to be taken as a user-defined method, or NULL (default). By default, the genetic algorithm is used for obtained hard partitions, and the fixed-point algorithm otherwise.…”

Section: Interfacementioning

confidence: 99%

See 2 more Smart Citations

Sphericalk-Means Clustering

Hornik¹,

Feinerer²,

Kober³

et al. 2012

J. Stat. Soft.

169

View full text Add to dashboard Cite

Clustering text documents is a fundamental task in modern data analysis, requiring approaches which perform well both in terms of solution quality and computational efficiency. Spherical k-means clustering is one approach to address both issues, employing cosine dissimilarities to perform prototype-based partitioning of term weight representations of the documents. This paper presents the theory underlying the standard spherical k-means problem and suitable extensions, and introduces the R extension package skmeans which provides a computational environment for spherical k-means clustering featuring several solvers: a fixed-point and genetic algorithm, and interfaces to two external solvers (CLUTO and Gmeans). Performance of these solvers is investigated by means of a large scale benchmark experiment.

show abstract

Section: Methods "Kmndirs"mentioning

confidence: 99%

Section: Datamentioning

confidence: 99%

Section: Interfacementioning

confidence: 99%

See 1 more Smart Citation

Sphericalk-Means Clustering

Hornik¹,

Feinerer²,

Kober³

et al. 2012

J. Stat. Soft.

169

View full text Add to dashboard Cite

show abstract

“…To define "near", a measure of distance, or, equivalently, a measure of similarity is needed. For text classification, cosine similarity is widely used (Knaus 1987;Iezzi et al 2014;Maitra and Ramler 2010). Cosine similarity between two vectors u and v is defined as…”

Section: A Modified Nearest Neighbor Approachmentioning

confidence: 99%

Three Methods for Occupation Coding Based on Statistical Learning

Gweon

Schonlau

Kaczmirek

et al. 2017

Journal of Official Statistics

View full text Add to dashboard Cite

Occupation coding, an important task in official statistics, refers to coding a respondent's text answer into one of many hundreds of occupation codes. To date, occupation coding is still at least partially conducted manually, at great expense. We propose three methods for automatic coding: combining separate models for the detailed occupation codes and for aggregate occupation codes, a hybrid method that combines a duplicate-based approach with a statistical learning algorithm, and a modified nearest neighbor approach. Using data from the German General Social Survey (ALLBUS), we show that the proposed methods improve on both the coding accuracy of the underlying statistical learning algorithm and the coding accuracy of duplicates where duplicates exist. Further, we find defining duplicates based on ngram variables (a concept from text mining) is preferable to one based on exact string matches.

show abstract

“…The spherical k-means algorithm provided by the R package "skmeans" [36] is used, which implements a simple k-means strategy based on the cosine distance:…”

mentioning

confidence: 99%

Clustering and Support Vector Regression for Water Demand Forecasting and Anomaly Detection

Candelieri

2017

Water

100

View full text Add to dashboard Cite

This paper presents a completely data-driven and machine-learning-based approach, in two stages, to first characterize and then forecast hourly water demand in the short term with applications of two different data sources: urban water demand (SCADA data) and individual customer water consumption (AMR data). In the first case, reliable forecasting can be used to optimize operations, particularly the pumping schedule, in order to reduce energy-related costs, while in the second case, the comparison between forecast and actual values may support the online detection of anomalies, such as smart meter faults, fraud or possible cyber-physical attacks. Results are presented for a real case: the water distribution network in Milan.

show abstract

Ak-mean-directions Algorithm for Fast Clustering of Data on the Sphere

Cited by 32 publications

References 26 publications

Sphericalk-Means Clustering

Sphericalk-Means Clustering

Three Methods for Occupation Coding Based on Statistical Learning

Clustering and Support Vector Regression for Water Demand Forecasting and Anomaly Detection

Contact Info

Product

Resources

About