Visualizing temporal cluster changes using Relative Density Self-Organizing Maps

Denny,; Williams, Graham J.; Christen, Peter

doi:10.1007/s10115-009-0264-5

Cited by 21 publications

(15 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These density estimations are then used to detect structural changes in clustering results. The evaluation using MISE showed that the proposed density estimation using KDE has higher accuracy than the density estimation proposed previously in [11], [27].…”

Section: Discussionmentioning

confidence: 76%

“…Therefore, in the original ReDSOM visualization [11], [27], the density estimation ρ h,M (v) centred at the location of a vector v in data space R d using map M is defined as the weighted count of prototype vectors m j of M in data space R d centred on vector v in the data space R d . The weight is calculated based on a Gaussian kernel function centred on vector v with radius/bandwidth h, as shown in Eq.…”

Section: Related Workmentioning

confidence: 99%

“…1 shows the plots of MISE MM and MISE P against QE of different maps size trained with the 2D dataset with three disjoint clusters shown in Fig. 2 Relative density RD M(τ2)/M(τ1) (v) is defined as the log ratio of the density estimation centred at the location of vector v on map M(τ 2 ) to the density estimation centred at the same location on the reference map M(τ 1 ) [11], [27]:…”

Section: Evaluation Of the Som-based Density Estimationmentioning

confidence: 99%

“…Therefore, the proposed density estimation can detect emerging clusters when it is used in the ReDSOM calculation. The usage of ReDSOM in analyzing real life datasets can be found in [27].…”

Section: Evaluation Of the Som-based Density Estimationmentioning

confidence: 99%

See 3 more Smart Citations

Relative density estimation using Self-Organizing Maps

Denny

2014

2014 International Conference on Advanced Computer Science and Information System

View full text Add to dashboard Cite

Organizations need knowledge of change, such as changes in customer purchasing behaviour, to adapt business strategies in response to changing circumstances. To understand what has changed, analysts have to be able to relate new knowledge acquired from a newer dataset to that acquired from an earlier dataset. This paper presents a method to detect changes in clustering structure over time. Discovering clustering changes can also be applied in other contexts, such as fraud detection and customer attrition analysis.The key contribution of this paper is the enhancement of the measurement of relative density using SOM. This measurement is used in the visualization method called Relative Density Self-Organizing Map (ReDSOM) to compare clustering structures from two snapshot datasets. This visualization provide means for analysts to visually identify and analyze various changes in the clustering structure, such as emerging clusters, disappearing clusters, splitting clusters, and merging clusters.These contributions have been evaluated using synthetic datasets, as well as real-life datasets from the World Bank. Experiments showed that the new measure is more sensitive in detecting changes in density.

show abstract

Section: Discussionmentioning

confidence: 76%

Section: Related Workmentioning

confidence: 99%

Section: Evaluation Of the Som-based Density Estimationmentioning

confidence: 99%

Section: Evaluation Of the Som-based Density Estimationmentioning

confidence: 99%

See 2 more Smart Citations

Relative density estimation using Self-Organizing Maps

Denny

2014

2014 International Conference on Advanced Computer Science and Information System

View full text Add to dashboard Cite

show abstract

“…Using a standard two-dimensional SOM for exploratory temporal structure analysis, processing of the time dimension has thus far been proposed along two suboptimal directions: computing separate maps per time unit (e.g. [6][7][8]) or one map on pooled panel data (e.g. [9][10][11]).…”

Section: Introductionmentioning

confidence: 99%

Self-organizing time map: An abstraction of temporal multivariate patterns

Sarlin

2013

Neurocomputing

View full text Add to dashboard Cite

This paper adopts and adapts Kohonen's standard Self-Organizing Map (SOM) for exploratory temporal structure analysis. The Self-Organizing Time Map (SOTM) implements SOM-type learning to one-dimensional arrays for individual time units, preserves the orientation with short-term memory and arranges the arrays in an ascending order of time. The twodimensional representation of the SOTM attempts thus twofold topology preservation, where the horizontal direction preserves time topology and the vertical direction data topology. This enables discovering the occurrence and exploring the properties of temporal structural changes in data. For representing qualities and properties of SOTMs, we adapt measures and visualizations from the standard SOM paradigm, as well as introduce a measure of temporal structural changes. The functioning of the SOTM, and its visualizations and quality and property measures, are illustrated on artificial toy data. The usefulness of the SOTM in a real-world setting is shown on poverty, welfare and development indicators.

show abstract

Contrast and change mining

Boettcher

2011

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Because the world with its markets, innovations, and customers is changing faster than ever before, the key to survival for businesses is the ability to detect, assess, and respond to changing conditions timely and intelligently. Understanding changes and reacting to or acting upon them therefore become a strategic issue not only for companies but also in many other domains. The corresponding need for knowledge has been answered by data mining research by proposing a multitude of methods for analyzing different aspects of change. This article provides an overview of recent works on methods for change analysis, thereby focusing on contrast mining and change mining, the two emerging subfields of contemporary data mining research.

show abstract

Visualizing temporal cluster changes using Relative Density Self-Organizing Maps

Cited by 21 publications

References 22 publications

Relative density estimation using Self-Organizing Maps

Relative density estimation using Self-Organizing Maps

Self-organizing time map: An abstraction of temporal multivariate patterns

Contrast and change mining

Contact Info

Product

Resources

About