A New Approach for Exploring Multivariate Data: Self-Organising Maps

Bock, Timothy

doi:10.1177/147078530404600202

Cited by 2 publications

(8 citation statements)

References 23 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way researchers have started to position this method is by comparing the results of self-organising maps to the more conventional approach of k-means cluster analysis. Recently, Curry et al (2003), Bock (2004) and Kiang et al (2006) each reported such comparisons, seeking to substantiate the benefits of using self-organising maps. Kiang et al (2006: 44) concluded from a strict comparison of the approaches that self-organising maps were 'at least as good a classification analysis as K-means'.…”

Section: Segmenting and Visualising Public Orientations Using Self-ormentioning

confidence: 99%

“…As discussed earlier, some researchers such as Bock (2004) and Curry et al (2003) treat selecting the number of nodes on the map as selecting the number of segments that will be profiled. Bock (2004) concluded this process of selecting map dimensions and a cluster solution could benefit from more objective indicators. The approach we used to abstract the distinct segments involved first creating a moderately sized map, then engaging in an iterative process of viewing possible boundaries for orientations based on the results of a Davies-Bouldin index for cluster validity (1979) and interpreting the profile of possible solutions.…”

Section: Segmenting and Visualising Public Orientations Using Self-ormentioning

confidence: 99%

“…Using this software the orientation boundaries were illustrated based on the results of running a Davies-Bouldin index for cluster validity (1979). This is an extension to the processes followed by Curry et al (2003), Bock (2004) and Kiang et al (2006), in an effort to more objectively abstract the different segmentsorientations. This process is similar to that described by Vesanto and Alhoniemi (2000) in a technical paper about how to use self-organising maps to cluster data.…”

Section: Segmenting and Visualising Public Orientations Using Self-ormentioning

confidence: 99%

“…We delineated these orientations using self-organising maps, a relatively new analytical approach for segmenting responses profiles, which has proven useful for both segmenting and visualising response profiles (e.g. Curry et al 2003;Bock 2004;Kiang et al 2006). …”

mentioning

confidence: 99%

See 3 more Smart Citations

Exploring the orientations which characterise the likely public acceptance of low emission energy technologies

et al. 2010

View full text Add to dashboard Cite

There is a large body of research and development into the low emission energy technologies that has the potential to assist developed and developing countries transition to more sustainable energy systems. It has long been recognised that public perceptions can have a fundamental effect on the market for technology and this issue raises questions about the role society will play in developing a low emissions energy future. Understanding how the public will respond to the range of low emission energy technologies as part of a climate change mitigation package is therefore critical for researchers, policy makers and industry stakeholders. In the current research, we investigated the Australian public's likely acceptance of a range of low emission energy technologies by assessing the diverse 'orientations' that have emerged in response to low emission energy technologies. In a survey of two Australian states we measured the support for, and knowledge of, a range of low emission energy technologies. Using self-organising maps, a relatively new approach for segmenting response profiles, we identified that at least four distinct 'orientations' have emerged toward the issue and are characterising the likely acceptance of these technologies: 'Disengaged', 'Nuclear Oriented', 'Renewables Oriented', and 'Engaged'. The implications of these multiple public viewpoints are described for climate change mitigation policy and for future research into the social acceptance of alternative energy technologies.

show abstract

Section: Segmenting and Visualising Public Orientations Using Self-ormentioning

confidence: 99%

Section: Segmenting and Visualising Public Orientations Using Self-ormentioning

confidence: 99%

Section: Segmenting and Visualising Public Orientations Using Self-ormentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Exploring the orientations which characterise the likely public acceptance of low emission energy technologies

et al. 2010

View full text Add to dashboard Cite

show abstract

“…SOM clusters the data in a manner similar to cluster analysis but has an additional benefit of ordering the clusters and enabling the visualization of large numbers of clusters [16, 17]. This technique is particularly useful for the analysis of large datasets where similarity matching plays a very important role [4, 6].…”

Section: Introductionmentioning

confidence: 99%

The New and Computationally Efficient MIL-SOM Algorithm: Potential Benefits for Visualization and Analysis of a Large-Scale High-Dimensional Clinically Acquired Geographic Data

Oyana

Achenie

Heo

2012

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

The objective of this paper is to introduce an efficient algorithm, namely, the mathematically improved learning-self organizing map (MIL-SOM) algorithm, which speeds up the self-organizing map (SOM) training process. In the proposed MIL-SOM algorithm, the weights of Kohonen's SOM are based on the proportional-integral-derivative (PID) controller. Thus, in a typical SOM learning setting, this improvement translates to faster convergence. The basic idea is primarily motivated by the urgent need to develop algorithms with the competence to converge faster and more efficiently than conventional techniques. The MIL-SOM algorithm is tested on four training geographic datasets representing biomedical and disease informatics application domains. Experimental results show that the MIL-SOM algorithm provides a competitive, better updating procedure and performance, good robustness, and it runs faster than Kohonen's SOM.

show abstract

A New Approach for Exploring Multivariate Data: Self-Organising Maps

Cited by 2 publications

References 23 publications

Exploring the orientations which characterise the likely public acceptance of low emission energy technologies

Exploring the orientations which characterise the likely public acceptance of low emission energy technologies

The New and Computationally Efficient MIL-SOM Algorithm: Potential Benefits for Visualization and Analysis of a Large-Scale High-Dimensional Clinically Acquired Geographic Data

Contact Info

Product

Resources

About