A comparison of the classification capabilities of the 1-dimensional kohonen neural network with two pratitioning and three hierarchical cluster analysis algorithms

Waller, Niels G.; Kaiser, Heather A.; Illian, Janine; Manry, Mike

doi:10.1007/bf02295433

Cited by 62 publications

(72 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Conclusions seem to be ambivalent as different authors point to different conclusions, and no definitive results have emerged. Some authors (Flexer 1999;Balakrishnan, Cooper et al 1994;Waller, Kaiser et al 1998) suggest that SOM performs equal or worst than statistical approaches, while other authors conclude the opposite (Openshaw and Openshaw 1997;Openshaw, Blake et al 1995).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-organizing Maps as Substitutes for K-Means Clustering

Bação¹,

Lobo²,

Paìnho³

2005

Lecture Notes in Computer Science

198

View full text Add to dashboard Cite

Abstract. One of the most widely used clustering techniques used in GISc problems is the k-means algorithm. One of the most important issues in the correct use of k-means is the initialization procedure that ultimately determines which part of the solution space will be searched. In this paper we briefly review different initialization procedures, and propose Kohonen's SelfOrganizing Maps as the most convenient method, given the proper training parameters. Furthermore, we show that in the final stages of its training procedure the Self-Organizing Map algorithms is rigorously the same as the kmeans algorithm. Thus we propose the use of Self-Organizing Maps as possible substitutes for the more classical k-means clustering algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

“…There have been a number of tests comparing SOM's with k-means (Balakrishnan, Cooper et al1994;Openshaw and Openshaw 1997;Waller, Kaiser et al 1998). Conclusions seem to be ambivalent as different authors point to different conclusions, and no definitive results have emerged.…”

Section: Introductionmentioning

confidence: 99%

Self-organizing Maps as Substitutes for K-Means Clustering

Bação¹,

Lobo²,

Paìnho³

2005

Lecture Notes in Computer Science

198

View full text Add to dashboard Cite

show abstract

“…It is widely recognized in the literature that the performance of the k-means method depends largely on the initial seeds used to begin the clustering process [19,44,45]. Steinley [46] cautions about the starting seeds used in the k-means procedure and notes that researchers have often chosen to use starting seeds from a hierarchical method like Ward's minimum variance to obtain the starting seeds for the k-means method [47,48]. The results from the Ward's method analysis were refined FVFlanduse US farmland should be devoted to producing food and not fuel.…”

Section: Cluster Analysismentioning

confidence: 99%

Greenhouse gas emission reductions as a motivator of e85 purchases across market segments

et al. 2012

View full text Add to dashboard Cite

Background: Climate change has become a concern of both policy makers and consumers. Transportation constitutes a key source of greenhouse gas (GHG) emissions; hence, alternative transportation fuels with reduced GHG emissions are of increasing interest as a potential strategy for decreasing emissions. However, consumer views on achieving emission reductions through the use of alternative fuels have not been widely studied. Understanding consumer preferences related to alternative fuels is relevant as new fuel options become available. Methods: This study uses a two-step cluster analysis of opinion variables to segment consumers into four market segments (Potential activists, Environmentals, Neutrals, and National interests). Cluster profiles are examined based on demographics and opinion variables related to concerns about national security, food versus fuel, perceived effects of personal actions, perceived effects of other's actions, and environmental issues. Willingness to pay (WTP) for reductions in GHG emissions through purchases of ethanol blends is estimated via conjoint analysis from a national survey. Results: Estimates reveal that WTP varies in significance and magnitude across the four segments. In particular, the Environmentals market cluster is the only cluster consistently willing to pay a premium for emission reductions.

show abstract

“…In addition, the representation of the data in a SOM provides a means for swiftly visualizing trends and tendencies within complex data. (For more about the Kohonen SOM, see Balakrishan, Cooper, Jacob, & Lewis, 1994;Murtagh & Hernandez-Pajares, 1995;Ripley, 1996;or Waller, Kaiser, Illian, & Manry, 1998).…”

Section: Kohonen Self-organizing Mapsmentioning

confidence: 99%

Automated Tools for Subject Matter Expert Evaluation of Automated Scoring

Williamson

Bejar

Sax³

2004

ETS Research Report Series

View full text Add to dashboard Cite

As automated scoring of complex constructed-response examinations reaches operational status, the process of evaluating the quality of resultant scores, particularly in contrast to scores of expert human graders, becomes as complex as the data itself. Using a vignette from the Architectural Registration Examination (ARE), this paper explores the potential utility of classification and regression trees (CART) and Kohonen self-organizing maps (SOM) as tools to facilitate subject matter expert (SME) examination of the fine-grained (feature level) quality of automated scores for complex data, with implications for the validity of the resultant scores. The paper explores both supervised and unsupervised learning techniques, the former being represented by CART (Breiman, Friedman, Olshen, & Stone, 1984) and the latter by SOM (Kohonen, 1989). Three applications comprise this investigation, the first of which suggests that CART can facilitate efficient and economical identification of specific elements of complex solutions that contribute to automated and human score discrepancies. The second application builds on the first by exploring CART's value for efficiently and accurately automating case selection for human intervention to ensure score validity. The final application explores the potential for SOM to reduce the need for SMEs in evaluating automated scoring. While both supervised and unsupervised methodologies examined were found to be promising tools for facilitating SME roles in maintaining and improving the quality of automated scoring, such applications remain unproven and further studies are necessary to establish the reliability of these techniques.

show abstract

A comparison of the classification capabilities of the 1-dimensional kohonen neural network with two pratitioning and three hierarchical cluster analysis algorithms

Abstract: neural networks, Kohonen models, cluster analysis,

Cited by 62 publications

References 38 publications

Self-organizing Maps as Substitutes for K-Means Clustering

Self-organizing Maps as Substitutes for K-Means Clustering

Greenhouse gas emission reductions as a motivator of e85 purchases across market segments

Automated Tools for Subject Matter Expert Evaluation of Automated Scoring

Contact Info

Product

Resources

About