A simple method for visualizing labelled and unlabelled data in high-dimensional spaces

dc.contributor.authorGreene, J R
dc.date.accessioned2017-04-26T08:08:35Z
dc.date.available2017-04-26T08:08:35Z
dc.date.issued2004
dc.date.updated2016-01-07T08:33:27Z
dc.description.abstractThe low-dimensional visualisation of highdimensional data is a valuable way of detecting structure (such as clusters, and the presence of outliers) in the data, and avoiding some of the pitfalls of blind data manipulation. Projection based on principal component analysis is widely employed and often useful, but it is a variancepreserving projection which takes no account of class labels, and may, for this reason, hide significant structure. Here we present a very simple method which appears to yield useful visualizations for many datasets. It is based on a random search for a linear transformation, and projection into a twodimensional visual space, which maximises an objective measure of class separability in the visual space. The method, which can be thought of as a variant of projection pursuit with a novel interest measure, is demonstrated on datasets from the UCI Repository. Tentative interim results are also given for a proposed extension based on spectral clustering, for extending the method to unlabelled data.
dc.identifier.apacitation 2004. <i>A simple method for visualizing labelled and unlabelled data in high-dimensional spaces.</i> http://hdl.handle.net/11427/24219en_ZA
dc.identifier.chicagocitation. 2004. <i>A simple method for visualizing labelled and unlabelled data in high-dimensional spaces.</i> http://hdl.handle.net/11427/24219en_ZA
dc.identifier.citationGreene, JR. (2004). A simple method for visualizing labelled and unlabelled data in high-dimensional spaces, 45-49
dc.identifier.ris TY - AU - Greene, J R AB - The low-dimensional visualisation of highdimensional data is a valuable way of detecting structure (such as clusters, and the presence of outliers) in the data, and avoiding some of the pitfalls of blind data manipulation. Projection based on principal component analysis is widely employed and often useful, but it is a variancepreserving projection which takes no account of class labels, and may, for this reason, hide significant structure. Here we present a very simple method which appears to yield useful visualizations for many datasets. It is based on a random search for a linear transformation, and projection into a twodimensional visual space, which maximises an objective measure of class separability in the visual space. The method, which can be thought of as a variant of projection pursuit with a novel interest measure, is demonstrated on datasets from the UCI Repository. Tentative interim results are also given for a proposed extension based on spectral clustering, for extending the method to unlabelled data. DA - 2004 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2004 T1 - A simple method for visualizing labelled and unlabelled data in high-dimensional spaces TI - A simple method for visualizing labelled and unlabelled data in high-dimensional spaces UR - http://hdl.handle.net/11427/24219 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/24219
dc.identifier.vancouvercitation. 2004. <i>A simple method for visualizing labelled and unlabelled data in high-dimensional spaces.</i> http://hdl.handle.net/11427/24219en_ZA
dc.language.isoeng
dc.publisher.departmentDepartment of Electrical Engineeringen_ZA
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.publisher.institutionUniversity of Cape Town
dc.relation.ispartofProceedings of the 15th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Grabouw, South Africa
dc.titleA simple method for visualizing labelled and unlabelled data in high-dimensional spaces
dc.typeOther
uct.type.filetypeText
uct.type.filetypeImage
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Greene_Proceedings_2004.pdf
Size:
81.93 KB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections