A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling

Some state-of-the-art dimensionality reduction techniques are reviewed and investigated in this thesis. Dimensionality reduction techniques can be categorized inti two serving different purposes. The first category is to mitigate the computational load and to address the Curse-of-Dimensionality, and...

Full description

Saved in:
Bibliographic Details
Main Author: Wang, Wan Qiu
Other Authors: Chan Kap Luk
Format: Theses and Dissertations
Language:English
Published: 2011
Subjects:
Online Access:https://hdl.handle.net/10356/42687
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-42687
record_format dspace
spelling sg-ntu-dr.10356-426872023-07-04T16:13:52Z A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling Wang, Wan Qiu Chan Kap Luk School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Some state-of-the-art dimensionality reduction techniques are reviewed and investigated in this thesis. Dimensionality reduction techniques can be categorized inti two serving different purposes. The first category is to mitigate the computational load and to address the Curse-of-Dimensionality, and the second category is to model the data spread or manifold. ISOMAP and LLE techniques are developed for the second purpose, and both of them are embedding techniques. By means of embedding, some data points in a higher dimensional space can be mapped into a lower dimensional space, provided that the pairwise distances are kept unchanged or within a small tolerant range. Some conven- tional category one techniques, such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), are developed from variance analysis, but they also can be interpreted as embedding techniques through links to the metric Multidimensional Scaling (MDS). MASTER OF ENGINEERING (EEE) 2011-01-07T02:17:29Z 2011-01-07T02:17:29Z 2005 2005 Thesis Wang, W. Q. (2005). A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling. Master’s thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/42687 10.32657/10356/42687 en 129 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Wang, Wan Qiu
A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling
description Some state-of-the-art dimensionality reduction techniques are reviewed and investigated in this thesis. Dimensionality reduction techniques can be categorized inti two serving different purposes. The first category is to mitigate the computational load and to address the Curse-of-Dimensionality, and the second category is to model the data spread or manifold. ISOMAP and LLE techniques are developed for the second purpose, and both of them are embedding techniques. By means of embedding, some data points in a higher dimensional space can be mapped into a lower dimensional space, provided that the pairwise distances are kept unchanged or within a small tolerant range. Some conven- tional category one techniques, such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), are developed from variance analysis, but they also can be interpreted as embedding techniques through links to the metric Multidimensional Scaling (MDS).
author2 Chan Kap Luk
author_facet Chan Kap Luk
Wang, Wan Qiu
format Theses and Dissertations
author Wang, Wan Qiu
author_sort Wang, Wan Qiu
title A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling
title_short A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling
title_full A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling
title_fullStr A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling
title_full_unstemmed A study of dimensionality reduction as subspace data embedding linked by multidimensional scaling
title_sort study of dimensionality reduction as subspace data embedding linked by multidimensional scaling
publishDate 2011
url https://hdl.handle.net/10356/42687
_version_ 1772827135686213632