Dimensionality Reduction Techniques for Compositional Data : An Empirical Study

Graduate Thesis Or Dissertation

Public Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/ks65hm632

Descriptions

Attribute Name	Values
Creator	George, Rogen
Abstract	Compositional data is a type of data where the features are non-negative and always sum to a constant. This type of data is frequently encountered in many ﬁelds such as microbiology, geology, economics and natural language processing. Compositional data has unique statistical properties that makes it difficult to apply standard dimensionality reduction techniques on it. Although there are multiple machine learning techniques that perform dimensionality reduction on compositional data, it is unclear how these methods perform relative to each other on difficult data sets. This thesis evaluates six difficult dimensionality reduction techniques on four difficult data sets. Although there was no single dominant algorithm among these techniques, we were able to observe trends that indicate which algorithms are more eﬀective on certain types of data.
Contributor	Wong, Weng-Keen
License	All rights reserved
Resource Type	Masters Thesis
Date Issued	2021-06-04
Degree Level	Master's
Degree Name	Master of Science (M.S.)
Degree Field	Computer Science
Degree Grantor	Oregon State University
Commencement Year	2021
Advisor	Wong, Weng-Keen
Committee Member	Park, Si Hong Fern, Xiaoli Z.
Academic Affiliation	Electrical Engineering and Computer Science
Rights Statement	In Copyright
Publisher	Oregon State University
Peer Reviewed	No
Language	English [eng]

Parents:

This work has no parents.

In Collection:

Thumbnail	Title	Date Uploaded	Visibility	Actions
	GeorgeRogen2021.pdf	2021-06-10	Public	Download