Dimension Reduction Techniques in Morhpometrics
Dimension Reduction Techniques in Morhpometrics
diploma thesis (DEFENDED)

View/ Open
Permanent link
http://hdl.handle.net/20.500.11956/49451Identifiers
Study Information System: 73385
Collections
- Kvalifikační práce [11267]
Author
Advisor
Referee
Mráz, František
Faculty / Institute
Faculty of Mathematics and Physics
Discipline
Software Systems
Department
Department of Software and Computer Science Education
Date of defense
6. 9. 2011
Publisher
Univerzita Karlova, Matematicko-fyzikální fakultaLanguage
English
Grade
Good
Keywords (Czech)
Redukce dimenze, morfometrie, locally linear embedding, multidimensional scalingKeywords (English)
Dimensionality reduction, morphometrics, locally linear embedding, multidimensional scalingTato práce se zabývá aplikací metod redukce dimenze v antropologii a morfometrii. Zejména se sousteuje na nelinearní metody redukce dimenze. Práce zavádí nový postup nazývaný multipass redukce dimenze. Ukážeme, že pomocí multipass redukce dimenze lze vylepšit výsledky klasifikace a snížit počet dimenzí nutných pro klasifikaci pomocí klastrování.
This thesis centers around dimensionality reduction and its usage on landmark-type data which are often used in anthropology and morphometrics. In particular we focus on non-linear dimensionality reduction methods - locally linear embedding and multidimensional scaling. We introduce a new approach to dimensionality reduction called multipass dimensionality reduction and show that improves the quality of classification as well as requiring less dimensions for successful classification than the traditional singlepass methods.