Statistical multivariate methods of analysis of data from biological texts and ontologies

Abstract

The research involves text mining of biological texts using statistical methods of classification and clustering. The classification involves the use of Linear Discriminant Analysis, LDA, Support Vector Machines, SVA and Multinomial Logistic Regression, MLR, LDA was found to perform the best. Non Linear Canonical Correlation, Analysis, NLCCA was also used in order to describe the information of the words of the texts, their gene ontology and Medical Subject Headings with only one dataset, with reduced number of variables. The clustering was based on a stochastic algorithm, namely Markov clustering (MCL) and represented the results to the end user in a 2d or 3d environment.

All items in National Archive of Phd theses are protected by copyright.

DOI
10.12681/eadd/18932
Handle URL
http://hdl.handle.net/10442/hedi/18932
ND
18932
Alternative title
Στατιστικές μέθοδοι πολυμεταβλητής ανάλυσης δεδομένων από βιολογικά κείμενα και οντολογίες
Author
Theodosiou, T. (Father's name: Georgios)
Date
2008
Degree Grantor
Aristotle University Of Thessaloniki (AUTH)
Committee members
Βακάλη Αθηνά
Αγγελής Ελευθέριος
Βλαχάβας Ιωάννης
Δαμιανού Χαράλαμπος
Θωμόπουλος Γεώργιος
Καρανίκας Κωνσταντίνος
Νικήτα Κωνσταντίνα
Discipline
Natural Sciences
Computer and Information Sciences
Keywords
Statistical multivariate analysis; Clustering; Classification; Biological texts; Biological ontologies
Country
Greece
Language
Greek
Description
191 σ., im.
Usage statistics
VIEWS
Concern the unique Ph.D. Thesis' views for the period 07/2018 - 07/2023.
Source: Google Analytics.
ONLINE READER
Concern the online reader's opening for the period 07/2018 - 07/2023.
Source: Google Analytics.
DOWNLOADS
Concern all downloads of this Ph.D. Thesis' digital file.
Source: National Archive of Ph.D. Theses.
USERS
Concern all registered users of National Archive of Ph.D. Theses who have interacted with this Ph.D. Thesis. Mostly, it concerns downloads.
Source: National Archive of Ph.D. Theses.
Related items (based on users' visits)