Vector Representation of Arbitrary-sized Matrices

Title

Vector Representation of Arbitrary-sized Matrices

 Author

Wang, Jing (TU Delft Electrical Engineering, Mathematics and Computer Science)

Contributor

Tax, David (mentor)

Degree granting institution

Delft University of Technology

 Date

2017-07-13

 Abstract

In the thesis, we aim to compare matrices that can vary in size or shape, and their columns/rows are permutation invariant. We propose a general solution to such problem by using the vector representation to represent a matrix. Several feature representations are invented and investigated in the thesis, based on histogram, statistics, eigenvalues/singular values and multiple instance representation. They are used to identify structural patterns in an organization management problem based on questionnaire-like data. We further extend the work to other matrix-like data (e.g. graph data) to verify the efficacy of our proposed method.

 Subject

matrix representation
graph classification
management performance

 To reference this document use:

http://resolver.tudelft.nl/uuid:c306fbf2-f468-4d72-a57f-ff97a34cefca

 Part of collection

Student theses

 Document type

master thesis

 Rights

© 2017 Jing Wang
Files
PDF master_thesis.pdf 5 MB
Close viewer