The analysis of three-dimensional embeddings in Virtual Reality

The analysis of three-dimensional embeddings in Virtual Reality

Grisel, Bastiaan (TU Delft Electrical Engineering, Mathematics and Computer Science)

Eisemann, Elmar (mentor)
Vilanova Bartroli, Anna (graduation committee)
Brinkman, Willem-Paul (graduation committee)

Delft University of Technology

Computer Science | Data Science and Technology

2018-12-18

Dimensionality reduction algorithms transform high-dimensional datasets with many attributes per observation into lower-dimensional representations (called embeddings) such that the structure of the dataset is maintained as well as possible. In this research, the use of Virtual Reality (VR) to analyse these embeddings has been evaluated and compared to the analysis on a desktop computer. The rationale for using VR is two-fold: three-dimensional embeddings generally better preserve the structure of a high-dimensional dataset than two-dimensional embeddings and the analysis of three-dimensional embeddings is difficult on desktop monitors. A user study (n=29) has been conducted in which participants performed the common analysis task of cluster identification. The task has been performed using a two-dimensional embedding on a desktop computer, a three-dimensional embedding on a desktop computer and a three-dimensional embedding in Virtual Reality. On average, participants that had at least used VR once before could better and more consistently identify clusters in the VR experiments compared to other methods. Participants found it easier to analyse a three-dimensional embedding in VR compared to analysing it on a desktop computer.

virtual
reality
embedding
visualisation
data
high-dimensional

http://resolver.tudelft.nl/uuid:afad36f5-64c7-4969-9615-93d89b43e65f

Student theses

master thesis

© 2018 Bastiaan Grisel