Date of Award

12-18-2014

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Computer Science

First Advisor

Ying Zhu

Second Advisor

Scott Owen

Third Advisor

Ben Miller

Fourth Advisor

Yi Zhao

Fifth Advisor

Raj Sunderraman

Abstract

The amount of spatio-temporal data produced everyday has sky rocketed in the recent years due to the commercial GPS systems and smart devices. Together with this, the need for tools and techniques to analyze this kind of data have also increased. A major task of spatio-temporal data analysis is to discover relationships and patterns among spatially and temporally scattered events. However, most of the existing visualization techniques implement a top-down approach i.e, they require prior knowledge of existing patterns. In this dissertation, I present my novel visualization technique called Storygraph which supports bottom-up discovery of patterns. Since Storygraph presents and integrated view, analysis of events can be done with losing either of time or spatial contexts. In addition, Storygraph can handle spatio-temporal uncertainty making it ideal for data being extracted from text. In the subsequent chapters, I demonstrate the versatility and the effectiveness of the Storygraph along with case studies from my published works. Finally, I also talk about edge bundling in Storygraph to enhance the aesthetics and improve the readability of Storygraph.

DOI

https://doi.org/10.57709/6381718

Download

Share

COinS