A SURVEY ON AUTOMATED METHODS FOR EXPLORATORY VISUAL ANALYSIS

PhD Qualifying Examination


Title: "A SURVEY ON AUTOMATED METHODS FOR EXPLORATORY VISUAL ANALYSIS"

by

Mr. Haotian LI


Abstract:

Exploratory visual analysis (EVA) provides data analysts with a graphical 
approach to inspect and understand the unfamiliar dataset intuitively. It 
is widely adopted nowadays since it can preserve more details of the data 
than statistical analysis. However, during EVA, users face critical 
challenges on data selection and visualization creation due to the large 
search space of data and visual designs. Users have to spend considerable 
time exhausting different subsets of data and designing effective 
visualizations for them to discover potentially interesting data facts. To 
mitigate this issue, researchers have proposed various automated 
approaches that leverage the computational power of machines to reduce the 
manual efforts in EVA.

In this article, we aim to systematically review the automated methods for 
EVA. We first review how existing methods address the two challenges, 
i.e., data selection and visualization creation. Based on the 
functionalities of reviewed studies, we summarize that the target of 
developing automated methods for EVA is to offer users effortless and 
adaptive analysis. Finally, by comparing existing studies with the target, 
potential future directions are identified and discussed.


Date:			Friday, 3 December 2021

Time:                  	3:00pm - 5:00pm

Venue:			Room 3494
 			(lifts 25/26)

Committee Members:	Prof. Huamin Qu (Supervisor)
 			Prof. Dik-Lun Lee (Chairperson)
 			Dr. Yangqiu Song
 			Prof. Xiaofang Zhou


**** ALL are Welcome ****