Paper Info
Title
Visual analytics for model selection in time series analysis.
Abstract
Model selection in time series analysis is a challenging task for domain experts in many application areas such as epidemiology, economy, or environmental sciences. The methodology used for this task demands a close combination of human judgement and automated computation. However, statistical software tools do not adequately support this combination through interactive visual interfaces. We propose a Visual Analytics process to guide domain experts in this task. For this purpose, we developed the TiMoVA prototype that implements this process based on user stories and iterative expert feedback on user experience. The prototype was evaluated by usage scenarios with an example dataset from epidemiology and interviews with two external domain experts in statistics. The insights from the experts' feedback and the usage scenarios show that TiMoVA is able to support domain experts in model selection tasks through interactive visual interfaces with short feedback cycles.
Year
DOI
Venue
2013
10.1109/TVCG.2013.222
Visualization and Computer Graphics, IEEE Transactions
Keywords
Field
DocType
time series analysis,timova prototype,usage scenario,model selection,challenging task,external domain expert,iterative expert feedback,short feedback cycle,visual analytics process,domain expert,model selection task,interactive visual interface,iterative methods,statistical analysis,data models,time series,data visualisation,mathematical model,data analysis,visual analytics
Time series,Computer vision,Data modeling,Data visualization,User experience design,Computer science,Judgement,Visual analytics,Model selection,Artificial intelligence,User story,Machine learning
Journal
Volume
Issue
ISSN
19
12
1941-0506
Citations 
PageRank 
References 
15
0.66
10
Authors
6
Name
Order
Citations
PageRank
Markus Bögl1150.66
wolfgang aigner284251.72
Peter Filzmoser335344.09
Tim Lammarsch413210.06
Silvia Miksch52212174.85
Alexander Rind618714.75