[Zurück]

M. Bögl, W. Aigner, P. Filzmoser, T. Lammarsch, S. Miksch, A. Rind:
"Visual Analytics for Model Selection in Time Series Analysis";
IEEE Transactions on Visualization and Computer Graphics, 19 (2013), 12; S. 2237 - 2246.

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.

Visual analytics, coordinated & multiple views, model selection, time series analysis, visual interaction

http://dx.doi.org/10.1109/TVCG.2013.222

http://publik.tuwien.ac.at/files/PubDat_220251.pdf

Projektleitung Silvia Miksch:
CVAST: Centre for Visual Analytics Science and Technology (Laura Bassi Centre of Expertise)

Projektleitung Silvia Miksch:
HypoVis: Modellierung von Hypothesen mit Visual Analytics Methoden zur Analyse der Vergangenheit und der Vorhersage der Zukunft