[Back]

C. Bors, M. Bögl, T. Gschwandtner, S. Miksch:
"Visual Support for Rastering of Unequally Spaced Time Series";
Talk: 10th International Symposium on Visual Information Communication and Interaction, Bangkok (invited); 2017-08-14 - 2017-08-16; in: "Proceedings of the 10th International Symposium on Visual Information Communication and Interaction", R. Biuk-Aghai, J. Li, S. Takahashi (ed.); ACM International Conference Proceeding Series, ACM New York, NY, USA (2017), ISBN: 978-1-4503-5292-5; 53 - 57.

Preprocessing is a mandatory first step to make data usable for analysis. While in time series analysis many established methods require data that are sampled in regular time intervals, in practice sensors may sample data at varying interval lengths. Time series rastering is the process of aggregating unequally spaced time series into equal interval lengths. In this paper we discuss critical aspects in the context of time series rastering, and we present a visual design which supports the parametrization of the rastering transformation, communicates the introduced uncertainties and quality issues, and facilitates the comparison of alternative rastering outcomes to achieve optimal results.

uncertainty, time series analysis, rastering, data quality

http://dx.doi.org/10.1145/3105971.3105984

http://publik.tuwien.ac.at/files/publik_260983.pdf

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

Project Head Silvia Miksch:
Visuelle Segmentierung und Labeling multivariater Zeitserien