Publications

Towards quantitative visual analytics with structured brushing and linked statistics

S. Rado┼í, R. Splechtna, K. Matkovi─ç, M. Juras, E. Gr├Âller, and H. Hauser

Abstract

Until now a lot of visual analytics predominantly delivers qualitative results—based, for example, on a continuous color map or a detailed spatial encoding. Important target applications, however, such as medical diagnosis and decision making, clearly benefit from quantitative analysis results. In this paper we propose several specific extensions to the well-established concept oflinking&brushing in order to make the analysis results more quantitative. We structure the brushing space in order to improvethe reproducibility of the brushing operation, e.g., by introducing the percentile grid. We also enhance the linked visualization with overlaid descriptive statistics to enable a more quantitative reading of the resulting focus+context visualization. Addition-ally, we introduce two novel brushing techniques: the percentile brush and the Mahalanob is brush. Both use the underlying data to support statistically meaningful interactions with the data. We illustrate the use of the new techniques in the context of two case studies, one based on meteorological data and the other one focused on data from the automotive industry where we evaluate a shaft design in the context of mechanical power transmission in cars.

S. Rado┼í, R. Splechtna, K. Matkovi─ç, M. Juras, E. Gr├Âller, and H. Hauser, "Towards quantitative visual analytics with structured brushing and linked statistics," Computer Graphics Forum, vol. 35, iss. 3, p. 251ÔÇô260, 2016.
[BibTeX]

Until now a lot of visual analytics predominantly delivers qualitative results—based, for example, on a continuous color map or a detailed spatial encoding. Important target applications, however, such as medical diagnosis and decision making, clearly benefit from quantitative analysis results. In this paper we propose several specific extensions to the well-established concept oflinking&brushing in order to make the analysis results more quantitative. We structure the brushing space in order to improvethe reproducibility of the brushing operation, e.g., by introducing the percentile grid. We also enhance the linked visualization with overlaid descriptive statistics to enable a more quantitative reading of the resulting focus+context visualization. Addition-ally, we introduce two novel brushing techniques: the percentile brush and the Mahalanob is brush. Both use the underlying data to support statistically meaningful interactions with the data. We illustrate the use of the new techniques in the context of two case studies, one based on meteorological data and the other one focused on data from the automotive industry where we evaluate a shaft design in the context of mechanical power transmission in cars.
@ARTICLE {radovs2016towards,
author = "Rado{\v{s}}, Sanjin and Splechtna, Rainer and Matkovi{\'c}, K and Juras, M and Gr{\"o}ller, Eduard and Hauser, Helwig",
title = "Towards quantitative visual analytics with structured brushing and linked statistics",
journal = "Computer Graphics Forum",
year = "2016",
volume = "35",
number = "3",
pages = "251--260",
abstract = "Until now a lot of visual analytics predominantly delivers qualitative results—based, for example, on a continuous color map or a detailed spatial encoding. Important target applications, however, such as medical diagnosis and decision making, clearly benefit from quantitative analysis results. In this paper we propose several specific extensions to the well-established concept oflinking&brushing in order to make the analysis results more quantitative. We structure the brushing space in order to improvethe reproducibility of the brushing operation, e.g., by introducing the percentile grid. We also enhance the linked visualization with overlaid descriptive statistics to enable a more quantitative reading of the resulting focus+context visualization. Addition-ally, we introduce two novel brushing techniques: the percentile brush and the Mahalanob is brush. Both use the underlying data to support statistically meaningful interactions with the data. We illustrate the use of the new techniques in the context of two case studies, one based on meteorological data and the other one focused on data from the automotive industry where we evaluate a shaft design in the context of mechanical power transmission in cars.",
pdf = "pdfs/Rado-_et_al-2016-Computer_Graphics_Forum.pdf",
thumbnails = "images/Rado-_et_al-2016-Computer_Graphics_Forum_1.png"
}
projectidprojectid

Downloads

Full paper [PDF]