Publications

On sketch-based selections from scatterplots using KDE, compared to Mahalanobis and CNN brushing

C. Fan and H. Hauser

Abstract

"Fast and accurate brushing is crucial in visual data exploration and sketch-based solutions are successful methods. In this paper, we detail a solution, based on kernel density estimation (KDE), which computes a data subset selection in a scatterplot from a simple click-and-drag interaction. We explain, how this technique relates to two alternative approaches, i.e., Mahalanobis brushing and CNN brushing. To study this relation, we conducted two user studies and present both a quantitative three-fold comparison as well as additional details about the prevalence of all possible cases in that each technique succeeds/fails. With this, we also provide a comparison between empirical modeling and implicit modeling by deep learning in terms of accuracy, efficiency, generality and interpretability."

C. Fan and H. Hauser, "On sketch-based selections from scatterplots using KDE, compared to Mahalanobis and CNN brushing," IEEE Computer Graphics and Applications, pp. 1-13, 2021. doi:10.1109/MCG.2021.3097889
[BibTeX]

"Fast and accurate brushing is crucial in visual data exploration and sketch-based solutions are successful methods. In this paper, we detail a solution, based on kernel density estimation (KDE), which computes a data subset selection in a scatterplot from a simple click-and-drag interaction. We explain, how this technique relates to two alternative approaches, i.e., Mahalanobis brushing and CNN brushing. To study this relation, we conducted two user studies and present both a quantitative three-fold comparison as well as additional details about the prevalence of all possible cases in that each technique succeeds/fails. With this, we also provide a comparison between empirical modeling and implicit modeling by deep learning in terms of accuracy, efficiency, generality and interpretability."
@article{brushingComparison,
author={Fan, Chaoran and Hauser, Helwig},
journal={IEEE Computer Graphics and Applications},
title={On sketch-based selections from scatterplots using KDE, compared to Mahalanobis and CNN brushing},
year={2021},
volume={},
number={},
pages={1-13},
doi={10.1109/MCG.2021.3097889},
abstract = {"Fast and accurate brushing is crucial in visual data exploration and sketch-based solutions are successful methods. In this paper, we detail a solution, based on kernel density estimation (KDE), which computes a data subset selection in a scatterplot from a simple click-and-drag interaction. We explain, how this technique relates to two alternative approaches, i.e., Mahalanobis brushing and CNN brushing. To study this relation, we conducted two user studies and present both a quantitative three-fold comparison as well as additional details about the prevalence of all possible cases in that each technique succeeds/fails. With this, we also provide a comparison between empirical modeling and implicit modeling by deep learning in terms of accuracy, efficiency, generality and interpretability."},
pdf = "pdfs/Fan-2021-brushingComparison.pdf",
images = "images/Fan-2021-brushingComparison.png",
thumbnails = "images/Fan-2021-brushingComparison.png",
}
projectidprojectid

Media

Downloads

Full paper [PDF]