Flow-based scatterplots for sensitivity analysis

Yu Hsuan Chan, Carlos D. Correa, Kwan-Liu Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

36 Citations (Scopus)

Abstract

Visualization of multi-dimensional data is challenging due to the number of complex correlations that may be present in the data but that are difficult to be visually identified. One of the main causes for this problem is the inherent loss of information that occurs when high-dimensional data is projected into 2D or 3D. Although 2D scatterplots are ubiquitous due to their simplicity and familiarity, there are not a lot of variations on their basic metaphor. In this paper, we present a new way of visualizing multidimensional data using scatterplots. We extend 2D scatterplots using sensitivity coefficients to highlight local variation of one variable with respect to another. When applied to a scatterplot, these sensitivities can be understood as velocities, and the resulting visualization resembles a flow field. We also present a number of operations, based on flow-field analysis, that help users navigate, select and cluster points in an efficient manner. We show the flexibility and generality of this approach using a number of multidimensional data sets across different domains.

Original languageEnglish (US)
Title of host publicationVAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings
Pages43-50
Number of pages8
DOIs
StatePublished - Dec 1 2010
Event1st IEEE Conference on Visual Analytics Science and Technology, VAST 10 - Salt Lake City, UT, United States
Duration: Oct 24 2010Oct 29 2010

Other

Other1st IEEE Conference on Visual Analytics Science and Technology, VAST 10
CountryUnited States
CitySalt Lake City, UT
Period10/24/1010/29/10

Fingerprint

Sensitivity analysis
Flow fields
Visualization

Keywords

  • Data transformations
  • Model fitting
  • Principal component analysis
  • Uncertainty

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Chan, Y. H., Correa, C. D., & Ma, K-L. (2010). Flow-based scatterplots for sensitivity analysis. In VAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings (pp. 43-50). [5652460] https://doi.org/10.1109/VAST.2010.5652460

Flow-based scatterplots for sensitivity analysis. / Chan, Yu Hsuan; Correa, Carlos D.; Ma, Kwan-Liu.

VAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings. 2010. p. 43-50 5652460.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chan, YH, Correa, CD & Ma, K-L 2010, Flow-based scatterplots for sensitivity analysis. in VAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings., 5652460, pp. 43-50, 1st IEEE Conference on Visual Analytics Science and Technology, VAST 10, Salt Lake City, UT, United States, 10/24/10. https://doi.org/10.1109/VAST.2010.5652460
Chan YH, Correa CD, Ma K-L. Flow-based scatterplots for sensitivity analysis. In VAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings. 2010. p. 43-50. 5652460 https://doi.org/10.1109/VAST.2010.5652460
Chan, Yu Hsuan ; Correa, Carlos D. ; Ma, Kwan-Liu. / Flow-based scatterplots for sensitivity analysis. VAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings. 2010. pp. 43-50
@inproceedings{1c6e2caccb4f4929a254ea6e0ae95d81,
title = "Flow-based scatterplots for sensitivity analysis",
abstract = "Visualization of multi-dimensional data is challenging due to the number of complex correlations that may be present in the data but that are difficult to be visually identified. One of the main causes for this problem is the inherent loss of information that occurs when high-dimensional data is projected into 2D or 3D. Although 2D scatterplots are ubiquitous due to their simplicity and familiarity, there are not a lot of variations on their basic metaphor. In this paper, we present a new way of visualizing multidimensional data using scatterplots. We extend 2D scatterplots using sensitivity coefficients to highlight local variation of one variable with respect to another. When applied to a scatterplot, these sensitivities can be understood as velocities, and the resulting visualization resembles a flow field. We also present a number of operations, based on flow-field analysis, that help users navigate, select and cluster points in an efficient manner. We show the flexibility and generality of this approach using a number of multidimensional data sets across different domains.",
keywords = "Data transformations, Model fitting, Principal component analysis, Uncertainty",
author = "Chan, {Yu Hsuan} and Correa, {Carlos D.} and Kwan-Liu Ma",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/VAST.2010.5652460",
language = "English (US)",
isbn = "9781424494866",
pages = "43--50",
booktitle = "VAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings",

}

TY - GEN

T1 - Flow-based scatterplots for sensitivity analysis

AU - Chan, Yu Hsuan

AU - Correa, Carlos D.

AU - Ma, Kwan-Liu

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Visualization of multi-dimensional data is challenging due to the number of complex correlations that may be present in the data but that are difficult to be visually identified. One of the main causes for this problem is the inherent loss of information that occurs when high-dimensional data is projected into 2D or 3D. Although 2D scatterplots are ubiquitous due to their simplicity and familiarity, there are not a lot of variations on their basic metaphor. In this paper, we present a new way of visualizing multidimensional data using scatterplots. We extend 2D scatterplots using sensitivity coefficients to highlight local variation of one variable with respect to another. When applied to a scatterplot, these sensitivities can be understood as velocities, and the resulting visualization resembles a flow field. We also present a number of operations, based on flow-field analysis, that help users navigate, select and cluster points in an efficient manner. We show the flexibility and generality of this approach using a number of multidimensional data sets across different domains.

AB - Visualization of multi-dimensional data is challenging due to the number of complex correlations that may be present in the data but that are difficult to be visually identified. One of the main causes for this problem is the inherent loss of information that occurs when high-dimensional data is projected into 2D or 3D. Although 2D scatterplots are ubiquitous due to their simplicity and familiarity, there are not a lot of variations on their basic metaphor. In this paper, we present a new way of visualizing multidimensional data using scatterplots. We extend 2D scatterplots using sensitivity coefficients to highlight local variation of one variable with respect to another. When applied to a scatterplot, these sensitivities can be understood as velocities, and the resulting visualization resembles a flow field. We also present a number of operations, based on flow-field analysis, that help users navigate, select and cluster points in an efficient manner. We show the flexibility and generality of this approach using a number of multidimensional data sets across different domains.

KW - Data transformations

KW - Model fitting

KW - Principal component analysis

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=78650931630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650931630&partnerID=8YFLogxK

U2 - 10.1109/VAST.2010.5652460

DO - 10.1109/VAST.2010.5652460

M3 - Conference contribution

AN - SCOPUS:78650931630

SN - 9781424494866

SP - 43

EP - 50

BT - VAST 10 - IEEE Conference on Visual Analytics Science and Technology 2010, Proceedings

ER -