Eye-tracking based adaptive parallel coordinates

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Parallel coordinates is a well-known technique for visual analysis of high-dimensional data. Although it is effective for interactive discovery of patterns in subsets of dimensions and data records, it also has scalability issues for large datasets. In particular, the amount of visual information potentially being shown in a parallel coordinates plot grows combinatorially with the number of dimensions. Choosing the right ordering of axes is crucial, and poor design can lead to visual noise and a cluttered plot. In this case, the user may overlook a significant pattern, or leave some dimensions unexplored. In this work, we demonstrate how eye-tracking can help an analyst efficiently and effectively reorder the axes in a parallel coordinates plot. Implicit input from an inexpensive eye-tracker assists the system in finding unexplored dimensions. Using this information, the system guides the user either visually or automatically to find further appropriate orderings of the axes.

Original languageEnglish
Title of host publicationSIGGRAPH Asia 2019 Posters, SA 2019
PublisherAssociation of Computing Machinery
ISBN (Electronic)9781450369435
DOIs
Publication statusPublished - 17 Nov 2019
EventSIGGRAPH Asia 2019 Posters - International Conference on Computer Graphics and Interactive Techniques, SA 2019 - Brisbane, Australia
Duration: 17 Nov 201920 Nov 2019

Publication series

NameSIGGRAPH Asia 2019 Posters, SA 2019

Conference

ConferenceSIGGRAPH Asia 2019 Posters - International Conference on Computer Graphics and Interactive Techniques, SA 2019
CountryAustralia
CityBrisbane
Period17/11/1920/11/19

Fingerprint

Scalability

Keywords

  • Adaptive user interfaces
  • Eye-tracking
  • Parallel coordinates

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Chegini, M., Andrews, K., Schreck, T., & Sourin, A. (2019). Eye-tracking based adaptive parallel coordinates. In SIGGRAPH Asia 2019 Posters, SA 2019 [3364563] (SIGGRAPH Asia 2019 Posters, SA 2019). Association of Computing Machinery. https://doi.org/10.1145/3355056.3364563

Eye-tracking based adaptive parallel coordinates. / Chegini, Mohammad; Andrews, Keith; Schreck, Tobias; Sourin, Alexei.

SIGGRAPH Asia 2019 Posters, SA 2019. Association of Computing Machinery, 2019. 3364563 (SIGGRAPH Asia 2019 Posters, SA 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Chegini, M, Andrews, K, Schreck, T & Sourin, A 2019, Eye-tracking based adaptive parallel coordinates. in SIGGRAPH Asia 2019 Posters, SA 2019., 3364563, SIGGRAPH Asia 2019 Posters, SA 2019, Association of Computing Machinery, SIGGRAPH Asia 2019 Posters - International Conference on Computer Graphics and Interactive Techniques, SA 2019, Brisbane, Australia, 17/11/19. https://doi.org/10.1145/3355056.3364563
Chegini M, Andrews K, Schreck T, Sourin A. Eye-tracking based adaptive parallel coordinates. In SIGGRAPH Asia 2019 Posters, SA 2019. Association of Computing Machinery. 2019. 3364563. (SIGGRAPH Asia 2019 Posters, SA 2019). https://doi.org/10.1145/3355056.3364563
Chegini, Mohammad ; Andrews, Keith ; Schreck, Tobias ; Sourin, Alexei. / Eye-tracking based adaptive parallel coordinates. SIGGRAPH Asia 2019 Posters, SA 2019. Association of Computing Machinery, 2019. (SIGGRAPH Asia 2019 Posters, SA 2019).
@inproceedings{a28ce13f2152457c818a1cd02c5399e2,
title = "Eye-tracking based adaptive parallel coordinates",
abstract = "Parallel coordinates is a well-known technique for visual analysis of high-dimensional data. Although it is effective for interactive discovery of patterns in subsets of dimensions and data records, it also has scalability issues for large datasets. In particular, the amount of visual information potentially being shown in a parallel coordinates plot grows combinatorially with the number of dimensions. Choosing the right ordering of axes is crucial, and poor design can lead to visual noise and a cluttered plot. In this case, the user may overlook a significant pattern, or leave some dimensions unexplored. In this work, we demonstrate how eye-tracking can help an analyst efficiently and effectively reorder the axes in a parallel coordinates plot. Implicit input from an inexpensive eye-tracker assists the system in finding unexplored dimensions. Using this information, the system guides the user either visually or automatically to find further appropriate orderings of the axes.",
keywords = "Adaptive user interfaces, Eye-tracking, Parallel coordinates",
author = "Mohammad Chegini and Keith Andrews and Tobias Schreck and Alexei Sourin",
year = "2019",
month = "11",
day = "17",
doi = "10.1145/3355056.3364563",
language = "English",
series = "SIGGRAPH Asia 2019 Posters, SA 2019",
publisher = "Association of Computing Machinery",
booktitle = "SIGGRAPH Asia 2019 Posters, SA 2019",
address = "United States",

}

TY - GEN

T1 - Eye-tracking based adaptive parallel coordinates

AU - Chegini, Mohammad

AU - Andrews, Keith

AU - Schreck, Tobias

AU - Sourin, Alexei

PY - 2019/11/17

Y1 - 2019/11/17

N2 - Parallel coordinates is a well-known technique for visual analysis of high-dimensional data. Although it is effective for interactive discovery of patterns in subsets of dimensions and data records, it also has scalability issues for large datasets. In particular, the amount of visual information potentially being shown in a parallel coordinates plot grows combinatorially with the number of dimensions. Choosing the right ordering of axes is crucial, and poor design can lead to visual noise and a cluttered plot. In this case, the user may overlook a significant pattern, or leave some dimensions unexplored. In this work, we demonstrate how eye-tracking can help an analyst efficiently and effectively reorder the axes in a parallel coordinates plot. Implicit input from an inexpensive eye-tracker assists the system in finding unexplored dimensions. Using this information, the system guides the user either visually or automatically to find further appropriate orderings of the axes.

AB - Parallel coordinates is a well-known technique for visual analysis of high-dimensional data. Although it is effective for interactive discovery of patterns in subsets of dimensions and data records, it also has scalability issues for large datasets. In particular, the amount of visual information potentially being shown in a parallel coordinates plot grows combinatorially with the number of dimensions. Choosing the right ordering of axes is crucial, and poor design can lead to visual noise and a cluttered plot. In this case, the user may overlook a significant pattern, or leave some dimensions unexplored. In this work, we demonstrate how eye-tracking can help an analyst efficiently and effectively reorder the axes in a parallel coordinates plot. Implicit input from an inexpensive eye-tracker assists the system in finding unexplored dimensions. Using this information, the system guides the user either visually or automatically to find further appropriate orderings of the axes.

KW - Adaptive user interfaces

KW - Eye-tracking

KW - Parallel coordinates

UR - http://www.scopus.com/inward/record.url?scp=85076760146&partnerID=8YFLogxK

U2 - 10.1145/3355056.3364563

DO - 10.1145/3355056.3364563

M3 - Conference contribution

T3 - SIGGRAPH Asia 2019 Posters, SA 2019

BT - SIGGRAPH Asia 2019 Posters, SA 2019

PB - Association of Computing Machinery

ER -