Abstract
Parallel coordinates is well-known as a popular tool for visualizing the underlying relationships among variables in high-dimension datasets. However, this representation still suffers from visual clutter arising from intersections among poly line plots especially when the number of data samples and their associated dimension become high. This paper presents a method of alleviating such visual clutter by contracting multiple axes through the analysis of correlation between every pair of variables. In this method, we first construct a graph by connecting axis nodes with an edge weighted by data correlation between the corresponding pair of dimensions, and then reorder the multiple axes by projecting the nodes onto the primary axis obtained through the spectral graph analysis. This allows us to compose a dendrogram tree by recursively merging a pair of the closest axes one by one. Our visualization platform helps the visual interpretation of such axis contraction by plotting the principal component of each data sample along the composite axis. Smooth animation of the associated axis contraction and expansion has also been implemented to enhance the visual readability of behavior inherent in the given high-dimensional datasets.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the International Conference on Information Visualisation |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 7-12 |
| Number of pages | 6 |
| ISBN (Print) | 9781479941032 |
| DOIs | |
| Publication status | Published - 2014 Sep 18 |
| Event | 2014 18th International Conference on Information Visualisation: Visualisation, BioMedical Visualization, Visualisation on Built and Rural Environments and Geometric Modelling and Imaging, IV 2014 - Paris, France Duration: 2014 Jul 16 → 2014 Jul 18 |
Other
| Other | 2014 18th International Conference on Information Visualisation: Visualisation, BioMedical Visualization, Visualisation on Built and Rural Environments and Geometric Modelling and Imaging, IV 2014 |
|---|---|
| Country | France |
| City | Paris |
| Period | 14/7/16 → 14/7/18 |
Fingerprint
Keywords
- axis contraction
- dendrograms
- parallel coordinates
- spectral graph theory
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Software
- Signal Processing
Cite this
Spectral-based contractible parallel coordinates. / Nohno, Koto; Wu, Hsiang Yun; Watanabe, Kazuho; Takahashi, Shigeo; Fujishiro, Issei.
Proceedings of the International Conference on Information Visualisation. Institute of Electrical and Electronics Engineers Inc., 2014. p. 7-12 6902872.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Spectral-based contractible parallel coordinates
AU - Nohno, Koto
AU - Wu, Hsiang Yun
AU - Watanabe, Kazuho
AU - Takahashi, Shigeo
AU - Fujishiro, Issei
PY - 2014/9/18
Y1 - 2014/9/18
N2 - Parallel coordinates is well-known as a popular tool for visualizing the underlying relationships among variables in high-dimension datasets. However, this representation still suffers from visual clutter arising from intersections among poly line plots especially when the number of data samples and their associated dimension become high. This paper presents a method of alleviating such visual clutter by contracting multiple axes through the analysis of correlation between every pair of variables. In this method, we first construct a graph by connecting axis nodes with an edge weighted by data correlation between the corresponding pair of dimensions, and then reorder the multiple axes by projecting the nodes onto the primary axis obtained through the spectral graph analysis. This allows us to compose a dendrogram tree by recursively merging a pair of the closest axes one by one. Our visualization platform helps the visual interpretation of such axis contraction by plotting the principal component of each data sample along the composite axis. Smooth animation of the associated axis contraction and expansion has also been implemented to enhance the visual readability of behavior inherent in the given high-dimensional datasets.
AB - Parallel coordinates is well-known as a popular tool for visualizing the underlying relationships among variables in high-dimension datasets. However, this representation still suffers from visual clutter arising from intersections among poly line plots especially when the number of data samples and their associated dimension become high. This paper presents a method of alleviating such visual clutter by contracting multiple axes through the analysis of correlation between every pair of variables. In this method, we first construct a graph by connecting axis nodes with an edge weighted by data correlation between the corresponding pair of dimensions, and then reorder the multiple axes by projecting the nodes onto the primary axis obtained through the spectral graph analysis. This allows us to compose a dendrogram tree by recursively merging a pair of the closest axes one by one. Our visualization platform helps the visual interpretation of such axis contraction by plotting the principal component of each data sample along the composite axis. Smooth animation of the associated axis contraction and expansion has also been implemented to enhance the visual readability of behavior inherent in the given high-dimensional datasets.
KW - axis contraction
KW - dendrograms
KW - parallel coordinates
KW - spectral graph theory
UR - http://www.scopus.com/inward/record.url?scp=84912075377&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84912075377&partnerID=8YFLogxK
U2 - 10.1109/IV.2014.60
DO - 10.1109/IV.2014.60
M3 - Conference contribution
AN - SCOPUS:84912075377
SN - 9781479941032
SP - 7
EP - 12
BT - Proceedings of the International Conference on Information Visualisation
PB - Institute of Electrical and Electronics Engineers Inc.
ER -