Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration

Sungahnn Ko; Shehzad Afzal; Simon Walton; Yang Yang; Junghoon Chae; Abish Malik; Yun Jang; Min Chen; David Ebert

doi:10.1109/VAST.2014.7042484

Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration

Sungahnn Ko, Shehzad Afzal, Simon Walton, Yang Yang, Junghoon Chae, Abish Malik, Yun Jang, Min Chen, David Ebert

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

32 Scopus citations

Abstract

This paper focuses on the integration of a family of visual analytics techniques for analyzing high-dimensional, multivariate network data that features spatial and temporal information, network connections, and a variety of other categorical and numerical data types. Such data types are commonly encountered in transportation, shipping, and logistics industries. Due to the scale and complexity of the data, it is essential to integrate techniques for data analysis, visualization, and exploration. We present new visual representations, Petal and Thread, to effectively present many-to-many network data including multi-attribute vectors. In addition, we deploy an information-theoretic model for anomaly detection across varying dimensions, displaying highlighted anomalies in a visually consistent manner, as well as supporting a managed process of exploration. Lastly, we evaluate the proposed methodology through data exploration and an empirical study.

Original language	English
Title of host publication	2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings
Editors	Min Chen, David Ebert, Chris North
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	83-92
Number of pages	10
ISBN (Electronic)	9781479962273
DOIs	https://doi.org/10.1109/VAST.2014.7042484
State	Published - Feb 13 2015
Externally published	Yes
Event	2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Paris, France Duration: Oct 9 2014 → Oct 14 2014

Publication series

Name	2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings

Conference

Conference	2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014
Country/Territory	France
City	Paris
Period	10/9/14 → 10/14/14

Keywords

I.3.6 [Computer Graphics]: Methodology and Techniques - Interaction techniques
I.3.8 [Computer Graphics]: Applications - Visual Analytics

Access to Document

10.1109/VAST.2014.7042484

Cite this

Ko, S., Afzal, S., Walton, S., Yang, Y., Chae, J., Malik, A., Jang, Y., Chen, M., & Ebert, D. (2015). Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration. In M. Chen, D. Ebert, & C. North (Eds.), 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings (pp. 83-92). Article 7042484 (2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VAST.2014.7042484

Ko, Sungahnn ; Afzal, Shehzad ; Walton, Simon et al. / Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration. 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings. editor / Min Chen ; David Ebert ; Chris North. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 83-92 (2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings).

@inproceedings{0e557cebdc6a48988547fadfa829b89b,

title = "Analyzing high-dimensional multivar{\'i}ate network links with integrated anomaly detection, highlighting and exploration",

abstract = "This paper focuses on the integration of a family of visual analytics techniques for analyzing high-dimensional, multivariate network data that features spatial and temporal information, network connections, and a variety of other categorical and numerical data types. Such data types are commonly encountered in transportation, shipping, and logistics industries. Due to the scale and complexity of the data, it is essential to integrate techniques for data analysis, visualization, and exploration. We present new visual representations, Petal and Thread, to effectively present many-to-many network data including multi-attribute vectors. In addition, we deploy an information-theoretic model for anomaly detection across varying dimensions, displaying highlighted anomalies in a visually consistent manner, as well as supporting a managed process of exploration. Lastly, we evaluate the proposed methodology through data exploration and an empirical study.",

keywords = "I.3.6 [Computer Graphics]: Methodology and Techniques - Interaction techniques, I.3.8 [Computer Graphics]: Applications - Visual Analytics",

author = "Sungahnn Ko and Shehzad Afzal and Simon Walton and Yang Yang and Junghoon Chae and Abish Malik and Yun Jang and Min Chen and David Ebert",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 ; Conference date: 09-10-2014 Through 14-10-2014",

year = "2015",

month = feb,

day = "13",

doi = "10.1109/VAST.2014.7042484",

language = "English",

series = "2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "83--92",

editor = "Min Chen and David Ebert and Chris North",

booktitle = "2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings",

}

Ko, S, Afzal, S, Walton, S, Yang, Y, Chae, J, Malik, A, Jang, Y, Chen, M & Ebert, D 2015, Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration. in M Chen, D Ebert & C North (eds), 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings., 7042484, 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 83-92, 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014, Paris, France, 10/9/14. https://doi.org/10.1109/VAST.2014.7042484

Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration. / Ko, Sungahnn; Afzal, Shehzad; Walton, Simon et al.
2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings. ed. / Min Chen; David Ebert; Chris North. Institute of Electrical and Electronics Engineers Inc., 2015. p. 83-92 7042484 (2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration

AU - Ko, Sungahnn

AU - Afzal, Shehzad

AU - Walton, Simon

AU - Yang, Yang

AU - Chae, Junghoon

AU - Malik, Abish

AU - Jang, Yun

AU - Chen, Min

AU - Ebert, David

PY - 2015/2/13

Y1 - 2015/2/13

N2 - This paper focuses on the integration of a family of visual analytics techniques for analyzing high-dimensional, multivariate network data that features spatial and temporal information, network connections, and a variety of other categorical and numerical data types. Such data types are commonly encountered in transportation, shipping, and logistics industries. Due to the scale and complexity of the data, it is essential to integrate techniques for data analysis, visualization, and exploration. We present new visual representations, Petal and Thread, to effectively present many-to-many network data including multi-attribute vectors. In addition, we deploy an information-theoretic model for anomaly detection across varying dimensions, displaying highlighted anomalies in a visually consistent manner, as well as supporting a managed process of exploration. Lastly, we evaluate the proposed methodology through data exploration and an empirical study.

AB - This paper focuses on the integration of a family of visual analytics techniques for analyzing high-dimensional, multivariate network data that features spatial and temporal information, network connections, and a variety of other categorical and numerical data types. Such data types are commonly encountered in transportation, shipping, and logistics industries. Due to the scale and complexity of the data, it is essential to integrate techniques for data analysis, visualization, and exploration. We present new visual representations, Petal and Thread, to effectively present many-to-many network data including multi-attribute vectors. In addition, we deploy an information-theoretic model for anomaly detection across varying dimensions, displaying highlighted anomalies in a visually consistent manner, as well as supporting a managed process of exploration. Lastly, we evaluate the proposed methodology through data exploration and an empirical study.

KW - I.3.6 [Computer Graphics]: Methodology and Techniques - Interaction techniques

KW - I.3.8 [Computer Graphics]: Applications - Visual Analytics

UR - http://www.scopus.com/inward/record.url?scp=84929468312&partnerID=8YFLogxK

U2 - 10.1109/VAST.2014.7042484

DO - 10.1109/VAST.2014.7042484

M3 - Conference contribution

AN - SCOPUS:84929468312

T3 - 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings

SP - 83

EP - 92

BT - 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings

A2 - Chen, Min

A2 - Ebert, David

A2 - North, Chris

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014

Y2 - 9 October 2014 through 14 October 2014

ER -

Ko S, Afzal S, Walton S, Yang Y, Chae J, Malik A et al. Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration. In Chen M, Ebert D, North C, editors, 2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 83-92. 7042484. (2014 IEEE Conference on Visual Analytics Science and Technology, VAST 2014 - Proceedings). doi: 10.1109/VAST.2014.7042484

Analyzing high-dimensional multivaríate network links with integrated anomaly detection, highlighting and exploration

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this