An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data

Takanori Fujiwara, Jia Kai Chou, Shilpika, Panpan Xu, Liu Ren, Kwan Liu Ma

Research output: Contribution to journalArticle

Abstract

Dimensionality reduction (DR) methods are commonly used for analyzing and visualizing multidimensional data. However, when data is a live streaming feed, conventional DR methods cannot be directly used because of their computational complexity and inability to preserve the projected data positions at previous time points. In addition, the problem becomes even more challenging when the dynamic data records have a varying number of dimensions as often found in real-world applications. This paper presents an incremental DR solution. We enhance an existing incremental PCA method in several ways to ensure its usability for visualizing streaming multidimensional data. First, we use geometric transformation and animation methods to help preserve a viewer's mental map when visualizing the incremental results. Second, to handle data dimension variants, we use an optimization method to estimate the projected data positions, and also convey the resulting uncertainty in the visualization. We demonstrate the effectiveness of our design with two case studies using real-world datasets.

Original languageEnglish (US)
Article number8809834
Pages (from-to)418-428
Number of pages11
JournalIEEE Transactions on Visualization and Computer Graphics
Volume26
Issue number1
DOIs
StatePublished - Jan 2020

Fingerprint

Animation
Computational complexity
Visualization
Uncertainty

Keywords

  • Dimensionality reduction
  • principal component analysis
  • streaming data
  • uncertainty
  • visual analytics

ASJC Scopus subject areas

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

Cite this

An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data. / Fujiwara, Takanori; Chou, Jia Kai; Shilpika; Xu, Panpan; Ren, Liu; Ma, Kwan Liu.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 26, No. 1, 8809834, 01.2020, p. 418-428.

Research output: Contribution to journalArticle

Fujiwara, Takanori ; Chou, Jia Kai ; Shilpika ; Xu, Panpan ; Ren, Liu ; Ma, Kwan Liu. / An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data. In: IEEE Transactions on Visualization and Computer Graphics. 2020 ; Vol. 26, No. 1. pp. 418-428.
@article{fb490763c5e441eb9bb7d26521587811,
title = "An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data",
abstract = "Dimensionality reduction (DR) methods are commonly used for analyzing and visualizing multidimensional data. However, when data is a live streaming feed, conventional DR methods cannot be directly used because of their computational complexity and inability to preserve the projected data positions at previous time points. In addition, the problem becomes even more challenging when the dynamic data records have a varying number of dimensions as often found in real-world applications. This paper presents an incremental DR solution. We enhance an existing incremental PCA method in several ways to ensure its usability for visualizing streaming multidimensional data. First, we use geometric transformation and animation methods to help preserve a viewer's mental map when visualizing the incremental results. Second, to handle data dimension variants, we use an optimization method to estimate the projected data positions, and also convey the resulting uncertainty in the visualization. We demonstrate the effectiveness of our design with two case studies using real-world datasets.",
keywords = "Dimensionality reduction, principal component analysis, streaming data, uncertainty, visual analytics",
author = "Takanori Fujiwara and Chou, {Jia Kai} and Shilpika and Panpan Xu and Liu Ren and Ma, {Kwan Liu}",
year = "2020",
month = "1",
doi = "10.1109/TVCG.2019.2934433",
language = "English (US)",
volume = "26",
pages = "418--428",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data

AU - Fujiwara, Takanori

AU - Chou, Jia Kai

AU - Shilpika,

AU - Xu, Panpan

AU - Ren, Liu

AU - Ma, Kwan Liu

PY - 2020/1

Y1 - 2020/1

N2 - Dimensionality reduction (DR) methods are commonly used for analyzing and visualizing multidimensional data. However, when data is a live streaming feed, conventional DR methods cannot be directly used because of their computational complexity and inability to preserve the projected data positions at previous time points. In addition, the problem becomes even more challenging when the dynamic data records have a varying number of dimensions as often found in real-world applications. This paper presents an incremental DR solution. We enhance an existing incremental PCA method in several ways to ensure its usability for visualizing streaming multidimensional data. First, we use geometric transformation and animation methods to help preserve a viewer's mental map when visualizing the incremental results. Second, to handle data dimension variants, we use an optimization method to estimate the projected data positions, and also convey the resulting uncertainty in the visualization. We demonstrate the effectiveness of our design with two case studies using real-world datasets.

AB - Dimensionality reduction (DR) methods are commonly used for analyzing and visualizing multidimensional data. However, when data is a live streaming feed, conventional DR methods cannot be directly used because of their computational complexity and inability to preserve the projected data positions at previous time points. In addition, the problem becomes even more challenging when the dynamic data records have a varying number of dimensions as often found in real-world applications. This paper presents an incremental DR solution. We enhance an existing incremental PCA method in several ways to ensure its usability for visualizing streaming multidimensional data. First, we use geometric transformation and animation methods to help preserve a viewer's mental map when visualizing the incremental results. Second, to handle data dimension variants, we use an optimization method to estimate the projected data positions, and also convey the resulting uncertainty in the visualization. We demonstrate the effectiveness of our design with two case studies using real-world datasets.

KW - Dimensionality reduction

KW - principal component analysis

KW - streaming data

KW - uncertainty

KW - visual analytics

UR - http://www.scopus.com/inward/record.url?scp=85075602208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075602208&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2019.2934433

DO - 10.1109/TVCG.2019.2934433

M3 - Article

C2 - 31449024

AN - SCOPUS:85075602208

VL - 26

SP - 418

EP - 428

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 1

M1 - 8809834

ER -