Transition Icons for Time-Series Visualization and Exploratory Analysis

Paul V. Nickerson, Raheleh Baharloo, Amal Wanigatunga, Todd M. Manini, Patrick J. Tighe, Parisa Rashidi

Research output: Contribution to journalArticle

Abstract

The modern healthcare landscape has seen the rapid emergence of techniques and devices that temporally monitor and record physiological signals. The prevalence of time-series data within the healthcare field necessitates the development of methods that can analyze the data in order to draw meaningful conclusions. Time-series behavior is notoriously difficult to intuitively understand due to its intrinsic high-dimensionality, which is compounded in the case of analyzing groups of time series collected from different patients. Our framework, which we call transition icons, renders common patterns in a visual format useful for understanding the shared behavior within groups of time series. Transition icons are adept at detecting and displaying subtle differences and similarities, e.g., between measurements taken from patients receiving different treatment strategies or stratified by demographics. We introduce various methods that collectively allow for exploratory analysis of groups of time series, while being free of distribution assumptions and including simple heuristics for parameter determination. Our technique extracts discrete transition patterns from symbolic aggregate approXimation representations, and compiles transition frequencies into a bag of patterns constructed for each group. These transition frequencies are normalized and aligned in icon form to intuitively display the underlying patterns. We demonstrate the transition icon technique for two time-series datasets - postoperative pain scores, and hip-worn accelerometer activity counts. We believe transition icons can be an important tool for researchers approaching time-series data, as they give rich and intuitive information about collective time-series behaviors.

Original languageEnglish (US)
Pages (from-to)623-630
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Volume22
Issue number2
DOIs
StatePublished - Mar 1 2018

Fingerprint

Time series
Visualization
Delivery of Health Care
cyhalothrin
Postoperative Pain
Accelerometers
Hip
Research Personnel
Demography
Equipment and Supplies

Keywords

  • Bag of patterns
  • symbolic aggregate approximation
  • time series

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Transition Icons for Time-Series Visualization and Exploratory Analysis. / Nickerson, Paul V.; Baharloo, Raheleh; Wanigatunga, Amal; Manini, Todd M.; Tighe, Patrick J.; Rashidi, Parisa.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 22, No. 2, 01.03.2018, p. 623-630.

Research output: Contribution to journalArticle

Nickerson, Paul V. ; Baharloo, Raheleh ; Wanigatunga, Amal ; Manini, Todd M. ; Tighe, Patrick J. ; Rashidi, Parisa. / Transition Icons for Time-Series Visualization and Exploratory Analysis. In: IEEE Journal of Biomedical and Health Informatics. 2018 ; Vol. 22, No. 2. pp. 623-630.
@article{3d6698df23e6462fa7c214af5e87c206,
title = "Transition Icons for Time-Series Visualization and Exploratory Analysis",
abstract = "The modern healthcare landscape has seen the rapid emergence of techniques and devices that temporally monitor and record physiological signals. The prevalence of time-series data within the healthcare field necessitates the development of methods that can analyze the data in order to draw meaningful conclusions. Time-series behavior is notoriously difficult to intuitively understand due to its intrinsic high-dimensionality, which is compounded in the case of analyzing groups of time series collected from different patients. Our framework, which we call transition icons, renders common patterns in a visual format useful for understanding the shared behavior within groups of time series. Transition icons are adept at detecting and displaying subtle differences and similarities, e.g., between measurements taken from patients receiving different treatment strategies or stratified by demographics. We introduce various methods that collectively allow for exploratory analysis of groups of time series, while being free of distribution assumptions and including simple heuristics for parameter determination. Our technique extracts discrete transition patterns from symbolic aggregate approXimation representations, and compiles transition frequencies into a bag of patterns constructed for each group. These transition frequencies are normalized and aligned in icon form to intuitively display the underlying patterns. We demonstrate the transition icon technique for two time-series datasets - postoperative pain scores, and hip-worn accelerometer activity counts. We believe transition icons can be an important tool for researchers approaching time-series data, as they give rich and intuitive information about collective time-series behaviors.",
keywords = "Bag of patterns, symbolic aggregate approximation, time series",
author = "Nickerson, {Paul V.} and Raheleh Baharloo and Amal Wanigatunga and Manini, {Todd M.} and Tighe, {Patrick J.} and Parisa Rashidi",
year = "2018",
month = "3",
day = "1",
doi = "10.1109/JBHI.2017.2704608",
language = "English (US)",
volume = "22",
pages = "623--630",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Transition Icons for Time-Series Visualization and Exploratory Analysis

AU - Nickerson, Paul V.

AU - Baharloo, Raheleh

AU - Wanigatunga, Amal

AU - Manini, Todd M.

AU - Tighe, Patrick J.

AU - Rashidi, Parisa

PY - 2018/3/1

Y1 - 2018/3/1

N2 - The modern healthcare landscape has seen the rapid emergence of techniques and devices that temporally monitor and record physiological signals. The prevalence of time-series data within the healthcare field necessitates the development of methods that can analyze the data in order to draw meaningful conclusions. Time-series behavior is notoriously difficult to intuitively understand due to its intrinsic high-dimensionality, which is compounded in the case of analyzing groups of time series collected from different patients. Our framework, which we call transition icons, renders common patterns in a visual format useful for understanding the shared behavior within groups of time series. Transition icons are adept at detecting and displaying subtle differences and similarities, e.g., between measurements taken from patients receiving different treatment strategies or stratified by demographics. We introduce various methods that collectively allow for exploratory analysis of groups of time series, while being free of distribution assumptions and including simple heuristics for parameter determination. Our technique extracts discrete transition patterns from symbolic aggregate approXimation representations, and compiles transition frequencies into a bag of patterns constructed for each group. These transition frequencies are normalized and aligned in icon form to intuitively display the underlying patterns. We demonstrate the transition icon technique for two time-series datasets - postoperative pain scores, and hip-worn accelerometer activity counts. We believe transition icons can be an important tool for researchers approaching time-series data, as they give rich and intuitive information about collective time-series behaviors.

AB - The modern healthcare landscape has seen the rapid emergence of techniques and devices that temporally monitor and record physiological signals. The prevalence of time-series data within the healthcare field necessitates the development of methods that can analyze the data in order to draw meaningful conclusions. Time-series behavior is notoriously difficult to intuitively understand due to its intrinsic high-dimensionality, which is compounded in the case of analyzing groups of time series collected from different patients. Our framework, which we call transition icons, renders common patterns in a visual format useful for understanding the shared behavior within groups of time series. Transition icons are adept at detecting and displaying subtle differences and similarities, e.g., between measurements taken from patients receiving different treatment strategies or stratified by demographics. We introduce various methods that collectively allow for exploratory analysis of groups of time series, while being free of distribution assumptions and including simple heuristics for parameter determination. Our technique extracts discrete transition patterns from symbolic aggregate approXimation representations, and compiles transition frequencies into a bag of patterns constructed for each group. These transition frequencies are normalized and aligned in icon form to intuitively display the underlying patterns. We demonstrate the transition icon technique for two time-series datasets - postoperative pain scores, and hip-worn accelerometer activity counts. We believe transition icons can be an important tool for researchers approaching time-series data, as they give rich and intuitive information about collective time-series behaviors.

KW - Bag of patterns

KW - symbolic aggregate approximation

KW - time series

UR - http://www.scopus.com/inward/record.url?scp=85043595498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043595498&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2017.2704608

DO - 10.1109/JBHI.2017.2704608

M3 - Article

C2 - 28534797

AN - SCOPUS:85043595498

VL - 22

SP - 623

EP - 630

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 2

ER -