Sensor-Based Change Detection for Timely Solicitation of User Engagement

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The accurate detection of changes has the potential to form a fundamental component of systems which autonomously solicit user interaction based on transitions within an input stream for example, electrocardiogram data or accelerometry obtained from a mobile device. This solicited interaction may be utilised for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting user activity labels for generating real-world labelled datasets. Within this paper we extend our previous work on the Multivariate Online Change detection Algorithm subsequently exploring the utility of incorporating the Benjamini Hochberg method of correcting for multiple comparisons. Furthermore we evaluate our approach against similarly light-weight Multivariate Exponentially Weighted Moving Average and Cumulative Sum based techniques. Results are presented based on manually labelled change points in accelerometry data captured using 10 participants. Each participant performed 9 distinct activities for a total period of 35 minutes. The results subsequently demonstrate the practical potential of our approach from both accuracy and computational perspectives.
LanguageEnglish
JournalIEEE Transactions on Mobile Computing
VolumePP
Issue number99
Early online date15 Dec 2016
DOIs
Publication statusE-pub ahead of print - 15 Dec 2016

Fingerprint

Electrocardiography
Mobile devices
Labels
Sensors

Keywords

  • Multivariate change detection
  • Online change detection
  • Soliciting user interaction

Cite this

@article{8d8252a28c0d49d2a1392489949692c7,
title = "Sensor-Based Change Detection for Timely Solicitation of User Engagement",
abstract = "The accurate detection of changes has the potential to form a fundamental component of systems which autonomously solicit user interaction based on transitions within an input stream for example, electrocardiogram data or accelerometry obtained from a mobile device. This solicited interaction may be utilised for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting user activity labels for generating real-world labelled datasets. Within this paper we extend our previous work on the Multivariate Online Change detection Algorithm subsequently exploring the utility of incorporating the Benjamini Hochberg method of correcting for multiple comparisons. Furthermore we evaluate our approach against similarly light-weight Multivariate Exponentially Weighted Moving Average and Cumulative Sum based techniques. Results are presented based on manually labelled change points in accelerometry data captured using 10 participants. Each participant performed 9 distinct activities for a total period of 35 minutes. The results subsequently demonstrate the practical potential of our approach from both accuracy and computational perspectives.",
keywords = "Multivariate change detection, Online change detection, Soliciting user interaction",
author = "Timothy Patterson and Naveed Khan and McClean, {Sally I} and Chris Nugent and Shuai Zhang and Ian Cleland and Qin Ni",
year = "2016",
month = "12",
day = "15",
doi = "10.1109/TMC.2016.2640959",
language = "English",
volume = "PP",
number = "99",

}

Sensor-Based Change Detection for Timely Solicitation of User Engagement. / Patterson, Timothy; Khan, Naveed; McClean, Sally I; Nugent, Chris; Zhang, Shuai; Cleland, Ian; Ni, Qin.

Vol. PP, No. 99, 15.12.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Sensor-Based Change Detection for Timely Solicitation of User Engagement

AU - Patterson, Timothy

AU - Khan, Naveed

AU - McClean, Sally I

AU - Nugent, Chris

AU - Zhang, Shuai

AU - Cleland, Ian

AU - Ni, Qin

PY - 2016/12/15

Y1 - 2016/12/15

N2 - The accurate detection of changes has the potential to form a fundamental component of systems which autonomously solicit user interaction based on transitions within an input stream for example, electrocardiogram data or accelerometry obtained from a mobile device. This solicited interaction may be utilised for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting user activity labels for generating real-world labelled datasets. Within this paper we extend our previous work on the Multivariate Online Change detection Algorithm subsequently exploring the utility of incorporating the Benjamini Hochberg method of correcting for multiple comparisons. Furthermore we evaluate our approach against similarly light-weight Multivariate Exponentially Weighted Moving Average and Cumulative Sum based techniques. Results are presented based on manually labelled change points in accelerometry data captured using 10 participants. Each participant performed 9 distinct activities for a total period of 35 minutes. The results subsequently demonstrate the practical potential of our approach from both accuracy and computational perspectives.

AB - The accurate detection of changes has the potential to form a fundamental component of systems which autonomously solicit user interaction based on transitions within an input stream for example, electrocardiogram data or accelerometry obtained from a mobile device. This solicited interaction may be utilised for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting user activity labels for generating real-world labelled datasets. Within this paper we extend our previous work on the Multivariate Online Change detection Algorithm subsequently exploring the utility of incorporating the Benjamini Hochberg method of correcting for multiple comparisons. Furthermore we evaluate our approach against similarly light-weight Multivariate Exponentially Weighted Moving Average and Cumulative Sum based techniques. Results are presented based on manually labelled change points in accelerometry data captured using 10 participants. Each participant performed 9 distinct activities for a total period of 35 minutes. The results subsequently demonstrate the practical potential of our approach from both accuracy and computational perspectives.

KW - Multivariate change detection

KW - Online change detection

KW - Soliciting user interaction

U2 - 10.1109/TMC.2016.2640959

DO - 10.1109/TMC.2016.2640959

M3 - Article

VL - PP

IS - 99

ER -