Context Transitions: User identification and comparison of mobile device motion data

Thomas Lovett, Eamonn O'Neill

Research output: Chapter in Book/Report/Conference proceedingChapter

  • 1 Citations

Abstract

In this paper, we study a time-critical facet of context-awareness: context transitions, which we model as changes in specific context types over time, e.g., activity or location. We present results from a user-centred field study involving participant interviews and motion data capture from two mobile device sensors: the accelerometer and magnetic field sensor. The results show how the participants subjectively interpret their daily context transitions with variable granularity, and a comparison of these context transitions with mobile device motion data shows how the motion data poorly reflect the identified transitions. The results imply that care should be taken when representing and modelling users' subjective interpretations of context, as well as the objective nature of context sensors. Furthermore, processing and usability trade-offs should be made if real-time on-device transition detection is to be implemented.
LanguageEnglish
Title of host publicationActivity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report
Place of PublicationEl Segundo, CA.
PublisherAI Access Foundation
Pages42-47
Number of pages6
VolumeWS-11-04
StatusPublished - Aug 2011
Event2011 AAAI Workshop, August 7, 2011 - August 8, 2011 - San Francisco, CA, USA United States
Duration: 1 Aug 2011 → …

Publication series

NameAAAI Workshop - Technical Report
PublisherAI Access Foundation

Conference

Conference2011 AAAI Workshop, August 7, 2011 - August 8, 2011
CountryUSA United States
CitySan Francisco, CA
Period1/08/11 → …

Fingerprint

Mobile devices
Sensors
Accelerometers
Data acquisition
Magnetic fields
Processing

Cite this

Lovett, T., & O'Neill, E. (2011). Context Transitions: User identification and comparison of mobile device motion data. In Activity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report (Vol. WS-11-04, pp. 42-47). (AAAI Workshop - Technical Report). El Segundo, CA.: AI Access Foundation.

Context Transitions : User identification and comparison of mobile device motion data. / Lovett, Thomas; O'Neill, Eamonn.

Activity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report. Vol. WS-11-04 El Segundo, CA. : AI Access Foundation, 2011. p. 42-47 (AAAI Workshop - Technical Report).

Research output: Chapter in Book/Report/Conference proceedingChapter

Lovett, T & O'Neill, E 2011, Context Transitions: User identification and comparison of mobile device motion data. in Activity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report. vol. WS-11-04, AAAI Workshop - Technical Report, AI Access Foundation, El Segundo, CA., pp. 42-47, 2011 AAAI Workshop, August 7, 2011 - August 8, 2011, San Francisco, CA, USA United States, 1/08/11.
Lovett T, O'Neill E. Context Transitions: User identification and comparison of mobile device motion data. In Activity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report. Vol. WS-11-04. El Segundo, CA.: AI Access Foundation. 2011. p. 42-47. (AAAI Workshop - Technical Report).
Lovett, Thomas ; O'Neill, Eamonn. / Context Transitions : User identification and comparison of mobile device motion data. Activity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report. Vol. WS-11-04 El Segundo, CA. : AI Access Foundation, 2011. pp. 42-47 (AAAI Workshop - Technical Report).
@inbook{1229974c3e2e44748a14f616ad25011d,
title = "Context Transitions: User identification and comparison of mobile device motion data",
abstract = "In this paper, we study a time-critical facet of context-awareness: context transitions, which we model as changes in specific context types over time, e.g., activity or location. We present results from a user-centred field study involving participant interviews and motion data capture from two mobile device sensors: the accelerometer and magnetic field sensor. The results show how the participants subjectively interpret their daily context transitions with variable granularity, and a comparison of these context transitions with mobile device motion data shows how the motion data poorly reflect the identified transitions. The results imply that care should be taken when representing and modelling users' subjective interpretations of context, as well as the objective nature of context sensors. Furthermore, processing and usability trade-offs should be made if real-time on-device transition detection is to be implemented.",
author = "Thomas Lovett and Eamonn O'Neill",
year = "2011",
month = "8",
language = "English",
volume = "WS-11-04",
series = "AAAI Workshop - Technical Report",
publisher = "AI Access Foundation",
pages = "42--47",
booktitle = "Activity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report",

}

TY - CHAP

T1 - Context Transitions

T2 - User identification and comparison of mobile device motion data

AU - Lovett,Thomas

AU - O'Neill,Eamonn

PY - 2011/8

Y1 - 2011/8

N2 - In this paper, we study a time-critical facet of context-awareness: context transitions, which we model as changes in specific context types over time, e.g., activity or location. We present results from a user-centred field study involving participant interviews and motion data capture from two mobile device sensors: the accelerometer and magnetic field sensor. The results show how the participants subjectively interpret their daily context transitions with variable granularity, and a comparison of these context transitions with mobile device motion data shows how the motion data poorly reflect the identified transitions. The results imply that care should be taken when representing and modelling users' subjective interpretations of context, as well as the objective nature of context sensors. Furthermore, processing and usability trade-offs should be made if real-time on-device transition detection is to be implemented.

AB - In this paper, we study a time-critical facet of context-awareness: context transitions, which we model as changes in specific context types over time, e.g., activity or location. We present results from a user-centred field study involving participant interviews and motion data capture from two mobile device sensors: the accelerometer and magnetic field sensor. The results show how the participants subjectively interpret their daily context transitions with variable granularity, and a comparison of these context transitions with mobile device motion data shows how the motion data poorly reflect the identified transitions. The results imply that care should be taken when representing and modelling users' subjective interpretations of context, as well as the objective nature of context sensors. Furthermore, processing and usability trade-offs should be made if real-time on-device transition detection is to be implemented.

M3 - Chapter

VL - WS-11-04

T3 - AAAI Workshop - Technical Report

SP - 42

EP - 47

BT - Activity Context Representation: Techniques and Languages - Papers from the 2011 AAAI Workshop, Technical Report

PB - AI Access Foundation

CY - El Segundo, CA.

ER -