NFC based dataset annotation within a behavioral alerting platform

Joseph Rafferty, Jonathan Synnott, Chris Nugent, Gareth Morrison, Elena Tamburini

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Pervasive and ubiquitous computing increasingly relies on data-driven models learnt from large datasets. This learning process requires annotations in conjunction with datasets to prepare training data. Ambient Assistive Living (AAL) is one application of pervasive and ubiquitous computing that focuses on providing support for individuals. A subset of AAL solutions exist which model and recognize activities/behaviors to provide assistive services. This paper introduces an annotation mechanism for an AAL platform that can recognize, and provide alerts for, generic activities/behaviors. Previous annotation approaches have several limitations that make them unsuited for use in this platform. To address these deficiencies, an annotation solution relying on environmental NFC tags and smartphones has been devised. This paper details this annotation mechanism, its incorporation into the AAL platform and presents an evaluation focused on the efficacy of annotations produced. In this evaluation, the annotation mechanism was shown to offer reliable, low effort, secure and accurate annotations that are appropriate for learning user behaviors from datasets produced by this platform. Some weaknesses of this annotation approach were identified with solutions proposed within future work.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages146-151
Number of pages6
DOIs
Publication statusE-pub ahead of print - 4 May 2017
EventPervasive Computing and Communications Workshops (PerCom Workshops), 2017 IEEE International Conference on - Kona, Big Island, HI, USA
Duration: 4 May 2017 → …

Workshop

WorkshopPervasive Computing and Communications Workshops (PerCom Workshops), 2017 IEEE International Conference on
Period4/05/17 → …

Fingerprint

Ubiquitous computing
Smartphones

Keywords

  • annotation
  • NFC
  • smart environment
  • pervasive
  • computing
  • machine learning
  • ubiquitous computing
  • behavior
  • detection

Cite this

Rafferty, Joseph ; Synnott, Jonathan ; Nugent, Chris ; Morrison, Gareth ; Tamburini, Elena. / NFC based dataset annotation within a behavioral alerting platform. Unknown Host Publication. 2017. pp. 146-151
@inproceedings{67ba2d6e970a4bd492dd19e570cc5ac2,
title = "NFC based dataset annotation within a behavioral alerting platform",
abstract = "Pervasive and ubiquitous computing increasingly relies on data-driven models learnt from large datasets. This learning process requires annotations in conjunction with datasets to prepare training data. Ambient Assistive Living (AAL) is one application of pervasive and ubiquitous computing that focuses on providing support for individuals. A subset of AAL solutions exist which model and recognize activities/behaviors to provide assistive services. This paper introduces an annotation mechanism for an AAL platform that can recognize, and provide alerts for, generic activities/behaviors. Previous annotation approaches have several limitations that make them unsuited for use in this platform. To address these deficiencies, an annotation solution relying on environmental NFC tags and smartphones has been devised. This paper details this annotation mechanism, its incorporation into the AAL platform and presents an evaluation focused on the efficacy of annotations produced. In this evaluation, the annotation mechanism was shown to offer reliable, low effort, secure and accurate annotations that are appropriate for learning user behaviors from datasets produced by this platform. Some weaknesses of this annotation approach were identified with solutions proposed within future work.",
keywords = "annotation, NFC, smart environment, pervasive, computing, machine learning, ubiquitous computing, behavior, detection",
author = "Joseph Rafferty and Jonathan Synnott and Chris Nugent and Gareth Morrison and Elena Tamburini",
year = "2017",
month = "5",
day = "4",
doi = "10.1109/PERCOMW.2017.7917548",
language = "English",
isbn = "978-1-5090-4338-5",
pages = "146--151",
booktitle = "Unknown Host Publication",

}

Rafferty, J, Synnott, J, Nugent, C, Morrison, G & Tamburini, E 2017, NFC based dataset annotation within a behavioral alerting platform. in Unknown Host Publication. pp. 146-151, Pervasive Computing and Communications Workshops (PerCom Workshops), 2017 IEEE International Conference on, 4/05/17. https://doi.org/10.1109/PERCOMW.2017.7917548

NFC based dataset annotation within a behavioral alerting platform. / Rafferty, Joseph; Synnott, Jonathan; Nugent, Chris; Morrison, Gareth; Tamburini, Elena.

Unknown Host Publication. 2017. p. 146-151.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - NFC based dataset annotation within a behavioral alerting platform

AU - Rafferty, Joseph

AU - Synnott, Jonathan

AU - Nugent, Chris

AU - Morrison, Gareth

AU - Tamburini, Elena

PY - 2017/5/4

Y1 - 2017/5/4

N2 - Pervasive and ubiquitous computing increasingly relies on data-driven models learnt from large datasets. This learning process requires annotations in conjunction with datasets to prepare training data. Ambient Assistive Living (AAL) is one application of pervasive and ubiquitous computing that focuses on providing support for individuals. A subset of AAL solutions exist which model and recognize activities/behaviors to provide assistive services. This paper introduces an annotation mechanism for an AAL platform that can recognize, and provide alerts for, generic activities/behaviors. Previous annotation approaches have several limitations that make them unsuited for use in this platform. To address these deficiencies, an annotation solution relying on environmental NFC tags and smartphones has been devised. This paper details this annotation mechanism, its incorporation into the AAL platform and presents an evaluation focused on the efficacy of annotations produced. In this evaluation, the annotation mechanism was shown to offer reliable, low effort, secure and accurate annotations that are appropriate for learning user behaviors from datasets produced by this platform. Some weaknesses of this annotation approach were identified with solutions proposed within future work.

AB - Pervasive and ubiquitous computing increasingly relies on data-driven models learnt from large datasets. This learning process requires annotations in conjunction with datasets to prepare training data. Ambient Assistive Living (AAL) is one application of pervasive and ubiquitous computing that focuses on providing support for individuals. A subset of AAL solutions exist which model and recognize activities/behaviors to provide assistive services. This paper introduces an annotation mechanism for an AAL platform that can recognize, and provide alerts for, generic activities/behaviors. Previous annotation approaches have several limitations that make them unsuited for use in this platform. To address these deficiencies, an annotation solution relying on environmental NFC tags and smartphones has been devised. This paper details this annotation mechanism, its incorporation into the AAL platform and presents an evaluation focused on the efficacy of annotations produced. In this evaluation, the annotation mechanism was shown to offer reliable, low effort, secure and accurate annotations that are appropriate for learning user behaviors from datasets produced by this platform. Some weaknesses of this annotation approach were identified with solutions proposed within future work.

KW - annotation

KW - NFC

KW - smart environment

KW - pervasive

KW - computing

KW - machine learning

KW - ubiquitous computing

KW - behavior

KW - detection

U2 - 10.1109/PERCOMW.2017.7917548

DO - 10.1109/PERCOMW.2017.7917548

M3 - Conference contribution

SN - 978-1-5090-4338-5

SP - 146

EP - 151

BT - Unknown Host Publication

ER -