Online Change Detection for Timely Solicitation of User Interaction

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

2 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 accelerometry data obtained from a mobile device. This solicited interaction may be utilized for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting activity labels for generating real-world labelled datasets. Within this paper a change detection algorithm is presented which does not require knowledge of the underlying distributions, can run in online scenarios and considers multivariate datastreams. Results are presented demonstrating practicable potential with 99.81% accuracy and 60% precision for real-world accelerometry data.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages116-123
Number of pages8
Volume8867
DOIs
Publication statusPublished - 5 Dec 2014
Event8th International Conference on Ubiquitous Computing & Ambient Intelligence - Belfast, Northern Ireland
Duration: 5 Dec 2014 → …

Conference

Conference8th International Conference on Ubiquitous Computing & Ambient Intelligence
Period5/12/14 → …

Fingerprint

Mobile devices
Labels

Cite this

@inproceedings{da24bd2a61c8484c97d1c7467f3ce87b,
title = "Online Change Detection for Timely Solicitation of User Interaction",
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 accelerometry data obtained from a mobile device. This solicited interaction may be utilized for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting activity labels for generating real-world labelled datasets. Within this paper a change detection algorithm is presented which does not require knowledge of the underlying distributions, can run in online scenarios and considers multivariate datastreams. Results are presented demonstrating practicable potential with 99.81{\%} accuracy and 60{\%} precision for real-world accelerometry data.",
author = "Timothy Patterson and Sally McClean and CD Nugent and Shuai Zhang and Leo Galway and Ian Cleland",
year = "2014",
month = "12",
day = "5",
doi = "10.1007/978-3-319-13102-3_21",
language = "English",
isbn = "978-3-319-13102-3",
volume = "8867",
pages = "116--123",
booktitle = "Unknown Host Publication",

}

Patterson, T, McClean, S, Nugent, CD, Zhang, S, Galway, L & Cleland, I 2014, Online Change Detection for Timely Solicitation of User Interaction. in Unknown Host Publication. vol. 8867, pp. 116-123, 8th International Conference on Ubiquitous Computing & Ambient Intelligence, 5/12/14. https://doi.org/10.1007/978-3-319-13102-3_21

Online Change Detection for Timely Solicitation of User Interaction. / Patterson, Timothy; McClean, Sally; Nugent, CD; Zhang, Shuai; Galway, Leo; Cleland, Ian.

Unknown Host Publication. Vol. 8867 2014. p. 116-123.

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

TY - GEN

T1 - Online Change Detection for Timely Solicitation of User Interaction

AU - Patterson, Timothy

AU - McClean, Sally

AU - Nugent, CD

AU - Zhang, Shuai

AU - Galway, Leo

AU - Cleland, Ian

PY - 2014/12/5

Y1 - 2014/12/5

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 accelerometry data obtained from a mobile device. This solicited interaction may be utilized for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting activity labels for generating real-world labelled datasets. Within this paper a change detection algorithm is presented which does not require knowledge of the underlying distributions, can run in online scenarios and considers multivariate datastreams. Results are presented demonstrating practicable potential with 99.81% accuracy and 60% precision for real-world accelerometry data.

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 accelerometry data obtained from a mobile device. This solicited interaction may be utilized for diverse scenarios such as responding to changes in a patient's vital signs within a medical domain or requesting activity labels for generating real-world labelled datasets. Within this paper a change detection algorithm is presented which does not require knowledge of the underlying distributions, can run in online scenarios and considers multivariate datastreams. Results are presented demonstrating practicable potential with 99.81% accuracy and 60% precision for real-world accelerometry data.

U2 - 10.1007/978-3-319-13102-3_21

DO - 10.1007/978-3-319-13102-3_21

M3 - Conference contribution

SN - 978-3-319-13102-3

VL - 8867

SP - 116

EP - 123

BT - Unknown Host Publication

ER -