Neighbourhood Counting for Activity Detection from Time Series Sensor Data

Xin Hong, CD Nugent

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

2 Citations (Scopus)

Abstract

Health status along with assistive support requirements can be assessed by measures of activities of daily living. Advances in pervasive sensing and intelligent reasoning pave a way to monitor, i.e. detect and recognise, activities automatically and unobtrusively. The first task in monitoring activities is to detect when an activity has taken place based on a time series of sensor activation events. Inspired by the concepts of dynamic time warping and neighborhood counting matrix in similarity measures, this paper proposes a novel method to segment streams of sensor events for activity detection. Sensor segments may then be used as inputs to evidential ontology networks of activities for activity recognition.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages4
DOIs
Publication statusPublished - 2010
EventProceedings of the 10th International Conference on Information Technology and Applications in Biomedicine - Corfu, Greece
Duration: 1 Jan 2010 → …

Conference

ConferenceProceedings of the 10th International Conference on Information Technology and Applications in Biomedicine
Period1/01/10 → …

Fingerprint

Time series
Sensors
Ontology
Chemical activation
Health
Monitoring

Cite this

@inproceedings{65157bdb74b742c4ac629d395bc7c745,
title = "Neighbourhood Counting for Activity Detection from Time Series Sensor Data",
abstract = "Health status along with assistive support requirements can be assessed by measures of activities of daily living. Advances in pervasive sensing and intelligent reasoning pave a way to monitor, i.e. detect and recognise, activities automatically and unobtrusively. The first task in monitoring activities is to detect when an activity has taken place based on a time series of sensor activation events. Inspired by the concepts of dynamic time warping and neighborhood counting matrix in similarity measures, this paper proposes a novel method to segment streams of sensor events for activity detection. Sensor segments may then be used as inputs to evidential ontology networks of activities for activity recognition.",
author = "Xin Hong and CD Nugent",
year = "2010",
doi = "10.1109/ITAB.2010.5687818",
language = "English",
booktitle = "Unknown Host Publication",

}

Hong, X & Nugent, CD 2010, Neighbourhood Counting for Activity Detection from Time Series Sensor Data. in Unknown Host Publication. Proceedings of the 10th International Conference on Information Technology and Applications in Biomedicine, 1/01/10. https://doi.org/10.1109/ITAB.2010.5687818

Neighbourhood Counting for Activity Detection from Time Series Sensor Data. / Hong, Xin; Nugent, CD.

Unknown Host Publication. 2010.

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

TY - GEN

T1 - Neighbourhood Counting for Activity Detection from Time Series Sensor Data

AU - Hong, Xin

AU - Nugent, CD

PY - 2010

Y1 - 2010

N2 - Health status along with assistive support requirements can be assessed by measures of activities of daily living. Advances in pervasive sensing and intelligent reasoning pave a way to monitor, i.e. detect and recognise, activities automatically and unobtrusively. The first task in monitoring activities is to detect when an activity has taken place based on a time series of sensor activation events. Inspired by the concepts of dynamic time warping and neighborhood counting matrix in similarity measures, this paper proposes a novel method to segment streams of sensor events for activity detection. Sensor segments may then be used as inputs to evidential ontology networks of activities for activity recognition.

AB - Health status along with assistive support requirements can be assessed by measures of activities of daily living. Advances in pervasive sensing and intelligent reasoning pave a way to monitor, i.e. detect and recognise, activities automatically and unobtrusively. The first task in monitoring activities is to detect when an activity has taken place based on a time series of sensor activation events. Inspired by the concepts of dynamic time warping and neighborhood counting matrix in similarity measures, this paper proposes a novel method to segment streams of sensor events for activity detection. Sensor segments may then be used as inputs to evidential ontology networks of activities for activity recognition.

U2 - 10.1109/ITAB.2010.5687818

DO - 10.1109/ITAB.2010.5687818

M3 - Conference contribution

BT - Unknown Host Publication

ER -