Segmenting sensor data for activity monitoring in smart environments

Xin Hong, CD Nugent

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Within a smart environment, sensors have the ability to perceive changes of the environment itself and can therefore be used to infer high-level information such as activity behaviours. Sensor events collected over a period of time may contain several activities. The fundamental process of any automatic activity monitoring system is therefore to process streams of sensor events and detect occurrences of activities. In this study, we propose three segmentation algorithms to separate time series sensor data into segments to be further processed by an activity recognition algorithm. A preliminary evaluation of the approaches developed has been conducted on a data set collected from a single person living in an apartment over a period of 28 days. The results show that the proposed approaches can segment sensor data to detect activities and infer sensor segments to recognise activities with accuracies of 81.6, 81.6 and 82.9%, respectively.
LanguageEnglish
Pages545-559
JournalPersonal and Ubiquitous Computing
Volume17
Issue number3
DOIs
Publication statusPublished - 2013

Fingerprint

Monitoring
Sensors
Sensor
Time series

Keywords

  • Activity detection
  • Evidential modelling
  • Smart environments
  • Time series sensor segmentation

Cite this

@article{76a35447012f4d068a6b0bf1ba37a33c,
title = "Segmenting sensor data for activity monitoring in smart environments",
abstract = "Within a smart environment, sensors have the ability to perceive changes of the environment itself and can therefore be used to infer high-level information such as activity behaviours. Sensor events collected over a period of time may contain several activities. The fundamental process of any automatic activity monitoring system is therefore to process streams of sensor events and detect occurrences of activities. In this study, we propose three segmentation algorithms to separate time series sensor data into segments to be further processed by an activity recognition algorithm. A preliminary evaluation of the approaches developed has been conducted on a data set collected from a single person living in an apartment over a period of 28 days. The results show that the proposed approaches can segment sensor data to detect activities and infer sensor segments to recognise activities with accuracies of 81.6, 81.6 and 82.9{\%}, respectively.",
keywords = "Activity detection, Evidential modelling, Smart environments, Time series sensor segmentation",
author = "Xin Hong and CD Nugent",
year = "2013",
doi = "10.1007/s00779-012-0507-4",
language = "English",
volume = "17",
pages = "545--559",
journal = "Personal and Ubiquitous Computing",
issn = "1617-4909",
number = "3",

}

Segmenting sensor data for activity monitoring in smart environments. / Hong, Xin; Nugent, CD.

In: Personal and Ubiquitous Computing, Vol. 17, No. 3, 2013, p. 545-559.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Segmenting sensor data for activity monitoring in smart environments

AU - Hong, Xin

AU - Nugent, CD

PY - 2013

Y1 - 2013

N2 - Within a smart environment, sensors have the ability to perceive changes of the environment itself and can therefore be used to infer high-level information such as activity behaviours. Sensor events collected over a period of time may contain several activities. The fundamental process of any automatic activity monitoring system is therefore to process streams of sensor events and detect occurrences of activities. In this study, we propose three segmentation algorithms to separate time series sensor data into segments to be further processed by an activity recognition algorithm. A preliminary evaluation of the approaches developed has been conducted on a data set collected from a single person living in an apartment over a period of 28 days. The results show that the proposed approaches can segment sensor data to detect activities and infer sensor segments to recognise activities with accuracies of 81.6, 81.6 and 82.9%, respectively.

AB - Within a smart environment, sensors have the ability to perceive changes of the environment itself and can therefore be used to infer high-level information such as activity behaviours. Sensor events collected over a period of time may contain several activities. The fundamental process of any automatic activity monitoring system is therefore to process streams of sensor events and detect occurrences of activities. In this study, we propose three segmentation algorithms to separate time series sensor data into segments to be further processed by an activity recognition algorithm. A preliminary evaluation of the approaches developed has been conducted on a data set collected from a single person living in an apartment over a period of 28 days. The results show that the proposed approaches can segment sensor data to detect activities and infer sensor segments to recognise activities with accuracies of 81.6, 81.6 and 82.9%, respectively.

KW - Activity detection

KW - Evidential modelling

KW - Smart environments

KW - Time series sensor segmentation

U2 - 10.1007/s00779-012-0507-4

DO - 10.1007/s00779-012-0507-4

M3 - Article

VL - 17

SP - 545

EP - 559

JO - Personal and Ubiquitous Computing

T2 - Personal and Ubiquitous Computing

JF - Personal and Ubiquitous Computing

SN - 1617-4909

IS - 3

ER -