Duration discretisation for activity recognition

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Activity recognition has become a key component within smart environments that aim at providing assistive solutions for their users. Learning high level activities from low level sensor data depends on several parameters, one of which is the duration of the activities themselves. Nevertheless, directly incorporating continuous duration values into a model is a complex process and may not prove to be very qualitative. In this paper we aim at discretising activity related durations using different clustering algorithms. We explore the possibility of discretising duration data through the use of rudimentary clustering algorithms such as visual inspection to more established methods such as model based clustering. In addition, a probabilistic model is built that predicts both person and activities from the observed values of sensor sequence, time and discrete duration values. Each of the models created is compared in terms of its performance in the prediction of activities. Following analysis of the results attained it has been found that irrespective of the clustering algorithm used for duration discretisation, incorporating the duration information increases the prediction performance. Prediction accuracy was improved by almost 3% when the model was built incorporating durations.
LanguageEnglish
Pages277-295
JournalTechnology and Health Care
Volume20
Issue number4
DOIs
Publication statusPublished - 2012

Fingerprint

Clustering algorithms
Sensors
Inspection

Keywords

  • Activity recognition
  • duration
  • clustering algorithms
  • discretisation

Cite this

@article{107d4245bd6e451ebf8409c27b88a0db,
title = "Duration discretisation for activity recognition",
abstract = "Activity recognition has become a key component within smart environments that aim at providing assistive solutions for their users. Learning high level activities from low level sensor data depends on several parameters, one of which is the duration of the activities themselves. Nevertheless, directly incorporating continuous duration values into a model is a complex process and may not prove to be very qualitative. In this paper we aim at discretising activity related durations using different clustering algorithms. We explore the possibility of discretising duration data through the use of rudimentary clustering algorithms such as visual inspection to more established methods such as model based clustering. In addition, a probabilistic model is built that predicts both person and activities from the observed values of sensor sequence, time and discrete duration values. Each of the models created is compared in terms of its performance in the prediction of activities. Following analysis of the results attained it has been found that irrespective of the clustering algorithm used for duration discretisation, incorporating the duration information increases the prediction performance. Prediction accuracy was improved by almost 3{\%} when the model was built incorporating durations.",
keywords = "Activity recognition, duration, clustering algorithms, discretisation",
author = "Priyanka Chaurasia and Sally McClean and Bryan Scotney and CD Nugent",
year = "2012",
doi = "10.3233/THC-2012-0677",
language = "English",
volume = "20",
pages = "277--295",
number = "4",

}

Duration discretisation for activity recognition. / Chaurasia, Priyanka; McClean, Sally; Scotney, Bryan; Nugent, CD.

Vol. 20, No. 4, 2012, p. 277-295.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Duration discretisation for activity recognition

AU - Chaurasia, Priyanka

AU - McClean, Sally

AU - Scotney, Bryan

AU - Nugent, CD

PY - 2012

Y1 - 2012

N2 - Activity recognition has become a key component within smart environments that aim at providing assistive solutions for their users. Learning high level activities from low level sensor data depends on several parameters, one of which is the duration of the activities themselves. Nevertheless, directly incorporating continuous duration values into a model is a complex process and may not prove to be very qualitative. In this paper we aim at discretising activity related durations using different clustering algorithms. We explore the possibility of discretising duration data through the use of rudimentary clustering algorithms such as visual inspection to more established methods such as model based clustering. In addition, a probabilistic model is built that predicts both person and activities from the observed values of sensor sequence, time and discrete duration values. Each of the models created is compared in terms of its performance in the prediction of activities. Following analysis of the results attained it has been found that irrespective of the clustering algorithm used for duration discretisation, incorporating the duration information increases the prediction performance. Prediction accuracy was improved by almost 3% when the model was built incorporating durations.

AB - Activity recognition has become a key component within smart environments that aim at providing assistive solutions for their users. Learning high level activities from low level sensor data depends on several parameters, one of which is the duration of the activities themselves. Nevertheless, directly incorporating continuous duration values into a model is a complex process and may not prove to be very qualitative. In this paper we aim at discretising activity related durations using different clustering algorithms. We explore the possibility of discretising duration data through the use of rudimentary clustering algorithms such as visual inspection to more established methods such as model based clustering. In addition, a probabilistic model is built that predicts both person and activities from the observed values of sensor sequence, time and discrete duration values. Each of the models created is compared in terms of its performance in the prediction of activities. Following analysis of the results attained it has been found that irrespective of the clustering algorithm used for duration discretisation, incorporating the duration information increases the prediction performance. Prediction accuracy was improved by almost 3% when the model was built incorporating durations.

KW - Activity recognition

KW - duration

KW - clustering algorithms

KW - discretisation

U2 - 10.3233/THC-2012-0677

DO - 10.3233/THC-2012-0677

M3 - Article

VL - 20

SP - 277

EP - 295

IS - 4

ER -