Activity Monitoring Using a Smart Phone’s Accelerometer with Hierarchical Classification

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

64 Citations (Scopus)

Abstract

This paper presents details of a convenient andunobtrusive system for monitoring daily activities. A smartphone equipped with an embedded 3D-accelerometer was wornon the belt for the purposes of data recording. Once collectedthe data was processed to identify 6 activities offline (walking,posture transition, gentle motion, standing, sitting and lying).The processing technique adopted a novel hierarchicalclassification. In the first instance, rule-based reasoning is usedto discriminate between motion and motionless activities.Following this the classification process utilizes two multiclassSVM (support vector machines) classifiers to classify themotion and motionless activities, respectively. The classifierswere trained on data from one subject and tested on 10subjects. The experiments demonstrate that the hierarchicalmethod can reduce misclassification between motion andmotionless activities. The average accuracy was improvedcompared with using a single classifier by using thisclassification method (82.8% vs. 63.8%), and is important forproviding appropriate feedback in free living applications.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages6
Publication statusPublished - 19 Jul 2010
EventThe 6th International Conference on Intelligent Environments - Kuala Lumpur, Malaysia
Duration: 19 Jul 2010 → …

Conference

ConferenceThe 6th International Conference on Intelligent Environments
Period19/07/10 → …

Fingerprint

Accelerometers
Classifiers
Data recording
Monitoring
Smartphones
Support vector machines
Feedback
Processing
Experiments

Cite this

@inproceedings{9f529f4ed089447e85755da364ec190c,
title = "Activity Monitoring Using a Smart Phone’s Accelerometer with Hierarchical Classification",
abstract = "This paper presents details of a convenient andunobtrusive system for monitoring daily activities. A smartphone equipped with an embedded 3D-accelerometer was wornon the belt for the purposes of data recording. Once collectedthe data was processed to identify 6 activities offline (walking,posture transition, gentle motion, standing, sitting and lying).The processing technique adopted a novel hierarchicalclassification. In the first instance, rule-based reasoning is usedto discriminate between motion and motionless activities.Following this the classification process utilizes two multiclassSVM (support vector machines) classifiers to classify themotion and motionless activities, respectively. The classifierswere trained on data from one subject and tested on 10subjects. The experiments demonstrate that the hierarchicalmethod can reduce misclassification between motion andmotionless activities. The average accuracy was improvedcompared with using a single classifier by using thisclassification method (82.8{\%} vs. 63.8{\%}), and is important forproviding appropriate feedback in free living applications.",
author = "Shumei Zhang and PJ McCullagh and CD Nugent and H Zheng",
year = "2010",
month = "7",
day = "19",
language = "English",
booktitle = "Unknown Host Publication",

}

Zhang, S, McCullagh, PJ, Nugent, CD & Zheng, H 2010, Activity Monitoring Using a Smart Phone’s Accelerometer with Hierarchical Classification. in Unknown Host Publication. The 6th International Conference on Intelligent Environments, 19/07/10.

Activity Monitoring Using a Smart Phone’s Accelerometer with Hierarchical Classification. / Zhang, Shumei; McCullagh, PJ; Nugent, CD; Zheng, H.

Unknown Host Publication. 2010.

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

TY - GEN

T1 - Activity Monitoring Using a Smart Phone’s Accelerometer with Hierarchical Classification

AU - Zhang, Shumei

AU - McCullagh, PJ

AU - Nugent, CD

AU - Zheng, H

PY - 2010/7/19

Y1 - 2010/7/19

N2 - This paper presents details of a convenient andunobtrusive system for monitoring daily activities. A smartphone equipped with an embedded 3D-accelerometer was wornon the belt for the purposes of data recording. Once collectedthe data was processed to identify 6 activities offline (walking,posture transition, gentle motion, standing, sitting and lying).The processing technique adopted a novel hierarchicalclassification. In the first instance, rule-based reasoning is usedto discriminate between motion and motionless activities.Following this the classification process utilizes two multiclassSVM (support vector machines) classifiers to classify themotion and motionless activities, respectively. The classifierswere trained on data from one subject and tested on 10subjects. The experiments demonstrate that the hierarchicalmethod can reduce misclassification between motion andmotionless activities. The average accuracy was improvedcompared with using a single classifier by using thisclassification method (82.8% vs. 63.8%), and is important forproviding appropriate feedback in free living applications.

AB - This paper presents details of a convenient andunobtrusive system for monitoring daily activities. A smartphone equipped with an embedded 3D-accelerometer was wornon the belt for the purposes of data recording. Once collectedthe data was processed to identify 6 activities offline (walking,posture transition, gentle motion, standing, sitting and lying).The processing technique adopted a novel hierarchicalclassification. In the first instance, rule-based reasoning is usedto discriminate between motion and motionless activities.Following this the classification process utilizes two multiclassSVM (support vector machines) classifiers to classify themotion and motionless activities, respectively. The classifierswere trained on data from one subject and tested on 10subjects. The experiments demonstrate that the hierarchicalmethod can reduce misclassification between motion andmotionless activities. The average accuracy was improvedcompared with using a single classifier by using thisclassification method (82.8% vs. 63.8%), and is important forproviding appropriate feedback in free living applications.

M3 - Conference contribution

BT - Unknown Host Publication

ER -