Physical activity recognition using multiple sensors embedded in a wearable device

Yunyoung Nam, Seungmin Rho, Chul Ung Lee

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

In this article, we present a wearable intelligence device for activity monitoring applications. We developed and evaluated algorithms to recognize physical activities from data acquired using a 3-axis accelerometer with a single camera worn on a body. The recognition process is performed in two steps: at first the features for defining a human activity are measured by the 3-axis accelerometer sensor and the image sensor embedded in a wearable device. Then, the physical activity corresponding to the measured features is determined by applying the SVM classifier. The 3-axis accelerometer sensor computes the correlation between axes and the magnitude of the FFT for other features of an activity. Acceleration data is classified into nine activity labels. Through the image sensor, multiple optical flow vectors computed on each grid image patch are extracted as features for defining an activity. In the experiments, we showed that an overall accuracy rate of activity recognition based our method was 92.78%.

Original languageEnglish
Article number26
JournalTransactions on Embedded Computing Systems
Volume12
Issue number2
DOIs
Publication statusPublished - 2013 Feb 1

Fingerprint

Accelerometers
Image sensors
Sensors
Optical flows
Fast Fourier transforms
Labels
Classifiers
Cameras
Monitoring
Experiments

Keywords

  • Accelerometer
  • Human activity recognition
  • SVM
  • Ubiquitous
  • Wearable computing

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Physical activity recognition using multiple sensors embedded in a wearable device. / Nam, Yunyoung; Rho, Seungmin; Lee, Chul Ung.

In: Transactions on Embedded Computing Systems, Vol. 12, No. 2, 26, 01.02.2013.

Research output: Contribution to journalArticle

@article{62718ab36d194f07a2f028499684c333,
title = "Physical activity recognition using multiple sensors embedded in a wearable device",
abstract = "In this article, we present a wearable intelligence device for activity monitoring applications. We developed and evaluated algorithms to recognize physical activities from data acquired using a 3-axis accelerometer with a single camera worn on a body. The recognition process is performed in two steps: at first the features for defining a human activity are measured by the 3-axis accelerometer sensor and the image sensor embedded in a wearable device. Then, the physical activity corresponding to the measured features is determined by applying the SVM classifier. The 3-axis accelerometer sensor computes the correlation between axes and the magnitude of the FFT for other features of an activity. Acceleration data is classified into nine activity labels. Through the image sensor, multiple optical flow vectors computed on each grid image patch are extracted as features for defining an activity. In the experiments, we showed that an overall accuracy rate of activity recognition based our method was 92.78{\%}.",
keywords = "Accelerometer, Human activity recognition, SVM, Ubiquitous, Wearable computing",
author = "Yunyoung Nam and Seungmin Rho and Lee, {Chul Ung}",
year = "2013",
month = "2",
day = "1",
doi = "10.1145/2423636.2423644",
language = "English",
volume = "12",
journal = "Transactions on Embedded Computing Systems",
issn = "1539-9087",
publisher = "Association for Computing Machinery (ACM)",
number = "2",

}

TY - JOUR

T1 - Physical activity recognition using multiple sensors embedded in a wearable device

AU - Nam, Yunyoung

AU - Rho, Seungmin

AU - Lee, Chul Ung

PY - 2013/2/1

Y1 - 2013/2/1

N2 - In this article, we present a wearable intelligence device for activity monitoring applications. We developed and evaluated algorithms to recognize physical activities from data acquired using a 3-axis accelerometer with a single camera worn on a body. The recognition process is performed in two steps: at first the features for defining a human activity are measured by the 3-axis accelerometer sensor and the image sensor embedded in a wearable device. Then, the physical activity corresponding to the measured features is determined by applying the SVM classifier. The 3-axis accelerometer sensor computes the correlation between axes and the magnitude of the FFT for other features of an activity. Acceleration data is classified into nine activity labels. Through the image sensor, multiple optical flow vectors computed on each grid image patch are extracted as features for defining an activity. In the experiments, we showed that an overall accuracy rate of activity recognition based our method was 92.78%.

AB - In this article, we present a wearable intelligence device for activity monitoring applications. We developed and evaluated algorithms to recognize physical activities from data acquired using a 3-axis accelerometer with a single camera worn on a body. The recognition process is performed in two steps: at first the features for defining a human activity are measured by the 3-axis accelerometer sensor and the image sensor embedded in a wearable device. Then, the physical activity corresponding to the measured features is determined by applying the SVM classifier. The 3-axis accelerometer sensor computes the correlation between axes and the magnitude of the FFT for other features of an activity. Acceleration data is classified into nine activity labels. Through the image sensor, multiple optical flow vectors computed on each grid image patch are extracted as features for defining an activity. In the experiments, we showed that an overall accuracy rate of activity recognition based our method was 92.78%.

KW - Accelerometer

KW - Human activity recognition

KW - SVM

KW - Ubiquitous

KW - Wearable computing

UR - http://www.scopus.com/inward/record.url?scp=84874838130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874838130&partnerID=8YFLogxK

U2 - 10.1145/2423636.2423644

DO - 10.1145/2423636.2423644

M3 - Article

AN - SCOPUS:84874838130

VL - 12

JO - Transactions on Embedded Computing Systems

JF - Transactions on Embedded Computing Systems

SN - 1539-9087

IS - 2

M1 - 26

ER -