Activity Recognition Based on an Accelerometer in a Smartphone Using an FFT-Based New Feature and Fusion Methods

Yang XUE; Yaoquan HU; Lianwen JIN

doi:10.1587/transinf.E97.D.2182

Activity Recognition Based on an Accelerometer in a Smartphone Using an FFT-Based New Feature and Fusion Methods

Yang XUE, Yaoquan HU, Lianwen JIN

Full Text Views

0

Share
Cite this

Summary :

With the development of personal electronic equipment, the use of a smartphone with a tri-axial accelerometer to detect human physical activity is becoming popular. In this paper, we propose a new feature based on FFT for activity recognition from tri-axial acceleration signals. To improve the classification performance, two fusion methods, minimal distance optimization (MDO) and variance contribution ranking (VCR), are proposed. The new proposed feature achieves a recognition rate of 92.41%, which outperforms six traditional time- or frequency-domain features. Furthermore, the proposed fusion methods effectively improve the recognition rates. In particular, the average accuracy based on class fusion VCR (CFVCR) is 97.01%, which results in an improvement in accuracy of 4.14% compared with the results without any fusion. Experiments confirm the effectiveness of the new proposed feature and fusion methods.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.8 pp.2182-2186

Publication Date: 2014/08/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.2182

Type of Manuscript: LETTER

Category: Human-computer Interaction

Authors

Yang XUE
  South China University of Technology
Yaoquan HU
  South China University of Technology
Lianwen JIN
  South China University of Technology

Keyword

acceleration data, activity recognition, feature extraction, fusion method, tri-axial accelerometer

Cite this

Copy

Yang XUE, Yaoquan HU, Lianwen JIN, "Activity Recognition Based on an Accelerometer in a Smartphone Using an FFT-Based New Feature and Fusion Methods" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 8, pp. 2182-2186, August 2014, doi: 10.1587/transinf.E97.D.2182.
Abstract: With the development of personal electronic equipment, the use of a smartphone with a tri-axial accelerometer to detect human physical activity is becoming popular. In this paper, we propose a new feature based on FFT for activity recognition from tri-axial acceleration signals. To improve the classification performance, two fusion methods, minimal distance optimization (MDO) and variance contribution ranking (VCR), are proposed. The new proposed feature achieves a recognition rate of 92.41%, which outperforms six traditional time- or frequency-domain features. Furthermore, the proposed fusion methods effectively improve the recognition rates. In particular, the average accuracy based on class fusion VCR (CFVCR) is 97.01%, which results in an improvement in accuracy of 4.14% compared with the results without any fusion. Experiments confirm the effectiveness of the new proposed feature and fusion methods.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.2182/_p

Copy

@ARTICLE{e97-d_8_2182,
author={Yang XUE, Yaoquan HU, Lianwen JIN, },
journal={IEICE TRANSACTIONS on Information},
title={Activity Recognition Based on an Accelerometer in a Smartphone Using an FFT-Based New Feature and Fusion Methods},
year={2014},
volume={E97-D},
number={8},
pages={2182-2186},
abstract={With the development of personal electronic equipment, the use of a smartphone with a tri-axial accelerometer to detect human physical activity is becoming popular. In this paper, we propose a new feature based on FFT for activity recognition from tri-axial acceleration signals. To improve the classification performance, two fusion methods, minimal distance optimization (MDO) and variance contribution ranking (VCR), are proposed. The new proposed feature achieves a recognition rate of 92.41%, which outperforms six traditional time- or frequency-domain features. Furthermore, the proposed fusion methods effectively improve the recognition rates. In particular, the average accuracy based on class fusion VCR (CFVCR) is 97.01%, which results in an improvement in accuracy of 4.14% compared with the results without any fusion. Experiments confirm the effectiveness of the new proposed feature and fusion methods.},
keywords={},
doi={10.1587/transinf.E97.D.2182},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - Activity Recognition Based on an Accelerometer in a Smartphone Using an FFT-Based New Feature and Fusion Methods
T2 - IEICE TRANSACTIONS on Information
SP - 2182
EP - 2186
AU - Yang XUE
AU - Yaoquan HU
AU - Lianwen JIN
PY - 2014
DO - 10.1587/transinf.E97.D.2182
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2014
AB - With the development of personal electronic equipment, the use of a smartphone with a tri-axial accelerometer to detect human physical activity is becoming popular. In this paper, we propose a new feature based on FFT for activity recognition from tri-axial acceleration signals. To improve the classification performance, two fusion methods, minimal distance optimization (MDO) and variance contribution ranking (VCR), are proposed. The new proposed feature achieves a recognition rate of 92.41%, which outperforms six traditional time- or frequency-domain features. Furthermore, the proposed fusion methods effectively improve the recognition rates. In particular, the average accuracy based on class fusion VCR (CFVCR) is 97.01%, which results in an improvement in accuracy of 4.14% compared with the results without any fusion. Experiments confirm the effectiveness of the new proposed feature and fusion methods.
ER -