Format

Send to

Choose Destination
See comment in PubMed Commons below
Int J Environ Res Public Health. 2014 Apr 4;11(4):3822-44. doi: 10.3390/ijerph110403822.

Gait recognition and walking exercise intensity estimation.

Author information

1
Department of Computer Science and Information Engineering, National Taipei University, No. 151, University Road, Sanshia District, New Taipei City 23741, Taiwan. bslin@mail.ntpu.edu.tw.
2
Department of Computer Science and Information Engineering, National Taipei University, No. 151, University Road, Sanshia District, New Taipei City 23741, Taiwan. raistoliu@gmail.com.
3
Department of Electronic Engineering, National Ilan University, No. 1, Sec. 1, Shenlung Road, Yilan 260, Taiwan. chu@niu.edu.tw.
4
Department of Electrical Engineering, National Taipei University, No. 151, University Road, Sanshia District, New Taipei City 23741, Taiwan. gejan@mail.ntpu.edu.tw.
5
Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei 10617, Taiwan. geniustom@gmail.com.

Abstract

Cardiovascular patients consult doctors for advice regarding regular exercise, whereas obese patients must self-manage their weight. Because a system for permanently monitoring and tracking patients' exercise intensities and workouts is necessary, a system for recognizing gait and estimating walking exercise intensity was proposed. For gait recognition analysis, αβ filters were used to improve the recognition of athletic attitude. Furthermore, empirical mode decomposition (EMD) was used to filter the noise of patients' attitude to acquire the Fourier transform energy spectrum. Linear discriminant analysis was then applied to this energy spectrum for training and recognition. When the gait or motion was recognized, the walking exercise intensity was estimated. In addition, this study addressed the correlation between inertia and exercise intensity by using the residual function of the EMD and quadratic approximation to filter the effect of the baseline drift integral of the acceleration sensor. The increase in the determination coefficient of the regression equation from 0.55 to 0.81 proved that the accuracy of the method for estimating walking exercise intensity proposed by Kurihara was improved in this study.

PMID:
24714057
PMCID:
PMC4024985
DOI:
10.3390/ijerph110403822
[Indexed for MEDLINE]
Free PMC Article
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
    Loading ...
    Support Center