Smoothing of GRF data using functional data analysis technique

W. R Wan Din, Azmin Sham Rambely, Abdul Aziz Jemain

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Filtering is necessary in most digital signal processing. Data generated by mechanical equipment usually contains noise or spikes that need to be filtered before further processing occurs. This paper describes a method for smoothing or filtering spikes or noise present in the data by using a functional data analysis approach applied to biomechanical ground reaction force data. Ground reaction force data were collected from ten military subjects, age 31 ± 6.2 years, weight 71.6 ± 10.4 kg and height 166.3 ± 5.9 cm, using the Vicon 1.4 motion analysis system, Kistler force plates and thirty nine body markers. The results show that the optimum smoothing for this kind of data is obtained using a B-spline basis, penalizing fourth derivatives and a smoothing amount lambda equal to 1e-12. Functional data analysis proved to be one of the best methods for handling ground reaction data because of its ability to smooth the data and also perform other statistical analysis after converting it in the form of functional data.

Original languageEnglish
Pages (from-to)70-77
Number of pages8
JournalInternational Journal of Applied Mathematics and Statistics
Volume47
Issue number17
Publication statusPublished - 2013

Fingerprint

Functional Data Analysis
Smoothing
Digital signal processing
Splines
Statistical methods
Derivatives
Spike
Processing
Filtering
Motion Analysis
Functional Data
B-spline
Military
Statistical Analysis
Signal Processing
Derivative
Necessary
Motion analysis

Keywords

  • B-spline
  • Functional data analysis
  • Ground reaction force
  • Smoothing

ASJC Scopus subject areas

  • Applied Mathematics

Cite this

Smoothing of GRF data using functional data analysis technique. / Din, W. R Wan; Rambely, Azmin Sham; Jemain, Abdul Aziz.

In: International Journal of Applied Mathematics and Statistics, Vol. 47, No. 17, 2013, p. 70-77.

Research output: Contribution to journalArticle

@article{e5f6913c26054f21af0081daa1022b29,
title = "Smoothing of GRF data using functional data analysis technique",
abstract = "Filtering is necessary in most digital signal processing. Data generated by mechanical equipment usually contains noise or spikes that need to be filtered before further processing occurs. This paper describes a method for smoothing or filtering spikes or noise present in the data by using a functional data analysis approach applied to biomechanical ground reaction force data. Ground reaction force data were collected from ten military subjects, age 31 ± 6.2 years, weight 71.6 ± 10.4 kg and height 166.3 ± 5.9 cm, using the Vicon 1.4 motion analysis system, Kistler force plates and thirty nine body markers. The results show that the optimum smoothing for this kind of data is obtained using a B-spline basis, penalizing fourth derivatives and a smoothing amount lambda equal to 1e-12. Functional data analysis proved to be one of the best methods for handling ground reaction data because of its ability to smooth the data and also perform other statistical analysis after converting it in the form of functional data.",
keywords = "B-spline, Functional data analysis, Ground reaction force, Smoothing",
author = "Din, {W. R Wan} and Rambely, {Azmin Sham} and Jemain, {Abdul Aziz}",
year = "2013",
language = "English",
volume = "47",
pages = "70--77",
journal = "International Journal of Applied Mathematics and Statistics",
issn = "0973-1377",
publisher = "Centre for Environment Social and Economic Research",
number = "17",

}

TY - JOUR

T1 - Smoothing of GRF data using functional data analysis technique

AU - Din, W. R Wan

AU - Rambely, Azmin Sham

AU - Jemain, Abdul Aziz

PY - 2013

Y1 - 2013

N2 - Filtering is necessary in most digital signal processing. Data generated by mechanical equipment usually contains noise or spikes that need to be filtered before further processing occurs. This paper describes a method for smoothing or filtering spikes or noise present in the data by using a functional data analysis approach applied to biomechanical ground reaction force data. Ground reaction force data were collected from ten military subjects, age 31 ± 6.2 years, weight 71.6 ± 10.4 kg and height 166.3 ± 5.9 cm, using the Vicon 1.4 motion analysis system, Kistler force plates and thirty nine body markers. The results show that the optimum smoothing for this kind of data is obtained using a B-spline basis, penalizing fourth derivatives and a smoothing amount lambda equal to 1e-12. Functional data analysis proved to be one of the best methods for handling ground reaction data because of its ability to smooth the data and also perform other statistical analysis after converting it in the form of functional data.

AB - Filtering is necessary in most digital signal processing. Data generated by mechanical equipment usually contains noise or spikes that need to be filtered before further processing occurs. This paper describes a method for smoothing or filtering spikes or noise present in the data by using a functional data analysis approach applied to biomechanical ground reaction force data. Ground reaction force data were collected from ten military subjects, age 31 ± 6.2 years, weight 71.6 ± 10.4 kg and height 166.3 ± 5.9 cm, using the Vicon 1.4 motion analysis system, Kistler force plates and thirty nine body markers. The results show that the optimum smoothing for this kind of data is obtained using a B-spline basis, penalizing fourth derivatives and a smoothing amount lambda equal to 1e-12. Functional data analysis proved to be one of the best methods for handling ground reaction data because of its ability to smooth the data and also perform other statistical analysis after converting it in the form of functional data.

KW - B-spline

KW - Functional data analysis

KW - Ground reaction force

KW - Smoothing

UR - http://www.scopus.com/inward/record.url?scp=84887535466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887535466&partnerID=8YFLogxK

M3 - Article

VL - 47

SP - 70

EP - 77

JO - International Journal of Applied Mathematics and Statistics

JF - International Journal of Applied Mathematics and Statistics

SN - 0973-1377

IS - 17

ER -