Flat foot classification using principal component analysis applied to ground reaction forces

A. Bertani, A. Cappello, F. Catani, M. G. Benedetti, S. Giannini

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

Abstract

Statistical pattern recognition techniques were applied to discriminate between healthy and flat foot children through ground reaction force (GRF) measurements, 28 young subjects (age 11.8±1.8) with symptomatic flexible flat foot, and 13 healthy subjects (age 10.1±1.4) took part on this preliminar study. The Karhunen-Loeve expansion with Fukunaga-Koontz normalization was applied to each GRF component to extract concise and discriminant features from the original data. The best performances of the classifying process were obtained using three principal components of both vertical and fore-aft GRF projections. Both linear and quadratic Bayes classifiers were designed with 9.2% and 4.9% total this misclassification errors for vertical, and 14.9% and 9.5% for fore-aft projections, respectively. Analysis of correlation between the patterns of each class and the first principal component demonstrates that the most representative factors in the functional diagnosis of flat foot are the less absorption in the fore-aft component and the reduction of the second vertical peak during push-off.

Original languageEnglish
Title of host publicationInternational Conference on Simulations in Biomedicine, Proceedings, BIOMED
EditorsH. Power, C.A. Brebbia, J. Kenny
PublisherComputational Mechanics Publ
Pages259-268
Number of pages10
Publication statusPublished - 1997
EventProceedings of the 1997 4th International Conference on Simulations in Biomedicine, BIOMED - Acquasparta, Italy
Duration: Jun 9 1997Jun 11 1997

Other

OtherProceedings of the 1997 4th International Conference on Simulations in Biomedicine, BIOMED
CityAcquasparta, Italy
Period6/9/976/11/97

Fingerprint

Force measurement
Principal component analysis
Pattern recognition
Classifiers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Bertani, A., Cappello, A., Catani, F., Benedetti, M. G., & Giannini, S. (1997). Flat foot classification using principal component analysis applied to ground reaction forces. In H. Power, C. A. Brebbia, & J. Kenny (Eds.), International Conference on Simulations in Biomedicine, Proceedings, BIOMED (pp. 259-268). Computational Mechanics Publ.

Flat foot classification using principal component analysis applied to ground reaction forces. / Bertani, A.; Cappello, A.; Catani, F.; Benedetti, M. G.; Giannini, S.

International Conference on Simulations in Biomedicine, Proceedings, BIOMED. ed. / H. Power; C.A. Brebbia; J. Kenny. Computational Mechanics Publ, 1997. p. 259-268.

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

Bertani, A, Cappello, A, Catani, F, Benedetti, MG & Giannini, S 1997, Flat foot classification using principal component analysis applied to ground reaction forces. in H Power, CA Brebbia & J Kenny (eds), International Conference on Simulations in Biomedicine, Proceedings, BIOMED. Computational Mechanics Publ, pp. 259-268, Proceedings of the 1997 4th International Conference on Simulations in Biomedicine, BIOMED, Acquasparta, Italy, 6/9/97.
Bertani A, Cappello A, Catani F, Benedetti MG, Giannini S. Flat foot classification using principal component analysis applied to ground reaction forces. In Power H, Brebbia CA, Kenny J, editors, International Conference on Simulations in Biomedicine, Proceedings, BIOMED. Computational Mechanics Publ. 1997. p. 259-268
Bertani, A. ; Cappello, A. ; Catani, F. ; Benedetti, M. G. ; Giannini, S. / Flat foot classification using principal component analysis applied to ground reaction forces. International Conference on Simulations in Biomedicine, Proceedings, BIOMED. editor / H. Power ; C.A. Brebbia ; J. Kenny. Computational Mechanics Publ, 1997. pp. 259-268
@inproceedings{354a84d433dc400bb09dd13cb995354d,
title = "Flat foot classification using principal component analysis applied to ground reaction forces",
abstract = "Statistical pattern recognition techniques were applied to discriminate between healthy and flat foot children through ground reaction force (GRF) measurements, 28 young subjects (age 11.8±1.8) with symptomatic flexible flat foot, and 13 healthy subjects (age 10.1±1.4) took part on this preliminar study. The Karhunen-Loeve expansion with Fukunaga-Koontz normalization was applied to each GRF component to extract concise and discriminant features from the original data. The best performances of the classifying process were obtained using three principal components of both vertical and fore-aft GRF projections. Both linear and quadratic Bayes classifiers were designed with 9.2{\%} and 4.9{\%} total this misclassification errors for vertical, and 14.9{\%} and 9.5{\%} for fore-aft projections, respectively. Analysis of correlation between the patterns of each class and the first principal component demonstrates that the most representative factors in the functional diagnosis of flat foot are the less absorption in the fore-aft component and the reduction of the second vertical peak during push-off.",
author = "A. Bertani and A. Cappello and F. Catani and Benedetti, {M. G.} and S. Giannini",
year = "1997",
language = "English",
pages = "259--268",
editor = "H. Power and C.A. Brebbia and J. Kenny",
booktitle = "International Conference on Simulations in Biomedicine, Proceedings, BIOMED",
publisher = "Computational Mechanics Publ",

}

TY - GEN

T1 - Flat foot classification using principal component analysis applied to ground reaction forces

AU - Bertani, A.

AU - Cappello, A.

AU - Catani, F.

AU - Benedetti, M. G.

AU - Giannini, S.

PY - 1997

Y1 - 1997

N2 - Statistical pattern recognition techniques were applied to discriminate between healthy and flat foot children through ground reaction force (GRF) measurements, 28 young subjects (age 11.8±1.8) with symptomatic flexible flat foot, and 13 healthy subjects (age 10.1±1.4) took part on this preliminar study. The Karhunen-Loeve expansion with Fukunaga-Koontz normalization was applied to each GRF component to extract concise and discriminant features from the original data. The best performances of the classifying process were obtained using three principal components of both vertical and fore-aft GRF projections. Both linear and quadratic Bayes classifiers were designed with 9.2% and 4.9% total this misclassification errors for vertical, and 14.9% and 9.5% for fore-aft projections, respectively. Analysis of correlation between the patterns of each class and the first principal component demonstrates that the most representative factors in the functional diagnosis of flat foot are the less absorption in the fore-aft component and the reduction of the second vertical peak during push-off.

AB - Statistical pattern recognition techniques were applied to discriminate between healthy and flat foot children through ground reaction force (GRF) measurements, 28 young subjects (age 11.8±1.8) with symptomatic flexible flat foot, and 13 healthy subjects (age 10.1±1.4) took part on this preliminar study. The Karhunen-Loeve expansion with Fukunaga-Koontz normalization was applied to each GRF component to extract concise and discriminant features from the original data. The best performances of the classifying process were obtained using three principal components of both vertical and fore-aft GRF projections. Both linear and quadratic Bayes classifiers were designed with 9.2% and 4.9% total this misclassification errors for vertical, and 14.9% and 9.5% for fore-aft projections, respectively. Analysis of correlation between the patterns of each class and the first principal component demonstrates that the most representative factors in the functional diagnosis of flat foot are the less absorption in the fore-aft component and the reduction of the second vertical peak during push-off.

UR - http://www.scopus.com/inward/record.url?scp=0030677921&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030677921&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030677921

SP - 259

EP - 268

BT - International Conference on Simulations in Biomedicine, Proceedings, BIOMED

A2 - Power, H.

A2 - Brebbia, C.A.

A2 - Kenny, J.

PB - Computational Mechanics Publ

ER -