0
Research Papers

Predicting Complete Ground Reaction Forces and Moments During Gait With Insole Plantar Pressure Information Using a Wavelet Neural Network

[+] Author and Article Information
Taeyong Sim

Department of Bio-Mechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
300 Chunchun, Jangan,
Suwon, Gyeonggi 440-746, Korea
e-mail: tysim@skku.edu

Hyunbin Kwon

Department of Bio-Mechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
300 Chunchun, Jangan,
Suwon, Gyeonggi 440-746, Korea
e-mail: slimshady15@naver.com

Seung Eel Oh

Department of Bio-Mechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
300 Chunchun, Jangan,
Suwon, Gyeonggi 440-746, Korea
e-mail: dr51@skku.edu

Su-Bin Joo

Department of Bio-Mechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
300 Chunchun, Jangan,
Suwon, Gyeonggi 440-746, Korea
e-mail: 1001subin@naver.com

Ahnryul Choi

Division of Cardiovascular Medicine,
Department of Internal Medicine,
The University of Texas Health
Science Center at Houston,
6431 Fannin Street, MSB 1.246,
Houston, TX 77030
e-mail: avery@skku.edu

Hyun Mu Heo

Department of Bio-Mechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
300 Chunchun, Jangan,
Suwon, Gyeonggi 440-746, Korea
e-mail: hhmoo91@naver.com

Kisun Kim

SWINGBANK Ltd.,
7F Yeoam Building,
254-4 Seohyeon, Bundang,
Seongnam, Gyeonggi 463-824, Korea
e-mail: kskim@swingbank.com

Joung Hwan Mun

Professor
Department of Bio-Mechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
300 Chunchun, Jangan,
Suwon, Gyeonggi 440-746, Korea
e-mail: jmun@skku.edu

1Corresponding author.

Manuscript received November 25, 2014; final manuscript received June 17, 2015; published online July 1, 2015. Assoc. Editor: Kenneth Fischer.

J Biomech Eng 137(9), 091001 (Sep 01, 2015) (9 pages) Paper No: BIO-14-1585; doi: 10.1115/1.4030892 History: Received November 25, 2014; Revised June 17, 2015; Online July 01, 2015

In general, three-dimensional ground reaction forces (GRFs) and ground reaction moments (GRMs) that occur during human gait are measured using a force plate, which are expensive and have spatial limitations. Therefore, we proposed a prediction model for GRFs and GRMs, which only uses plantar pressure information measured from insole pressure sensors with a wavelet neural network (WNN) and principal component analysis-mutual information (PCA-MI). For this, the prediction model estimated GRFs and GRMs with three different gait speeds (slow, normal, and fast groups) and healthy/pathological gait patterns (healthy and adolescent idiopathic scoliosis (AIS) groups). Model performance was validated using correlation coefficients (r) and the normalized root mean square error (NRMSE%) and was compared to the prediction accuracy of the previous methods using the same dataset. As a result, the performance of the GRF and GRM prediction model proposed in this study (slow group: r = 0.840–0.989 and NRMSE% = 10.693–15.894%; normal group: r = 0.847–0.988 and NRMSE% = 10.920–19.216%; fast group: r = 0.823–0.953 and NRMSE% = 12.009–20.182%; healthy group: r = 0.836–0.976 and NRMSE% = 12.920–18.088%; and AIS group: r = 0.917–0.993 and NRMSE% = 7.914–15.671%) was better than that of the prediction models suggested in previous studies for every group and component (p < 0.05 or 0.01). The results indicated that the proposed model has improved performance compared to previous prediction models.

FIGURES IN THIS ARTICLE
<>
Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Block diagram of the model: N indicates the number of trials and Ni is the number of input variables

Grahic Jump Location
Fig. 2

The process of the data acquisition for each group and the block diagram of the protocol for generating WNN model. Bolded boxes represent the acquired dataset from plantar pressure sensors and the dotted boxes represent the acquired dataset from force plates.

Grahic Jump Location
Fig. 3

WNN structures with Ni inputs, M hidden wavelons and one output, which were used to predict each component of GRF and GRM

Grahic Jump Location
Fig. 4

The measured and predicted (a) GRF components (FAP, FML, and FV) and (b) GRM components (MAP, MML, and MV) for the overall group during a gait cycle. The measured and predicted results are represented with dashed and solid lines, respectively.

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In