Design and testing of a genetic algorithm neural network in the assessment of gait patterns

Fong-chin Su, Wen Lan Wu

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

It is important to be able to quantify changes in gait pattern accurately in order to understand the clinical implications of surgery or rehabilitation. Although supervised feed-forward backpropagation neural networks are very efficient in many pattern-recognition tasks, the genetic algorithm neural network (GANN), which can search in some appropriate space, has not been used previously for gait-pattern recognition. This study discusses how to use the GANN approach in gait-pattern recognition, and evaluates the complexity and training strategy of the particular classification problem. Both the GANN and a traditional artificial neural network (ANN) were used to classify the gait patterns of patients with ankle arthrodesis and normal subjects. The GANN model was able to classify subjects with recognition rates of up to 98.7%. In contrast, the ANN trained by using all possible predictor variables was only able to classify the subjects with recognition rates of 89.7%. It is suggested that the GANN model is more suitable to exploit the patient's gait pattern. The value of the neuron output can be used as an index of the difference from normal. By this means, all pathological gait patterns may be presented quantitatively. Copyright (C) 2000 IPEM.

Original languageEnglish
Pages (from-to)67-74
Number of pages8
JournalMedical Engineering and Physics
Volume22
Issue number1
DOIs
Publication statusPublished - 2000 Jan 1

Fingerprint

Genetic Testing
Gait
Genetic algorithms
Neural networks
Testing
Neural Networks (Computer)
Pattern recognition
Arthrodesis
Ankle
Rehabilitation
Backpropagation
Patient rehabilitation
Surgery
Neurons

All Science Journal Classification (ASJC) codes

  • Orthopedics and Sports Medicine
  • Psychology(all)

Cite this

@article{516ef1c9ae0c41edad4e62b78681b8bc,
title = "Design and testing of a genetic algorithm neural network in the assessment of gait patterns",
abstract = "It is important to be able to quantify changes in gait pattern accurately in order to understand the clinical implications of surgery or rehabilitation. Although supervised feed-forward backpropagation neural networks are very efficient in many pattern-recognition tasks, the genetic algorithm neural network (GANN), which can search in some appropriate space, has not been used previously for gait-pattern recognition. This study discusses how to use the GANN approach in gait-pattern recognition, and evaluates the complexity and training strategy of the particular classification problem. Both the GANN and a traditional artificial neural network (ANN) were used to classify the gait patterns of patients with ankle arthrodesis and normal subjects. The GANN model was able to classify subjects with recognition rates of up to 98.7{\%}. In contrast, the ANN trained by using all possible predictor variables was only able to classify the subjects with recognition rates of 89.7{\%}. It is suggested that the GANN model is more suitable to exploit the patient's gait pattern. The value of the neuron output can be used as an index of the difference from normal. By this means, all pathological gait patterns may be presented quantitatively. Copyright (C) 2000 IPEM.",
author = "Fong-chin Su and Wu, {Wen Lan}",
year = "2000",
month = "1",
day = "1",
doi = "10.1016/S1350-4533(00)00011-4",
language = "English",
volume = "22",
pages = "67--74",
journal = "Medical Engineering and Physics",
issn = "1350-4533",
publisher = "Elsevier BV",
number = "1",

}

Design and testing of a genetic algorithm neural network in the assessment of gait patterns. / Su, Fong-chin; Wu, Wen Lan.

In: Medical Engineering and Physics, Vol. 22, No. 1, 01.01.2000, p. 67-74.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Design and testing of a genetic algorithm neural network in the assessment of gait patterns

AU - Su, Fong-chin

AU - Wu, Wen Lan

PY - 2000/1/1

Y1 - 2000/1/1

N2 - It is important to be able to quantify changes in gait pattern accurately in order to understand the clinical implications of surgery or rehabilitation. Although supervised feed-forward backpropagation neural networks are very efficient in many pattern-recognition tasks, the genetic algorithm neural network (GANN), which can search in some appropriate space, has not been used previously for gait-pattern recognition. This study discusses how to use the GANN approach in gait-pattern recognition, and evaluates the complexity and training strategy of the particular classification problem. Both the GANN and a traditional artificial neural network (ANN) were used to classify the gait patterns of patients with ankle arthrodesis and normal subjects. The GANN model was able to classify subjects with recognition rates of up to 98.7%. In contrast, the ANN trained by using all possible predictor variables was only able to classify the subjects with recognition rates of 89.7%. It is suggested that the GANN model is more suitable to exploit the patient's gait pattern. The value of the neuron output can be used as an index of the difference from normal. By this means, all pathological gait patterns may be presented quantitatively. Copyright (C) 2000 IPEM.

AB - It is important to be able to quantify changes in gait pattern accurately in order to understand the clinical implications of surgery or rehabilitation. Although supervised feed-forward backpropagation neural networks are very efficient in many pattern-recognition tasks, the genetic algorithm neural network (GANN), which can search in some appropriate space, has not been used previously for gait-pattern recognition. This study discusses how to use the GANN approach in gait-pattern recognition, and evaluates the complexity and training strategy of the particular classification problem. Both the GANN and a traditional artificial neural network (ANN) were used to classify the gait patterns of patients with ankle arthrodesis and normal subjects. The GANN model was able to classify subjects with recognition rates of up to 98.7%. In contrast, the ANN trained by using all possible predictor variables was only able to classify the subjects with recognition rates of 89.7%. It is suggested that the GANN model is more suitable to exploit the patient's gait pattern. The value of the neuron output can be used as an index of the difference from normal. By this means, all pathological gait patterns may be presented quantitatively. Copyright (C) 2000 IPEM.

UR - http://www.scopus.com/inward/record.url?scp=0034014848&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034014848&partnerID=8YFLogxK

U2 - 10.1016/S1350-4533(00)00011-4

DO - 10.1016/S1350-4533(00)00011-4

M3 - Article

C2 - 10817950

AN - SCOPUS:0034014848

VL - 22

SP - 67

EP - 74

JO - Medical Engineering and Physics

JF - Medical Engineering and Physics

SN - 1350-4533

IS - 1

ER -