Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological Brake
A passive controlled ankle foot orthosis (PICAFO) used a passive actuator such as Magnetorheological (MR) brake to control the ankle stiffness. The PICAFO used two kinds of sensors, such as Electromyography (EMG) signal and ankle position (two inputs) to determine the amount of stiffness (one output...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2020-11-01
|
Series: | Open Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1515/eng-2021-0010 |
id |
doaj-f53a34b89b794a90bcd0c6d5645d6300 |
---|---|
record_format |
Article |
spelling |
doaj-f53a34b89b794a90bcd0c6d5645d63002021-10-03T07:42:30ZengDe GruyterOpen Engineering2391-54392020-11-011119110110.1515/eng-2021-0010eng-2021-0010Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological BrakeAdiputra Dimas0Azizi Abdul Rahman Mohd1Bahiuddin Irfan2Ubaidillah3Imaduddin Fitrian4Nazmi Nurhazimah5Electrical Engineering Department, Institut Teknologi Telkom Surabaya, Jalan Gayungan PTT17-19, Surabaya60234, IndonesiaMalaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur,Wilayah Persekutuan Kuala Lumpur, MalaysiaMalaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur,Wilayah Persekutuan Kuala Lumpur, MalaysiaMechanical Engineering Department, Faculty of Engineering, Universitas Sebelas Maret, Jalan Ir. Sutami 36 A, Kentingan, Surakarta, 57126, Central Java, IndonesiaMechanical Engineering Department, Faculty of Engineering, Universitas Sebelas Maret, Jalan Ir. Sutami 36 A, Kentingan, Surakarta, 57126, Central Java, IndonesiaMalaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur,Wilayah Persekutuan Kuala Lumpur, MalaysiaA passive controlled ankle foot orthosis (PICAFO) used a passive actuator such as Magnetorheological (MR) brake to control the ankle stiffness. The PICAFO used two kinds of sensors, such as Electromyography (EMG) signal and ankle position (two inputs) to determine the amount of stiffness (one output) to be generated by the MR brake. As the overall weight and design of an orthotic device must be optimized, the sensor numbers on PICAFO wanted to be reduced. To do that, a machine learning approach was implemented to simplify the previous stiffness function. In this paper, Non-linear Autoregressive Exogeneous (NARX) neural network were used to generate the simplified function. A total of 2060 data were used to build the network with detail such as 1309 training data, 281 validation data, 281 testing data 1, and 189 testing data 2. Three training algorithms were used such as Levenberg-Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient. The result shows that the function can be simplified into one input (ankle position) – one output (stiffness). Optimized result was shown by the NARX neural network with 15 hidden layers and trained using Bayesian Regularization with delay 2. In this case, the testing data shows R-value of 0.992 and MSE of 19.16.https://doi.org/10.1515/eng-2021-0010magnetorheological brakedamping stiffnesssensor numbersmachine learningnonlinear autoregressive exogenous |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Adiputra Dimas Azizi Abdul Rahman Mohd Bahiuddin Irfan Ubaidillah Imaduddin Fitrian Nazmi Nurhazimah |
spellingShingle |
Adiputra Dimas Azizi Abdul Rahman Mohd Bahiuddin Irfan Ubaidillah Imaduddin Fitrian Nazmi Nurhazimah Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological Brake Open Engineering magnetorheological brake damping stiffness sensor numbers machine learning nonlinear autoregressive exogenous |
author_facet |
Adiputra Dimas Azizi Abdul Rahman Mohd Bahiuddin Irfan Ubaidillah Imaduddin Fitrian Nazmi Nurhazimah |
author_sort |
Adiputra Dimas |
title |
Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological Brake |
title_short |
Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological Brake |
title_full |
Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological Brake |
title_fullStr |
Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological Brake |
title_full_unstemmed |
Sensor Number Optimization Using Neural Network for Ankle Foot Orthosis Equipped with Magnetorheological Brake |
title_sort |
sensor number optimization using neural network for ankle foot orthosis equipped with magnetorheological brake |
publisher |
De Gruyter |
series |
Open Engineering |
issn |
2391-5439 |
publishDate |
2020-11-01 |
description |
A passive controlled ankle foot orthosis (PICAFO) used a passive actuator such as Magnetorheological (MR) brake to control the ankle stiffness. The PICAFO used two kinds of sensors, such as Electromyography (EMG) signal and ankle position (two inputs) to determine the amount of stiffness (one output) to be generated by the MR brake. As the overall weight and design of an orthotic device must be optimized, the sensor numbers on PICAFO wanted to be reduced. To do that, a machine learning approach was implemented to simplify the previous stiffness function. In this paper, Non-linear Autoregressive Exogeneous (NARX) neural network were used to generate the simplified function. A total of 2060 data were used to build the network with detail such as 1309 training data, 281 validation data, 281 testing data 1, and 189 testing data 2. Three training algorithms were used such as Levenberg-Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient. The result shows that the function can be simplified into one input (ankle position) – one output (stiffness). Optimized result was shown by the NARX neural network with 15 hidden layers and trained using Bayesian Regularization with delay 2. In this case, the testing data shows R-value of 0.992 and MSE of 19.16. |
topic |
magnetorheological brake damping stiffness sensor numbers machine learning nonlinear autoregressive exogenous |
url |
https://doi.org/10.1515/eng-2021-0010 |
work_keys_str_mv |
AT adiputradimas sensornumberoptimizationusingneuralnetworkforanklefootorthosisequippedwithmagnetorheologicalbrake AT aziziabdulrahmanmohd sensornumberoptimizationusingneuralnetworkforanklefootorthosisequippedwithmagnetorheologicalbrake AT bahiuddinirfan sensornumberoptimizationusingneuralnetworkforanklefootorthosisequippedwithmagnetorheologicalbrake AT ubaidillah sensornumberoptimizationusingneuralnetworkforanklefootorthosisequippedwithmagnetorheologicalbrake AT imaduddinfitrian sensornumberoptimizationusingneuralnetworkforanklefootorthosisequippedwithmagnetorheologicalbrake AT nazminurhazimah sensornumberoptimizationusingneuralnetworkforanklefootorthosisequippedwithmagnetorheologicalbrake |
_version_ |
1716846153219178496 |