Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan

This paper exhibits the improvement and correlation of muscle models taking into account FES incitement parameters utilizing the Nonlinear Auto-Regressive model with Exogenous Inputs (NARX) using Multi-Layer Perceptron (MLP) and Cascade Forward Neural Network (CFNN). FES stimulations with varying fr...

全面介紹

Saved in:

書目詳細資料
主要作者:	Abu Hassan, Abu Huzaifah
格式:	Thesis
語言:	English
出版:	2016
主題:	Neural networks (Computer science)
在線閱讀:	https://ir.uitm.edu.my/id/eprint/69020/1/69020.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

id	my-uitm-ir.69020
record_format	uketd_dc
spelling	my-uitm-ir.690202023-02-02T14:57:57Z Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan 2016 Abu Hassan, Abu Huzaifah Neural networks (Computer science) This paper exhibits the improvement and correlation of muscle models taking into account FES incitement parameters utilizing the Nonlinear Auto-Regressive model with Exogenous Inputs (NARX) using Multi-Layer Perceptron (MLP) and Cascade Forward Neural Network (CFNN). FES stimulations with varying frequency, pulse width and pulse duration were utilized to evaluate the muscle torque. 722 data points' focuses were utilized to make muscle model. One Step Ahead (OSA) prediction, correlation tests, and residual histogram analysis were performed to accept the model. The ideal MLP results were obtained from input lag space of 1, output lag space of 43, and hidden units 30. A total of three terms were selected to construct the final model, namely ul (t - 1), y (t - 1), and u4 (t - 1). The last MSE delivered was 1.1299. The optimal CFNN results were gained from input lag space of 1, output lag space of 5, and hidden units 20. The terms selected are similar to that of the MLP model. The final MSE produced was 1.0320. The proposed approach figured out how to rough the system well with unbiased residuals, with CFNN demonstrating 8.66% MSE change over MLP with 33.33% less hidden units. 2016 Thesis https://ir.uitm.edu.my/id/eprint/69020/ https://ir.uitm.edu.my/id/eprint/69020/1/69020.pdf text en public degree Universiti Teknologi MARA (UiTM) Faculty of Electrical Engineering Yassin, Ihsan
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
advisor	Yassin, Ihsan
topic	Neural networks (Computer science)
spellingShingle	Neural networks (Computer science) Abu Hassan, Abu Huzaifah Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan
description	This paper exhibits the improvement and correlation of muscle models taking into account FES incitement parameters utilizing the Nonlinear Auto-Regressive model with Exogenous Inputs (NARX) using Multi-Layer Perceptron (MLP) and Cascade Forward Neural Network (CFNN). FES stimulations with varying frequency, pulse width and pulse duration were utilized to evaluate the muscle torque. 722 data points' focuses were utilized to make muscle model. One Step Ahead (OSA) prediction, correlation tests, and residual histogram analysis were performed to accept the model. The ideal MLP results were obtained from input lag space of 1, output lag space of 43, and hidden units 30. A total of three terms were selected to construct the final model, namely ul (t - 1), y (t - 1), and u4 (t - 1). The last MSE delivered was 1.1299. The optimal CFNN results were gained from input lag space of 1, output lag space of 5, and hidden units 20. The terms selected are similar to that of the MLP model. The final MSE produced was 1.0320. The proposed approach figured out how to rough the system well with unbiased residuals, with CFNN demonstrating 8.66% MSE change over MLP with 33.33% less hidden units.
format	Thesis
qualification_level	Bachelor degree
author	Abu Hassan, Abu Huzaifah
author_facet	Abu Hassan, Abu Huzaifah
author_sort	Abu Hassan, Abu Huzaifah
title	Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan
title_short	Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan
title_full	Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan
title_fullStr	Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan
title_full_unstemmed	Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan
title_sort	comparison between cascade forward and multi-layer perceptron neural networks for narx functional electrical stimulation (fes) based muscle model / abu huzaifah abu hassan
granting_institution	Universiti Teknologi MARA (UiTM)
granting_department	Faculty of Electrical Engineering
publishDate	2016
url	https://ir.uitm.edu.my/id/eprint/69020/1/69020.pdf
_version_	1783735833479610368

Comparison between cascade forward and multi-layer perceptron neural networks for NARX functional electrical stimulation (FES) based muscle model / Abu Huzaifah Abu Hassan

相似書籍