Open AccessBiodynamic Modelling of Hand for Glove Transmissibility Prediction using Artificial Neural Networks
Author(s) -
Tuan A. Z. Rahman,
Khairil Anas Md Rezali,
Azizan As’arry,
Nawal Aswan Abdul Jalil
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1262/1/012032
Subject(s) - transmissibility (structural dynamics) , artificial neural network , vibration , computer science , parametric statistics , artificial intelligence , simulation , mathematics , statistics , vibration isolation , acoustics , physics
Prediction of glove transmissibility to the hand plays an important role in order to improve its vibration reduction capability. This study presents a non-parametric biodynamic modelling of the hand based on artificial neural networks (ANNs) model for predicting the apparent mass in order to estimate the transmissibility of a glove to the hand. An experimental investigation was carried out to obtain the input-output vibration data using five subjects. Then, an ANNs model was used to map between the input and the output with its weight and bias parameters optimized using chaos-enhanced stochastic fractal search (CFS) algorithm. The results indicate that the developed ANNs hand model capable to predict the apparent mass of the human hand with an average accuracy of 97.67%.