Journals
Publish with us
Publishing partnerships
About us
Blog
Complexity
Journal overview
For authors
For reviewers
For editors
Table of Contents
Special Issues
Complexity
/
2019
/
Article
/
Tab 4
/
Research Article
Hybrid Approach of Finite Element Method, Kigring Metamodel, and Multiobjective Genetic Algorithm for Computational Optimization of a Flexure Elbow Joint for Upper-Limb Assistive Device
Table 4
The goodness-of-fit of the Kigring response surfaces.
Kigring metamodels
Parameters
Strain energy
Torque
Coefficient of determination
1
1
Root mean square error
7.6.10
ā10
2.4.10
ā6
Relative maximum absolute error
0
0
Relative average absolute error
0
0
Neural network
Parameters
Strain energy
Torque
Coefficient of determination
0.88
0.91
Root mean square error
0.02
98.54
Relative maximum absolute error
62.52
52.07
Relative average absolute error
25.85
23.13
Full second order polynomials
Parameters
Strain energy
Torque
Coefficient of determination
0.93
0.96
Root mean square error
0.02
59.50
Relative maximum absolute error
50.08
40.86
Relative average absolute error
22.18
14.33