Performance Evaluation of Feed Forward Neural and Recurrent Neural On Real System Dataset of Robot Execution

Authors

  • Ali.k. Diryag Department of Mechanical Engineering, Faculty of Engineering, Sirte University, Libya
  • Nasar A. Ali Department of Mechanical Engineering, Faculty of Engineering, Sirte University, Libya
  • kaled M. Legweel Faculty of Engineering science & Technology, Sabha, Libya

Keywords:

Artificial Neural networks, Recurent nural, Feedforward nural, real system.NN strectuers, Proformance

Abstract

This article presents approach based on the artificial neural networks (ANN). It is employed to evaluate of performance real date set of real system. The training and testing dataset used in the experiment consists of forces and torques memorized immediately after the real robot failed in assignment execution. Two types of neural networks (NN) are utilized in order to find best performance method - feed forward neural networks (FFNN) and recurrent neural networks (RNN) and an additional evaluation would be to run test sets for each neural network to see how small an error is produced. Moreover, we investigated 24 neural structures implemented in Matlab software. The obtained results confirm that this approach can be successfully applied in this domain.

References

L .P. VeeLenturf. Analysis and applications of artificial nural networks .Prentice Hall international Uk Ltd. 1995

G. K. Venayagamoorthy , "A Successful Interdisciplinary Course on Computational Intelligence", IEEE Computational Intelligence Magazine - A special issue on Educational Issues on Computationa lIntelligence, Feb. 2009, pp. 14-23.

Krose, B. and van der Smagt, P .. An Introduction to Neural Networks, 8th Edition, The University of Amsterdam , Amsterdam , 1996

M, T, Hagan, H,B. Demuth, M. H, Beat, Neutral Networks Design, PWS ,Beston, 2005

Li, Y., Powers, D. and Wen, P.: An improved training approach for feedforward neural networks. http://david.wardpowers.info/Research/AI/papers/200002-sub-LSBNN.pdf

Murat Kayri. “Predictive Abilities of Bayesian Regularization and Levenberg–Marquardt Algorithms in Artificial Neural Networks”: A Comparative Empirical Study on Social Data. Math. Comput. Appl. 2016

Salihu . ,A. , Garko. “Evaluating Feedforward And Elman Recurrent Neural Network Performances In Time Series Forecasting” Indian Journal of Pure and Applied Mathematics · June 2015

Richard L. W, M. R, and Venayagamoorthy. “Comparison of Feedforward and Feedback Neural Network Architectures for Short Term Wind Speed Prediction”. International Joint Conference on Neural Networks, Atlanta, Georgia, USA, June 14-19, 2009

Elman, J, L. Finding structure in time. Cognitive Science,14,179 211.[Cited on p.48.],1990

M. Jordan, “Serial order: A parallel distributed processing approach, ”Adv. Psychol., 1997

D. Tank and J. Hopfield, “Neural computation by concentrating information in time,”Proc. Natl. …, 1987.

http://www.ics.uci.edu/~mlearn/MLRepository.html.

Fun, M.-H. and M. T. Hagan,” Levenberg-marquardt training for modular networks,"Proceedings of the 1996 International JointConference on Neural Networks, 468{473, 1996

Hagan, M. T. and Menhaj M. B., “Training feed forward networks with the Marquardt algorithm”, IEEE Transaction on Neural Networks, 5(6), 1994, pp 989-993.

Downloads

Published

2023-02-02