Skip to main content

A Neural Network Model for Solving Nonlinear Optimization Problems with Real-Time Applications

  • Conference paper
Advances in Neural Networks – ISNN 2009 (ISNN 2009)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 5553))

Included in the following conference series:

  • 2539 Accesses

Abstract

A new neural network model is proposed for solving nonlinear optimization problems with a general form of linear constraints. Linear constraints, which may include equality, inequality and bound constraints, are considered to cover the need for engineering applications. By employing this new model in image fusion algorithm, an optimal fusion vector is exploited to enhance the quality of fused images efficiently. The stability and convergence analysis of the novel model are proved in details. The simulation examples are used to demonstrate the validity of the proposed model.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Kalouptisidis, N.: Signal Processing Systems, Theory and design. Wiley, New York (1997)

    Google Scholar 

  2. Youshikawa, T.: Foundations of Robotics: Analysis and Control. MIT Press, Cambridge (1990)

    Google Scholar 

  3. Cichocki, A., Unbehauen, R.: Neural Networks for Optimization and Signal Processing. Wiley, England (1993)

    MATH  Google Scholar 

  4. Xia, X., Wang, J.: A Dual Neural Network for Kinemic Control of Redundant Robot Manipulators. IEEE Trans. Systems Man. Cybernet. 31, 147–154 (2001)

    Article  Google Scholar 

  5. Bouzerdoum, A., Pattison, T.R.: Neural Network for Quadratic Optimization with Bound Constraints. IEEE Trans. Neural Networks 4, 293–304 (1993)

    Article  Google Scholar 

  6. Tank, D.W., Hopfield, J.J.: Simple Neural Network Optimization Networks: an A/D Converter Signal Decision Network, and Linear Programming Circuit. IEEE Trans. Circ. Syst. 33, 533–542 (1986)

    Article  Google Scholar 

  7. Kennedy, M.P., Chua, L.O.: Neural Networks for Nonlinear Programming. IEEE. Trans. Circuits Systems 35, 554–562 (1998)

    Article  MathSciNet  Google Scholar 

  8. Xia, Y., Wang, J.: Recurrent Neural Networks for Optimization: the State of Art. In: Medsker, L.R., Jain, L.C. (eds.), vol. 4. CRC Press, New York (2000)

    Google Scholar 

  9. Zhang, S., Constantinides, A.G.: Lagrange programming neural networks. IEEE Trans. Circuits Systems 39, 441–452 (1992)

    Article  MATH  Google Scholar 

  10. Sudharsanan, S., Sundareshan, M.: Exponential Stability and Systematic Synthesis of a Neural Network for Quadratic Minimization. Neural Networks 4, 599–613 (1991)

    Article  Google Scholar 

  11. Wang, J.: A Deterministic Annealing Neural Network for Convex Programming. Neural Networks 7, 629–641 (1994)

    Article  MATH  Google Scholar 

  12. Xia, Y.: A New Neural Network for Solving Linear and Quadratic Programming Problems. IEEE Trans. Neural Networks 7, 1544–1547 (1996)

    Article  Google Scholar 

  13. Liang, X.B., Wang, J.: A Recurrent Neural Network for Nonlinear Optimization with a Continuously Differentiable Objective Function and Bounded Constraints. IEEE Trans. Neural Networks 11, 1251–1262 (2000)

    Article  Google Scholar 

  14. Tao, Q., Cao, G.D., Xue, M.S., Qiao, H.: A High Performance Neural Network for Solving Nonlinear Programming Problems with Hybrid Constraints. Phys. Lett. A 288, 88–94 (2001)

    Article  MathSciNet  MATH  Google Scholar 

  15. Xia, Y., Wang, J.: A General Methodology for Designing Globally Convergent Optimization Neural Networks. IEEE Trans. Neural Networks 9, 1331–1343 (1998)

    Article  Google Scholar 

  16. Yashtini, M., Malek, A.: Solving Complementarity and Variational Inequalities Problems Using Neural Networks. Appl. Math. Comput. 190, 216–230 (2007)

    MathSciNet  MATH  Google Scholar 

  17. Yashtini, M., Malek, A.: A Discrete-time Neural Network for Solving Nonlinear Convex Problems with Hybrid Constraints. Appl. Math. Comput. 195, 576–584 (2008)

    MathSciNet  MATH  Google Scholar 

  18. Malek, A., Yashtini, M.: Image Fusion Algorithms for Color and Gray Level Images Based on LCLS Method and Novel Artificial Neural Network. Neurocomputing (submitted)

    Google Scholar 

  19. Oskoei, H.G., Malek, A., Ahmadi, A.: Novel Artificial Neural Network with Simulation Aspects for Solving Linear and Quadratic Programming Problems. Comp. Math. Appl. 53, 1439–1454 (2007)

    Article  MathSciNet  MATH  Google Scholar 

  20. Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and Distributed Computation, Numerical Methods. Prentice-Hall, Englewood Cliffs (1989)

    MATH  Google Scholar 

  21. Miller, R.K., Michel, A.N.: Ordinary Differential Equations. In: Neural Network. Academic, San Diego (1982)

    Google Scholar 

  22. Pang, J.S.: A Posteriori Error Bounds for the Linearly-constrained Variational Inequality Problem. Math. Oper. Res. 12, 474–484 (1987)

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Malek, A., Yashtini, M. (2009). A Neural Network Model for Solving Nonlinear Optimization Problems with Real-Time Applications. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5553. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01513-7_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-01513-7_11

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-01512-0

  • Online ISBN: 978-3-642-01513-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics