Synchronisation of SA and AV node oscillators using PSO optimised RBF-based controllers and comparison with adaptive control
by Abdolhossein Ayoubi; Mohammad Sadegh Sanie; Moharram Kazemi
International Journal of Medical Engineering and Informatics (IJMEI), Vol. 8, No. 3, 2016

Abstract: This paper studies the synchronisation of SA and AV node oscillators using PSO optimised RBF-based controllers systems. High levels of control activities may excite unmodelled dynamics of a system. The objective is to reach a trade-off between tracking performance and parametric uncertainty. Two methods are proposed to synchronise general forms of van der Pol (VDP) model and their performance. These methods use the radial basis function (RBF)-based neural controllers for this purpose. The first method uses a standard RBF neural controller. Particle swarm optimisation (PSO) algorithm is used to derive and optimise RBF controller parameters. In the second method, an error integral term is added to the equations of RBF neural network. The coefficients of error integral component and parameters of RBF neural network are also derived and optimised via PSO algorithm. Simulation results show the effectiveness and superiority of proposed methods in both performances in comparison with the adaptive controller.

Online publication date: Thu, 30-Jun-2016

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Medical Engineering and Informatics (IJMEI):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com