ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

A neuro-adaptive augmented optimal dynamic inversion approach for effective and efficient treatment of chronic myelogenous leukemia

Padhi, Radhakant and Kothari, Mangal (2006) A neuro-adaptive augmented optimal dynamic inversion approach for effective and efficient treatment of chronic myelogenous leukemia. In: American Control Conference 2006, JUN 14-16, 2006, Minneapolis, MN, pp. 4818-4823.

[img] PDF
getPDF.pdf2.pdf - Published Version
Restricted to Registered users only

Download (326Kb) | Request a copy
Official URL: http://ieeexplore.ieee.org/search/searchresult.jsp...

Abstract

Combining the advanced techniques of optimal dynamic inversion and model-following neuro-adaptive control design, an efficient technique is presented for effective treatment of chronic myelogenous leukemia (CML). A recently developed nonlinear mathematical model for cell dynamics is used for the control (medication) synthesis. First, taking a set of nominal parameters, a nominal controller is designed based on the principle of optimal dynamic inversion. This controller can treat nominal patients (patients having same nominal parameters as used for the control design) effectively. However, since the parameters of an actual patient can be different from that of the ideal patient, to make the treatment strategy more effective and efficient, a model-following neuro-adaptive controller is augmented to the nominal controller. In this approach, a neural network trained online (based on Lyapunov stability theory) facilitates a new adaptive controller, computed online. From the simulation studies, this adaptive control design approach (treatment strategy) is found to be very effective to treat the CML disease for actual patients. Sufficient generality is retained in the theoretical developments in this paper, so that the techniques presented can be applied to other similar problem as well. Note that the technique presented is computationally non-intensive and all computations can be carried out online.

Item Type: Conference Paper
Additional Information: Copyright of this article belongs to Institute of Electrical and Electronics Engineers.
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering (Formerly, Aeronautical Engineering)
Date Deposited: 10 Aug 2010 04:32
Last Modified: 19 Sep 2010 06:12
URI: http://eprints.iisc.ernet.in/id/eprint/30694

Actions (login required)

View Item View Item