Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Online Feedback Optimization for Medical Applications
We want to use the novel class of Online Feedback Optimization Controllers in medical applications like anaesthesia control. The advantage of these controllers is that they do not track a reference point, but rather drive the system to an optimal point defined by an optimization problem.
Keywords: Online Feedback Optimization,
Control Systems,
Medicine
Physiologic Control
Online Feedback Optimization is a novel way of controlling a system. The goal of such a controller is not to track a reference point, but to drive the system to an optimal point defined by an optimization problem (e.g. max depth of anaesthesia, or max oxygen saturation). These controllers use optimisation algorithms and put them to use in a closed-loop control system. This enables us to steer the system to an optimal point while taking constraints of the system into account (maximum drug usage, max pressure of a ventilator etc)
Online Feedback Optimization is a novel way of controlling a system. The goal of such a controller is not to track a reference point, but to drive the system to an optimal point defined by an optimization problem (e.g. max depth of anaesthesia, or max oxygen saturation). These controllers use optimisation algorithms and put them to use in a closed-loop control system. This enables us to steer the system to an optimal point while taking constraints of the system into account (maximum drug usage, max pressure of a ventilator etc)
The student will be introduced and taught in the concept of Online Feedback Optimization. Furthermore, the student will be given physiological system models and control problems in the field of medical applications that can be solved with Online Feedback Optimization Controllers. After this initial phase, the student will exploit the literature for further models and control problems.
Once the most suitable model(s) and control problem(s) is(are) identified, the student will implement the models and controller and analyse the performance.
The project can be adapted on the run if new interesting research directions arise.
Finally, if the results are promising they can be turned into a publication.
The student will be introduced and taught in the concept of Online Feedback Optimization. Furthermore, the student will be given physiological system models and control problems in the field of medical applications that can be solved with Online Feedback Optimization Controllers. After this initial phase, the student will exploit the literature for further models and control problems.
Once the most suitable model(s) and control problem(s) is(are) identified, the student will implement the models and controller and analyse the performance.
The project can be adapted on the run if new interesting research directions arise.
Finally, if the results are promising they can be turned into a publication.
Lukas Ortmann: ortmannl@control.ee.ethz.ch
Miguel Picallo Cruz: miguelp@control.ee.ethz.ch
Lukas Ortmann: ortmannl@control.ee.ethz.ch Miguel Picallo Cruz: miguelp@control.ee.ethz.ch