| Abstract: |
Presented herein are methods, and devices of adaptively tuning a zone based Model Predictive Control (MPC) controller, using at least one processor, which include determining, residuals based on prediction models storing, in a memory, the determined residuals, calculating a trust index by quantifying uncertainty of the prediction models using the stored residuals and tuning the MPC controller, in real time based on the calculated value of the trust index. |
| Inventor: |
LAGUNA, Alejandro SANZ (Cambridge, MA, US); DASSAU, Eyal (Acton, MA, US); DOYLE III, Francis J. (Chestnut Hill, MA, US) |
| Applicant: |
PRESIDENT AND FELLOWS OF HARVARD COLLEGE (Cambridge, MA, US); THE REGENTS OF THE UNIVERSITY OF CALIFORNIA (Oakland, CA, US) |
| Face Assignee: |
PRESIDENT AND FELLOWS OF HARVARD COLLEGE (Cambridge, MA, US); THE REGENTS OF THE UNIVERSITY OF CALIFORNIA (Oakland, CA, US) |
| Filed: |
2017-01-12 |
| Issued: |
2019-01-31 |
| Claims: |
12 |
|
US20190035507
|
1. A method of adaptively tuning a zone based Model Predictive Control (MPC) controller, using at least one processor, the method comprising:
(3)
(4)
|
|
11. A method of insulin delivery using an artificial pancreas, the artificial pancreas including at least one processor, the method comprising:
(0)
(5)
|
|
12. An artificial pancreas apparatus for insulin delivery, the artificial pancreas comprising:
(0)
(7)
|
|
