Home Patent Forecast® Sectors Log In   Contact  
How it works Patent Forecast® Sectors Insights
Menu
Enjoy your FREE PREVIEW which shows only 2022 data and 25 documents. Contact Patent Forecast for full access.        

AI Biotech/Diagnostics: Other Innovation

Search All Applications in AI Biotech/Diagnostics: Other Innovation


Application US20190035507


Published 2019-01-31

Predictive Control Model For The Artificial Pancreas Using Past Predictions

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.



Much More than Average Length Specification


View the Patent Matrix® Diagram to Explore the Claim Relationships

USPTO Full Text Publication >

3 Independent Claims

  • 1. A method of adaptively tuning a zone based Model Predictive Control (MPC) controller, using at least one processor, the method comprising: determining, using at least one of said at least one processor, residuals based on prediction models; storing, in a memory, the determined residuals; calculating a trust index, using at least one of said at least one processor, by quantifying uncertainty of the prediction models using the stored residuals; and tuning the MPC controller, in real time, using at least one of said at least one processor, based on the calculated value of the trust index.

  • 11. A method of insulin delivery using an artificial pancreas, the artificial pancreas including at least one processor, the method comprising: determining, using at least one of said at least one processor, residuals based on prediction models; storing, in a memory, the determined residuals; calculating a trust index, using at least one of said at least one processor, by quantifying uncertainty of the prediction models using the stored residuals; tuning a model prediction control (MPC) controller, in real time, using at least one of said at least one processor, based on the calculated value of the trust index; and controlling, using at least one of said at least one processor, the delivery of insulin based on the tuned MPC controller.

  • 12. An artificial pancreas apparatus for insulin delivery, the artificial pancreas comprising: at least one non-transitory memory operable to store program code; a model prediction control (MPC) controller including at least one processor operable to read said program code and operate as instructed by said program code, said program code causing the at least one processor to: determine residuals based on prediction models; store, in the at least one non-transitory memory, the determined residuals; calculate a trust index by quantifying uncertainty of the prediction models using the stored residuals; and tune the MPC controller in real time based on the calculated value of the trust index; and deliver the insulin based on the tuned MPC controller.