English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present the design and \textit{in-silico} evaluation of a closed-loopinsulin delivery algorithm to treat type 1 diabetes (T1D) consisting in adata-driven multi-step-ahead blood glucose (BG) predictor integrated into aLinear Time-Varying (LTV) Model Predictive Control (MPC) framework. Instead ofidentifying an open-loop model of the glucoregulatory system from availabledata, we propose to directly fit the entire BG prediction over a predefinedprediction horizon to be used in the MPC, as a nonlinear function of pastinput-ouput data and an affine function of future insulin control inputs. Forthe nonlinear part, a Long Short-Term Memory (LSTM) network is proposed, whilefor the affine component a linear regression model is chosen. To assessbenefits and drawbacks when compared to a traditional linear MPC based on anauto-regressive with exogenous (ARX) input model identified from data, weevaluated the proposed LSTM-MPC controller in three simulation scenarios: anominal case with 3 meals per day, a random meal disturbances case where mealswere generated with a recently published meal generator, and a case with 25$\%$decrease in the insulin sensitivity. Further, in all the scenarios, nofeedforward meal bolus was administered. For the more challenging random mealgeneration scenario, the mean $\pm$ standard deviation percent time in therange 70-180 [mg/dL] was 74.99 $\pm$ 7.09 vs. 54.15 $\pm$ 14.89, the mean $\pm$standard deviation percent time in the tighter range 70-140 [mg/dL] was47.78$\pm$8.55 vs. 34.62 $\pm$9.04, while the mean $\pm$ standard deviationpercent time in sever hypoglycemia, i.e., $<$ 54 [mg/dl] was 1.00$\pm$3.18 vs.9.45$\pm$11.71, for our proposed LSTM-MPC controller and the traditionalARX-MPC, respectively. Our approach provided accurate predictions of futureglucose concentrations and good closed-loop performances of the overall MPCcontroller.

Model Predictive Control (MPC) of an Artificial Pancreas with Data-Driven Learning of Multi-Step-Ahead Blood Glucose Predictors