Prior-knowledge-embedded model predictive control for blood glucose regulation: Towards efficient and safe artificial pancreas

Sun, Xiaoyu; Çınar, Ali; Liu, Jianchang; Rashid, Mudassir; Xia, Yu

doi:10.1016/j.bspc.2022.104551

Cited by 4 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive efforts, including diverse mathematical models and controller design techniques, have been employed to overcome these challenges, as detailed in comprehensive reviews such as [33,34] on existing models and the utilized controllers. MPC and PID are widely applied in APS [35,36]. Additionally, various advanced control design methods are systematically employed for improved automatic regulation system performance.…”

Section: Introductionmentioning

confidence: 99%

Optimizing Blood Glucose Regulation in Type 1 Diabetes Patients via Genetic Algorithm-Based Fuzzy Logic Controller Considering Substantial Meal Protocol

Ndakara Abubakar,

Essabbar,

Saikouk

2024

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Effective management of blood glucose levels in individuals with type 1 diabetes, especially after meals, is crucial for diabetes care. Artificial pancreas systems (APS) perform automated insulin delivery in subjects with type 1 diabetes mellitus (T1DM). In this study, an optimized fuzzy logic controller was designed to achieve a euglycemic range after a substantial meal intake. All in silico simulations were performed using the MATLAB/Simulink environment, leveraging control variability grid analysis (CVGA), and the performance of the controller was evaluated. The proposed controller is based on a fuzzy-logic control law designed in three stages. First, a nonlinear framework of the glucose-insulin regulatory system was identified based on the heavy meal protocol of three patients given as follows: for subject ID 117-1, a total of 295 gCHO; for subject ID 126-1, 236 gCHO; and subject ID 128-1, 394 gCHO over a day. Then, an iterative tree structure was employed to establish a stabilizing control rule for insulin delivery, integrating inputs from two Mamdani Fuzzy Inference System (FIS) objects. Finally, a genetic algorithm refines the control system by fine-tuning the uncertainty of the fuzzy membership functions. Two scenarios were considered for three patients to assess the performance of the proposed controller. The results indicated its effectiveness under various conditions, achieving a time in the range of 61.25%, 71% and 61.10% respectively for the three subjects. The obtained results are analyzed and compared with IMC and multi-objective output feedback controllers. The findings of the study reveal that the proposed controller shows promising advancements in tailored strategies for type 1 diabetes patients, outperforming the other controllers in terms of blood glucose regulation.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimizing Blood Glucose Regulation in Type 1 Diabetes Patients via Genetic Algorithm-Based Fuzzy Logic Controller Considering Substantial Meal Protocol

Ndakara Abubakar,

Essabbar,

Saikouk

2024

Int. J. Onl. Eng.

View full text Add to dashboard Cite

show abstract

Recent advances in the precision control strategy of artificial pancreas

Ming,

Guo,

Zhang

et al. 2024

Med Biol Eng Comput

View full text Add to dashboard Cite

Predicting the output error of the suboptimal state estimator to improve the performance of the MPC-based artificial pancreas

Dodek

Miklovičová

2023

Control Theory Technol.

View full text Add to dashboard Cite

The error of single step-ahead output prediction is the information traditionally used to correct the state estimate while exploiting the new measurement of the system output. However, its dynamics and statistical properties can be further studied and exploited in other ways. It is known that in the case of suboptimal state estimation, this output prediction error forms a correlated sequence, hence it can be effectively predicted in real time. Such a suboptimal scenario is typical in applications where the process noise model is not known or it is uncertain. Therefore, the paper deals with the problems of analytical and empirical modeling, identification, and prediction of the output error of the suboptimal state estimator for the sake of improving the output prediction accuracy and ultimately the performance of the model predictive control. The improvements are validated on an empirical model of type 1 diabetes within an in-silico experiment focused on glycemia prediction and implementation of the MPC-based artificial pancreas.

show abstract

Prior-knowledge-embedded model predictive control for blood glucose regulation: Towards efficient and safe artificial pancreas

Cited by 4 publications

References 37 publications

Optimizing Blood Glucose Regulation in Type 1 Diabetes Patients via Genetic Algorithm-Based Fuzzy Logic Controller Considering Substantial Meal Protocol

Optimizing Blood Glucose Regulation in Type 1 Diabetes Patients via Genetic Algorithm-Based Fuzzy Logic Controller Considering Substantial Meal Protocol

Recent advances in the precision control strategy of artificial pancreas

Predicting the output error of the suboptimal state estimator to improve the performance of the MPC-based artificial pancreas

Contact Info

Product

Resources

About