Journal of Applied Research in Electrical Engineering

Journal of Applied Research in Electrical Engineering

Investigating Robust Tracking of Type 1 Diabetes Control Using Model-Free Controllers

Document Type : Research article

Authors
Peyman Vafadoost Sabzevar 1
Ahmad Hajipour 1
Hamidreza Tavakoli 2
1 Biomedical Engineering Department, Electrical and Computer Faculty, Hakim Sabzevari University, Sabzevar, Iran
2 Electronic Engineering Department, Electrical and Computer Faculty, Hakim Sabzevari University Sabzevar, Iran
10.22055/jaree.2024.47542.1126
Abstract
One of the main challenges in the field of control is the use of a stable controller and its lack of dependence on the system model and dynamics, so that the input signal is applied to the system based on the existing needs. One of the areas that needs controlling and applying the input signal is type 1 diabetes, where people with this disease need constant and regular insulin injections based on blood glucose concentration. Based on this, in this article, two free model methods called the Q-learning algorithm and PID have been used to determine insulin dose, and the results of insulin dose injection show the results and high performance of the Q-learning algorithm in determining insulin dose. This algorithm is one of the methods based on artificial intelligence that discovers the optimal policy based on trial and error. Finally, the Q-learning algorithm has been investigated in the presence of noise, and its stability has been proven to ensure the performance of the controller.

Highlights

  • Q-learning algorithm has been used to determine insulin dose
  • PID controller has been used to determine insulin dose
  • Q-learning algorithm has been investigated in the presence of noise and its stability has been proven

Keywords
Q-Learning
PID controller
Model-Free
Injection insulin
Tracking blood glucose
Subjects
[1]     American Diabetes Association, “Diagnosis and classication of diabetes mellitus,” Diabetes Care, 2014, vol. 37, pp. S81-90.
[2]     American Diabetes Association, “Introduction: Standards of medical care in diabete,” Diabetes Care, 2018, vol. 41, pp. S1-2.
[3]     M. Z. Banday, S. S. Aga, and N. Saniya, "Pathophysiology of diabetes: An overview," Avicenna Journal of Medicine, vo. 10, no. 4,  pp. 174-188, 2020.
[4]     C. C. Patterson et al., "Worldwide estimates of incidence, prevalence and mortality of type 1 diabetes in children and adolescents: Results from the international diabetes federation diabetes atlas." Diabetes Research and Clinical Practice, vol. 157, p. 107842, 2019.
[5]     T. Quattrin, L. D. Mastrandrea, and L. S. K. Walker, "Type 1 diabetes." The Lancet, vol. 401, no. 10394, pp. 2149-2162, 2023.
[6]     A/ H. A. Abu-Rmileh, "Control and modeling techniques in biomedical engineering: the artificial pancreas for patients with type 1 diabetes," PhD Thesis, Universitat de Girona, 2013.
[7]     M. Bryer-Ash, 100 Questions & answers about diabetes. Jones & Bartlett Publishers, 2009.
[8]     C. S. Marathe et al., Gastrointestinal disorders in diabetes. [Online]. (2003), Available: https://www.ncbi.nlm.nih.gov/books/NBK553219/
[9]     S. A. Babar, A. Iftikhar, and I. S. Mughal, "Sliding -mode-based controllers for automation of blood glucose concentration for type 1 diabetes." IET Systems Biology, vol. 15, no. 2 pp. 72-82, 2021.
[10]  E. Matamoros-Alcivar, T. Ascencio-Lino, R. Fonseca, G. Villalba-Meneses, A. Tirado-Espín, L. Barona, and D. Almeida-Galárraga, "Implementation of MPC and PID control algorithms to the artificial pancreas for diabetes mellitus type 1," in 2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT), IEEE, 2021.
[11]  S. F. Ali, and R. Padhi. "Optimal blood glucose regulation of diabetic patients using single network adaptive critics," Optimal Control Applications and Methods, vol. 32, no. 2, pp. 196-214, 2011.
[12]  G. Tornese, V. Ceconi, L. Monasta, C. Carletti, E. Faleschini, and E. Barbi. "Glycemic control in type 1 diabetes mellitus during COVID-19 quarantine and the role of in-home physical activity." Diabetes Technology & Therapeutics, vol. 22, no. 6, pp. 462-467, 2020.
[13]  A. H. Mosavi et al.,,"Deep learning fuzzy immersion and invariance control for type-I diabetes," Computers in Biology and Medicine, vol. 149, p. 105975, 2022.
[14]  R. Nimri et al., "Insulin dose optimization using an automated artificial intelligence-based decision support system in youths with type 1 diabetes," Nature Medicine, vol. 26, no. 9, pp. 1380-1384, 2020.
[15]  A. K. Patra, and P. K. Rout. "Adaptive continuous-time model predictive controller for implantable insulin delivery system in Type I diabetic patient," Optimal Control Applications and Methods, vol. 38, no. 2, pp. 184-204, 2017.
[16]  B. Selma, H. Abouaïssa, S. Chouraqui, H. Kadem, D. Mehdeb, and M. Elaffifi, “Toward a model-free feedback control of blood glucose induced by meals for type-1 diabetics: in silico studies,” Iran Journal of Computer Science, pp.1-11, 2024..
[17]  M. Jaloli, and M. Cescon, “Basal-bolus advisor for type 1 diabetes (T1D) patients using multi-agent reinforcement learning (RL) methodology,” Control Engineering Practice, vol. 142, p.105762, 2024.
[18]  J. C. H. Christopher, "Watkins and peter dayan. Q-Learning." Machine Learning, vol. 8, no. 3, pp. 279-292, 1992.
[19]  K. H. Ang, G. Chong, and Y. Li. "PID control system analysis, design, and technology." IEEE Transactions on Control Systems Technology, vol. 13, no. 4, pp. 559-576, 2005.
[20]  M. A. Johnson, and M. H. Moradi, PID control. London, UK: Springer-Verlag London Limited, 2005.
[21]  C. Li, and R. Hu. "Simulation study on blood glucose control in diabetics," in 2007 1st International Conference on Bioinformatics and Biomedical Engineering, pp. 1103-1106. IEEE, 2007.
[22]  K. E. Andersen, and M. Højbjerre, "A bayesian approach to bergman’s minimal model," in International Workshop on Artificial Intelligence and Statistics, pp. 1-8, 2003.
[23]  P. S. Vafadoost, H. Sadrian, and A. Hajipour, "Tracking blood glucose concentration of type 1 diabetic patients using reinforcement learning," in 2023 9th International Conference on Control, Instrumentation and Automation (ICCIA), IEEE, 2023, pp. 1-6..
 
Journal of Applied Research in Electrical Engineering
Volume 3, Issue 2
Summer and Autumn 2024
July 2024
Pages 232-239

  • Receive Date 26 July 2024
  • Revise Date 15 October 2024
  • Accept Date 17 October 2024