Personalized Closed-Loop Artificial Pancreas: Integrating Real-Time Glucose Sensing, Adaptive Control, and Machine Learning for Dynamic Autonomous Insulin Regulation

This PhD project focuses on the development of a personalized closed-loop Artificial Pancreas System (APS) for autonomous insulin delivery, integrating real-time glucose sensing, adaptive control strategies, and machine learning techniques to improve glycemic regulation in individuals with Type 1 diabetes.

The research aims to address key limitations of current artificial pancreas technologies, including sensor inaccuracies, suboptimal real-time feedback integration, and limited predictive capability of control algorithms. By combining advanced glucose monitoring, embedded control systems, and data-driven modeling, the project seeks to enable continuous, real-time insulin adjustment that responds effectively to dynamic physiological conditions.

A central objective of this work is the personalization of insulin regulation through machine learning approaches that adapt to each patient’s unique metabolic characteristics, daily activities, and lifestyle factors such as exercise, stress, and diet. The project lies at the intersection of biomedical engineering, control theory, embedded systems, and artificial intelligence, contributing to next-generation intelligent medical devices for autonomous and patient-specific diabetes management.

Research Environment

Candidates are expected to carry out their research full-time within the structures of the Euromed University of Fes.

PhD Student’s Responsibilities

The PhD candidate will be expected to:

• Conduct an in-depth state-of-the-art review on artificial pancreas systems, glucose sensing technologies, closed-loop insulin control, and machine learning-based per-sonalization
• Design and implement embedded closed-loop control architectures for autonomous insulin delivery
• Develop and evaluate adaptive and predictive control algorithms for blood glucose regulation
• Integrate real-time glucose sensor data with insulin pump actuation under safety constraints
• Apply machine learning techniques to model patient-specific glucose–insulin dy-namics and personalize control strategies
• Perform simulation-based and experimental validation using virtual patient models and hardware-in-the-loop setups
• Analyze large physiological datasets and assess system robustness under variability in meals, exercise, stress, and daily routines
• Contribute to the development of safety, reliability, and performance evaluation metrics for medical-grade closed-loop systems
• Publish results in peer-reviewed scientific journals and present findings at interna-tional conferences
• Participate actively in research meetings, interdisciplinary collaborations, and dis-semination activities

Candidate Profile

• Master’s/Engineering degree in Embedded Systems engineering, Biomedical engineering, electrical engineering, control systems, computer science or a related field.
• Strong background in control systems, machine learning, and data-driven modelling
• Programming skills in Python, MATLAB, C/C++, or similar languages
• Practical skills in embedded systems, sensors, actuators and electronic hardware
• Motivation for interdisciplinary research, scientific publishing, and development of intelligent medical devices

The application file must include the following documents:

• Curriculum Vitae (CV) with photo
• A cover letter
• A copy of diplomas
• A copy of academic transcripts
• A copy of CIN/Passport

Submission of the Application File

The application file must be sent to the Doctoral Studies Center (CEDoc) of the Euro-Mediterranean University of Fes by email no later than February 14, 2026, to the following email address:

Euromed-CEDoc@ueuromed.org

For More Information

Administrative Affairs Officer of the CEDoc:
Ms. Boutaina Jai Mansouri – b.jai-mansouri@emadu.ueuromed.org

Director of Research and of the CEDoc:
Prof. Abdelghafour Marfak – a.marfak@euromed.org

Thesis Supervision

Thesis Supervisor:
Prof. Moad Essabbar – m.essabbar@insa.ueuromed.org