Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.


A novel Adaptive Artificial Pancreas for effective blood glucose control of Diabetic Patients

An Artificial Pancreas (AP) is a wearable, automated insulin infusion system, capable of providing blood glucose regulation for Diabetic Patients. Complex environmental and individualized factors, such as variability on meal times, meal portion sizes, physical exercise, severe stress and hormonal changes make the goal of current APs much more challenging and difficult. This work proposes, for the first time in the related literature, a novel unified approach of adaptive glucose control for all main types of Diabetes Mellitus (Type 1, Type 2, Prediabetes), under large inter and intra-day and subject variability. The proposed adaptive controller is designed as an Indirect Learning Type Controller and is developed for Imperial College’s Bio-Inspired Artificial Pancreas. Extensive in silico simulations are carried on a brand new, FDA-accepted simulator. We compare the performance and robustness of our proposed controller with the initially developed, non-adaptive controller, as well as with the most competitive approach of the current literature, under various scenarios. The results of our method are very successful. The proposed adaptive controller outperforms the compared methods at all levels. The high performance and reliability of our method lead us to proceed with clinical trials on real Patients in the next months.

Type of Seminar:
IfA Seminar
Alexandros Tanzanakis
Sep 25, 2017   14:00

ETL K 25
Contact Person:

No downloadable files available.
Biographical Sketch:
Alexandros Tanzanakis grew up in Athens, Greece. He completed a Diploma in Electrical & Computer Engineering with the highest honors in September 2016 at Technical University of Crete, Greece. His Diploma Thesis dealt with the development of a novel, energy efficient control method achieving human-like bipedal robot locomotion with the minimum energy cost of transport (COT) possible. In November 2016, he joined the Institute of Biomedical Engineering at Imperial College London, UK, where he currently works as a Biomedical Control Researcher. His latest research involves the development of the world’s first adaptive artificial pancreas capable of proving effective blood glucose control for all main Types of Diabetes Mellitus. His research interests include modeling, analysis and control of hybrid systems, systems biology and biological control, game theory and multiagent control systems, stochastic optimization and control, as well as control applications in various domains, e.g. biomedicine and robotics. He is a member of IEEE.