Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

PD Controller: Design

PD Controller: Design

In automotive engineering, car suspension systems often employ Proportional Derivative (PD) controllers to enhance performance. PD controllers are utilized to adjust the damping force in response to road conditions. A controller, acting as an amplifier with a constant gain, demonstrates proportional control, with output directly mirroring input.
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...

Feedback Loops

Feedback Loops

In most cases, excessive hormone production is prevented by negative feedback—a loop that starts with a stimulus inducing the release of a particular substance, like a hormone, to maintain a certain level before triggering a signal that results in a decrease in further release of the hormone.

PI Controller: Design

PI Controller: Design

Proportional Integral (PI) controllers are a fundamental component in modern control systems, widely used to enhance performance and mitigate steady-state errors. They are particularly effective in applications such as automatic brightness adjustment on smartphones, where they excel at mitigating steady-state errors for step-function inputs. Unlike PD controllers, which require time-varying errors to function optimally, PI controllers leverage their integral component to address residual...

PID Controller

PID Controller

Proportional-Integral-Derivative (PID) controllers are widely used in various control systems to enhance stability and performance. In a thermostat, it adjusts heating or cooling based on the temperature difference between the actual and desired levels. They are often used in automotive speed systems, effectively managing sudden speed changes while maintaining a constant speed under varying conditions. On the other hand, PI controllers, commonly employed in voltage regulation, enhance stability...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multimodal Sentiment and Emotion Analysis Framework for Personalized Health Coaching Messages: Proof-of-Concept Study.

JMIR formative research·2026

Same author

Edge-Aware Dual-Branch CNN Architecture for Alzheimer's Disease Diagnosis.

Journal of imaging informatics in medicine·2026

Same author

Generalized Gaussian Distribution Improved Permutation Entropy: A New Measure for Complex Time Series Analysis.

Entropy (Basel, Switzerland)·2024

Same author

Systematic Literature Review on Visual Analytics of Predictive Maintenance in the Manufacturing Industry.

Sensors (Basel, Switzerland)·2022

Same author

Sandwich-type electrochemical biosensor for glycoproteins detection based on dual-amplification of boronic acid-gold nanoparticles and dopamine-gold nanoparticles.

Biosensors & bioelectronics·2013

Same author

Ultrastructural study on dynamics of lipid bodies and plastids during ripening of chili pepper fruits.

Micron (Oxford, England : 1993)·2013

Search research articles

Related Experiment Video

Updated: May 30, 2025

Controlling Parkinson's Disease With Adaptive Deep Brain Stimulation

Controlling Parkinson's Disease With Adaptive Deep Brain Stimulation

Published on: July 16, 2014

A safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning.

Yan Feng Zhao¹, Jun Kit Chaw¹, Mei Choo Ang¹

¹Institute of Visual Informatics, The National University of Malaysia (UKM), Bangi, Malaysia.

|January 27, 2025

Summary

This summary is machine-generated.

A new deep reinforcement learning controller for artificial pancreas systems improves blood glucose control in type 1 diabetes. This safe and efficient system significantly reduces hypoglycemia, bringing closed-loop insulin delivery closer to clinical use.

More Related Videos

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

Related Experiment Videos

Last Updated: May 30, 2025

Controlling Parkinson's Disease With Adaptive Deep Brain Stimulation

Controlling Parkinson's Disease With Adaptive Deep Brain Stimulation

Published on: July 16, 2014

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

Area of Science:

Biomedical Engineering
Artificial Intelligence in Medicine
Endocrinology

Background:

Type 1 diabetes management requires continuous blood glucose monitoring and insulin adjustment.
Fully closed-loop artificial pancreas (AP) systems aim to automate glucose regulation, reducing patient burden.
Deep reinforcement learning (DRL) offers potential for adaptive insulin dosing but faces safety and efficiency challenges.

Purpose of the Study:

To develop a safe and efficient DRL-based controller for a fully closed-loop artificial pancreas.
To enhance the training efficiency and safety of DRL algorithms for insulin delivery.
To evaluate the controller's performance in simulated type 1 diabetes scenarios.

Main Methods:

Utilized a proximal policy optimization (PPO) algorithm enhanced with ten specific techniques for improved training efficiency.
Implemented a dual safety mechanism combining 'proactive guidance' and 'reactive correction' to mitigate glucose level risks.
Evaluated the controller's efficacy using the Simglucose simulator for type 1 diabetes management.

Main Results:

The DRL controller achieved a median Time in Range (TIR) of 87.45%, outperforming baseline methods.
Demonstrated a significantly lower incidence of hypoglycemia compared to existing approaches.
Effectively eliminated severe hypoglycemia and treatment failures in simulation.

Conclusions:

The proposed DRL-based artificial pancreas controller represents a significant advancement in automated glucose regulation for type 1 diabetes.
The enhanced PPO algorithm and dual safety mechanism contribute to a safer and more efficient closed-loop system.
This research marks a crucial step towards the clinical viability of fully closed-loop artificial pancreas technology.