相关实验视频
Updated: Jul 20, 2025

Improving IV Insulin Administration in a Community Hospital
Published on: June 11, 2012
闭环胰岛素输送系统的自动适应,使用连续奖励函数和渐进式分密化
Maria Cecilia Serafini1, Nicolas Rosales1, Fabricio Garelli1
1Grupo de Control Aplicado, Instituto LEICI (UNLP-CONICET), Facultad de Ingeniería, Universidad Nacional de La Plata, Argentina.
这项研究表明,强化学习 (RL) 药物通过适应胰岛素敏感性变化来改善长期人工胰腺 (AP) 系统的性能. 持续的奖励功能进一步增强了这些自动胰岛素输送 (AID) 系统,以更好地调节血糖.
科学领域:
- 生物医学工程 生物医学工程
- 控制系统 控制系统
- 人工智能的人工智能
背景情况:
- 人工胰腺 (AP) 系统,也称为自动胰岛素输送 (AID) 系统,对于血糖 (BG) 调节至关重要.
- 当前的AID系统往往专注于短期的表现,忽视了长期适应胰岛素敏感性 (IS) 等生理变异的情况.
- 对IS变化的不充分适应可能导致AID系统的性能不足.
研究的目的:
- 评估两种强化学习 (RL) 剂的长期适应能力,用于完全自动化胰岛素输送系统 (fAID).
- 为了比较训练有素的RL特工的性能,用零碎和连续的奖励函数进行训练.
- 在基于RL的AID系统中评估适应性离散方案,用于管理状态空间探索.
主要方法:
- 用于自动调节葡萄糖 (ARG) 算法的两个RL剂的in-silico评估.
- 实施一个适应性离散方案,以动态扩大状态空间.
- 训练RL代理人使用分片和连续奖励函数来处理胰岛素敏感性 (IS) 的变化.
主要成果:
- 在大多数成年人群中,这两种RL药物都在基于规则和基线的控制器上表现得更好.
- RL药物有效地适应了胰岛素敏感性 (IS) 的长期变化.
- 一个连续形状的奖励函数导致了优越的表现,而不是一个零碎的奖励函数.
结论:
- 在自动化胰岛素输送系统中,RL剂为长期适应提供了有希望的方法.
- 持续的奖励功能提高了RL代理在AID系统中的有效性.
- 拟议的自适应性分密化方案有助于高效的状态空间管理,以改善控制.
更多相关视频
09:08Three-dimensional Printing of Thermoplastic Materials to Create Automated Syringe Pumps with Feedback Control for Microfluidic Applications
Published on: August 30, 2018
08:32Studying the Hypothalamic Insulin Signal to Peripheral Glucose Intolerance with a Continuous Drug Infusion System into the Mouse Brain
Published on: January 4, 2018
相关概念视频
Open and closed-loop control systems
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal...
Insulin: Dosing Regimen and Adverse Effects
The basal dose constitutes about 40%-50% of the total daily dose, with the rest as premeal insulin. The mealtime insulin dose should mirror...
Insulin Formulations: Types and Delivery
Short-acting insulins are divided into...
PD Controller: Design
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
Feedback control systems
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...
PI Controller: Design