您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Effect of Hyperparameters of Reinforcement Learning in Blood Glucose Control

文献类型： 会议论文

第一作者： Máté Siket

作者： Máté Siket 1 ; László Szilágyi 2 ; Gy?rgy Eigner 3 ; Levente Kovács 3 ; Dénes-Fazakas Lehel 1 ;

作者机构： 1.Physiological Controls Research Center, óbuda University|Applied Informatics and Applied Mathematics Doctoral School, óbuda University, Budapest

2.Physiological Controls Research Center, óbuda University|Computational Intelligence Research Group, Sapientia University, Tg. Mute?, Romania

3.Physiological Controls Research Center, óbuda University|John von Neumann Faculty of Informatics, Biomatics and Applied Artificial Intelligence Institute, óbuda University

关键词： Measurement;Neural networks;Reinforcement learning;Control systems;Glucose;Diabetes;Blood

会议名称： IEEE International Conference on Systems, Man, and Cybernetics

主办单位：

页码： 1333-1340

摘要： Reinforcement learning (RL) has shown promise in controlling blood glucose levels in a personalized way in type 1 diabetic patients. In this study, we investigate the impact of different activation functions and layer numbers on RL performance in blood glucose control. We train RL agents with various combinations of activation functions and layer numbers on a virtual patient model. The RL agents are evaluated based on their ability to maintain blood glucose levels within a target range while minimizing the frequency and magnitude of hypoglycemia and hyperglycemia events. Our results show that the choice of activation function and layer number significantly affects the RL performance. Specifically, the agents with ReLU activation functions and two or three hidden layers outperform the other agents, achieving a higher percentage of time in the target range and fewer hypoglycemia and hyperglycemia events. These findings provide valuable insights for the development of RL-based blood glucose control systems in type 1 diabetic patients.

分类号： tp13-53

  • 相关文献

[1]Review of Reinforcement Learning-Based Control Algorithms in Artificial Pancreas Systems for Diabetes Mellitus Management. Lehel Dénes-Fazakas,Gy?z? Dénes Fazakas,Gy?rgy Eigner,Levente Kovács,László Szilágyi. 2024

[2]Control of Type 1 Diabetes Mellitus using direct reinforcement learning based controller. Lehel Dénes-Fazakas,Máté Siket,Gábor Kertész,László Szilágyi,Levente Kovács,Gyórgy Eigner. 2022

[3]Investigation of reward functions for controlling blood glucose level using reinforcement learning. Dénes-Fazakas Lehel,Máté Siket,László Szilágyi,Gyorgy Eigner,Levente Kovács. 2023

[4]Automatically estimated meals in Model Predictive Control-Moving Horizon Estimation control strategy. Máté Siket,Kamilla Novák,Levente Kovács,Gy?rgy Eigner. 2022

[5]Data Collection Studies for the Better Understanding of Factors in Type 1 Diabetes Management. Barbara Simon,Ádám Hartveg,Máté Siket,Lehel Dénes-Fazakas,Gyórgy Eigner,Levente Kovács,László Szilágyi. 2024

[6]Mobile Application Development for Diabetes Patient. Lehel Dénes-Fazakas,Gy?rgy Eigner,Milán Balázs,Levente Kovács,László Szilágyi,Csaba Potyok,Barbara Simon,ádám Hartveg,Máté Siket. 2024

[7]Web Application Development for Diabetes Patients. Miklos Nagy,Barbara Simon,László Szász,Máté Siket,Lehel Dénes-Fazakas,Gy?rgy Eigner,Patrik Péter Süli,Levente Kovács,László Szilágyi. 2024

[8]Babesia sp. BQ1 (Lintan): Molecular evidence of experimental transmission to sheep by Haemaphysalis qinghaiensis and Haemaphysalis longicornis. Guan, Guiquan,Moreau, Emmanuelle,Chauvin, Alain,Guan, Guiquan,Liu, Junlong,Hao, Xuefen,Ma, Miling,Luo, Jianxun,Yin, Hong.

[9]The New Method of Fruit Tree Characteristics Acquisition Using Electromagnetic Tracking Instrument. Wang, Jian,Wu, Ding-feng,Zhou, Guo-min,Qiu, Yun. 2011

[10]Short-Term Price Forecasting For Agro-products Using Artificial Neural Networks. Li, Gan-qiong,Xu, Shi-wei,Li, Zhe-min. 2010

[11]Modeling greenhouse air humidity by means of artificial neural network and principal component analysis. He, Fen,Ma, Chengwei,He, Fen.

[12]GROWTH PERFORMANCE AND ANTIOXIDANT CAPACITIES IN PIGLETS WITH DIFFERENT WEANING AGE. Li, L. A.,Yang, J. J.,Li, Y.,Jin, T. M.,Li, R. N.,Qin, S. Y.,Xie, J. J.,Du, G. M.. 2016

[13]Experimental infection with bovine ephemeral fever virus and analysis of its antibody response cattle. Zheng, F. Y.,Chen, Q. W.,Li, Z.,Gong, X. W.,Wang, J. D.,Yin, H..

[14]Accumulation and Depletion of Cadmium in the Blood, Milk, Hair, Feces, and Urine of Cows During and After Treatment. Su, Chuanyou,Zhang, Junmin,Zhao, Qingyu,Su, Chuanyou,Li, Zhentian,Liu, Kaidong,Sun, Youde,Wang, Jianhua.

[15]Rapid detection of Pseudomonas aeruginosa septicemia by real-time fluorescence loop-mediated isothermal amplification of free DNA in blood samples. Yang, Rungong,Fu, Shuhong,Gong, Meiliang,Li, Xiaoxia,Yu, Jihong,Bai, Jie,Ye, Ling,Yang, Jinghui,Chen, Hongyan,Fan, Yanfeng. 2016

[16]Influence of different dietary levels of zinc on performance, vitamin B-12, and blood parameters in lambs. Wang, Runlian,Zhu, Xiaoping,Guo, Fucun,Zhang, Wei,Jia, Zhihai. 2006

[17]Effects of flaxseed oil on anti-oxidative system and membrane deformation of human peripheral blood erythrocytes in high glucose level. Huang, Qingde,Xu, Jiqu,Deng, Qianchun,Huang, Fenghong,Yang, Wei,Fu, Juan,Yu, Miao,Wang, Di,Yao, Ping,Liu, Liegang,Yang, Wei,Fu, Juan,Yu, Miao,Wang, Di,Yao, Ping,Liu, Liegang. 2012

[18]Protective effect of Schisandrae chinensis oil on pancreatic beta-cells in diabetic rats. An, Liping,Wang, Chunmei,Han, Xiao,Xu, Guangyu,Yuan, Guangxin,Li, Hongyu,Sheng, Yu,Wang, Manli,Sun, Jingbo,Zhan, Jinzhuo,Sun, Hui,Li, Na,Du, Peige,Wang, Yingping,Fan, Meizhen,Ding, Fuxiang. 2015

[19]Antibacterial Activity of Polyphenols: Structure-Activity Relationship and Influence of Hyperglycemic Condition. Xie, Yixi,Chen, Jing,Xiao, Aiping,Liu, Liangliang,Xie, Yixi. 2017

[20]Therapeutic Strategies of Plant-derived Compounds for Diabetes Via Regulation of Monocyte Chemoattractant Protein-1. Czemplik, Magdalena,Kulma, Anna,Szopa, Jan,Wang, Yu Fu,Szopa, Jan,Szopa, Jan.

作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台