决策树
随机森林
人工神经网络
计算机科学
支持向量机
回归
有限元法
线性回归
回归分析
数据集
集合(抽象数据类型)
采样(信号处理)
机器学习
人工智能
工程类
数学
统计
结构工程
滤波器(信号处理)
计算机视觉
程序设计语言
作者
Ceren Tarar,Erdal Aydın,Ali K. Yetisen,Savaş Tasoğlu
出处
期刊:ACS omega
[American Chemical Society]
日期:2023-05-31
卷期号:8 (23): 20968-20978
被引量:4
标识
DOI:10.1021/acsomega.3c01744
摘要
Microneedles (MNs) allow for biological fluid sampling and drug delivery toward the development of minimally invasive diagnostics and treatment in medicine. MNs have been fabricated based on empirical data such as mechanical testing, and their physical parameters have been optimized through the trial-and-error method. While these methods showed adequate results, the performance of MNs can be enhanced by analyzing a large data set of parameters and their respective performance using artificial intelligence. In this study, finite element methods (FEMs) and machine learning (ML) models were integrated to determine the optimal physical parameters for a MN design in order to maximize the amount of collected fluid. The fluid behavior in a MN patch is simulated with several different physical and geometrical parameters using FEM, and the resulting data set is used as the input for ML algorithms including multiple linear regression, random forest regression, support vector regression, and neural networks. Decision tree regression (DTR) yielded the best prediction of optimal parameters. ML modeling methods can be utilized to optimize the geometrical design parameters of MNs in wearable devices for application in point-of-care diagnostics and targeted drug delivery.
科研通智能强力驱动
Strongly Powered by AbleSci AI