计算机与现代化

• 人工智能 • 上一篇    下一篇

基于K-均值聚类的RBF神经网络血糖浓度预测

  

  1. (广东食品药品职业学院,广东广州510520)
  • 收稿日期:2018-08-07 出版日期:2019-04-08 发布日期:2019-04-10
  • 作者简介:余丽玲(1988-),女,广东韶关人,讲师,硕士,研究方向:信号分析与处理,E-mail: lilingyu124@126.com; 金浩宇(1975-),男,教授,博士,研究方向:医疗器械的研究与开发
  • 基金资助:
    广东省科技计划资助项目(2015A020214016); 广东省医学科学技术研究基金资助项目(B2017093); 广东食品药品职业学院院级课题(2015YZ020,2018ZR032)

Prediction of Blood Glucose Based on K-means Clustering Algorithm with RBF Neural Network

  1. (Guangdong Food and Drug Vocational College, Guangzhou 510520, China)
  • Received:2018-08-07 Online:2019-04-08 Published:2019-04-10

摘要: 针对糖尿病患者血糖数据的复杂性与不稳定性,提出一种基于K-均值聚类算法的径向基函数(Radical Basis Function, RBF)神经网络的短期血糖预测方法。首先将动态血糖监测(Continous Glucose Monitoring System, CGMS)采集的糖尿病患者血糖浓度时间序列进行平滑滤波和归一化处理,提高血糖数据序列的光滑度,弱化原始血糖数据序列的随机性。然后对处理后的血糖浓度时间序列构造RBF网络,采用K-均值聚类进行优化,并用最小二乘法进行RBF网络的权值调整进而获得未来血糖浓度的预测值,从而保证预测的精度。

关键词: 血糖预测, 时间序列, RBF神经网络, K-均值聚类算法

Abstract: In view of the complexity and instability of blood glucose data in diabetic patients, this paper presents a short-term blood glucose prediction method based on K-means clustering algorithm using RBF neural network. Firstly, the blood glucose concentration time series collected by CGMS is filtered and normalized to improve the smoothness of the blood glucose data sequence and weaken the randomness of the original blood glucose data sequence. Then the RBF network is constructed on the processed blood glucose concentration time series. The K-means clustering is used to optimize, and the weights of the RBF network are adjusted by the least square method to obtain the predicted value of the future blood glucose concentration, thereby ensuring the accuracy of the prediction.

Key words:  blood glucose prediction, time series, RBF neural network, K-means clustering algorithm

中图分类号: