摘要
Logistic回归健康评估模型是一种重要的健康状况评估模型,其参数选择对模型的质量有着重大影响。本文提出了一种混沌自适应粒子群算法求解Logistic回归健康评估模型参数。该算法引入惯性权重自适应策略和混沌优化策略加强算法的局部搜索能力、采用适应度方差来解决算法的早熟问题。为了验证所提出算法,本文建立了基于心率、体温、血压等健康评价指标的Logistic回归流行性感冒评估模型。仿真实验表明,本文算法能获得较优的Logistic回归流行性感冒评估模型的参数;采用该参数的Logistic回归流行性感冒评估模型的评估准确率为83.09%,能起到较好的辅助评估作用。
The Logistic regression health assessment model is an important assessment model of health status,and the selection of its parameters has a significant impact on the quality of the model.In this paper,a chaotic adaptive particle swarm optimization(PSO)algorithm is proposed to solve the parameters of the Logistic regression health assessment model.It introduces the inertia weight adaptive strategy and the chaos optimization strategy to strengthen its local search ability and uses the fitness variance to solve its precocious problem.In order to verify the proposed algorithm,the Logistic regression assessment model based on heart rate,body temperature,blood pressure and other health evaluation indexes was established.The simulation experiment shows that the algorithm can obtain the better parameters of the Logistic regression model;and the evaluation accuracy of the Logistic regression assessment model with this parameter is 83.09%,and it can play a better role in auxiliary evaluation.
作者
蔡延光
梁秉毅
蔡颢
戚远航
Ole Hejlesen
CAI Yanguang;LIANG Bingyi;CAI Hao;QI Yuanhang;Ole Hejlesen(School of Automation,Guangdong University of Technology,Guangzhou 510006,China;Department of Health Science&Technology,Aalborg University,Aalborg 9220,Denmark)
出处
《东莞理工学院学报》
2018年第1期1-7,共7页
Journal of Dongguan University of Technology
基金
国家自然科学基金(61074147)
广东省自然科学基金(S2011010005059)
广东省教育部产学研结合项目(2012B091000171
2011B090400460)
广东省科技计划项目(2012B050600028
2014B010118004
2016A050502060)
广州市花都区科技计划项目(HD14ZD001)
广州市科技计划项目(201604016055)
