基于改进支持向量回归算法的甲状腺疾病预测

Thyroid Disease Prediction Based on Improved Support Vector Regression Algorithm

本文构建一种甲状腺疾病机器学习预测诊断算法模型。从UCI(University of California,Irvine)网站获取甲状腺疾病数据集并进行预处理。引入鲸鱼优化算法优化支持向量回归(Support Vector Regression,SVR)模型参数,构建甲状腺疾病预测模型。基于改进支持向量回归算法预测模型能够准确的预测甲状腺功能状况,优化后模型均方误差根为0.2709,R2为0.744,模型预测准确率为0.926,具有较好的预测精度和较快的收敛速度。

To construct a machine learning predictive diagnostic algorithm model for thyroid diseases,this paper obtains a thyroid disease dataset from the UCI(University of California,Irvine)website and preprocesses it.It introduces the whale optimization algorithm to optimize the parameters of the least squares support vector machine model and constructs a thyroid disease prediction model.Based on the improved support vector regression algorithm,the prediction model can accurately predict thyroid function status.After optimization,the root mean square error of the model is 0.2709,R2 is 0.744,and the prediction accuracy of the model is 0.926,indicating good prediction accuracy and fast convergence speed.