基于改进极限学习机的数据智能化分析算法设计

Design of intelligent data analysis algorithm based on improved extreme learning machine

针对医疗财务数据的风险,文中提出了一种基于灰狼优化算法改进极限学习机的数据分析方法,实现了对数据风险的精准预测。该算法基于极限学习对数据进行深度挖掘和分析,并在此基础上进行改进,通过灰狼优化算法对极限学习机的权重参数进行优化。通过在真实数据集上与极限学习机进行实验对比,本算法的决定系数R2为0.96,优于极限学习机的0.81,验证了所提算法的有效性。同时,为了进一步验证该文算法的优越性,在实验仿真过程中还与多种机器学习算法进行对比,结果表明文中算法的预测效果更为优越,相比于其中表现最佳的SVM也有了0.06的提升。

Aiming at the risk of medical financial data,this paper proposes a data analysis method based on gray wolf optimization algorithm to improve the limit learning machine,which realizes accurate prediction of data risk.The algorithm is based on the extreme learning to deeply mine and analyze the data,and on this basis,it is improved.The weight parameters of the extreme learning machine are optimized through the gray wolf optimization algorithm.The experimental results on real data sets show 2 that the decision coefficient R of the algorithm is 0.96,which is better than 0.81 of the limit learning machine.At the same time,in order to further verify the superiority of this algorithm,it is also compared with a variety of machine learning algorithms in the experimental simulation process.The results show that the prediction effect of the algorithm in this paper is more superior,and it also has 0.06 improvement compared with the best performance SVM.