基于深度学习的健康云数据监控分析算法设计

Design of health cloud data monitoring and analysis algorithm based on deep learning

针对远程在线智能化健康监控的数据处理需求,基于数据挖掘和深度学习技术原理,文中提出了一种健康云数据监控分析算法。在数据挖掘的框架下,对健康云数据进行预处理,从而完成数据准备。在此基础上,建立了基于多隐藏层级联的深度学习网络的数据挖掘模型。为了更精确地对健康数据展开监控,通过反向传播算法进行网络训练,并使用梯度下降法进行迭代优化,实现网络代价函数的最小化。实验结果表明,文中所提算法相比于现有算法,在不提高训练复杂度的情况下具有更高的数据分析正确率,且对于不同类型的健康问题均具有良好的适用性。

Aiming at the data processing requirements of remote online intelligent health monitoring,based on the principles of data mining and deep learning technology,a health cloud data monitoring and analysis algorithm is proposed in this paper. In the framework of data mining,the health cloud data is preprocessed to complete the data preparation. On this basis,a data mining model based on multi hidden layer cascaded deep learning network is established. In order to monitor the health data more accurately,this paper uses the back-propagation algorithm for network training,and uses the gradient descent method for iterative optimization to minimize the network cost function. The experimental results show that compared with the existing algorithms,the proposed algorithm has higher data analysis accuracy without improving the training complexity,and has good applicability to different types of health problems.