摘要
针对传统NR法在各类医疗设备数据融合和分析中存在的准确度低、收敛速度慢等问题,设计了一种改进的数据感知与分析处理方法。该方法利用深度学习算法代替传统的NR法,提高了数据处理的准确度,通过引入非线性调节因子形成了改进神经网络算法,加快了深度学习算法的局部收敛速度。为实现对设备状态、性能的准确监测和预测,精准挖掘数据之间的关联信息,在多源信息数据采集的基础上,提出了多源改进深度学习算法。数值对比实验结果表明,所提算法的数据处理准确度可在98%以上,提高了对医疗设备异常数据识别的准确性。
An improved data perception and analysis processing method is designed to address the issues of low accuracy and slow convergence speed in the traditional NR method for data fusion and analysis of various medical devices.This method uses deep learning algorithms to replace the traditional NR method,improving the accuracy of data processing.By introducing nonlinear adjustment factors,an improved neural network algorithm is formed,which accelerates the local convergence speed of deep learning algorithms.To achieve accurate monitoring and prediction of device status and performance,and to accurately mine the correlation information between data,a multi-source improved deep learning algorithm is proposed based on multi-source information data collection.The numerical comparison experiment results show that the data processing accuracy of the proposed algorithm can reach over 98%,improving the accuracy of identifying abnormal data in medical equipment.
作者
任亦之
岳晓磊
REN Yi-zhi;YUE Xiao-lei(The First Affiliated Hospital of Hebei North University,Zhangjiakou 075000,Hebei Province,China)
出处
《信息技术》
2025年第7期29-33,39,共6页
Information Technology
基金
张家口市重点研发计划项目(2322015B)。
关键词
多源信息
深度学习
非线性调节因子
医疗设备
数据处理准确度
multi-source information
deep learning
nonlinear regulatory factor
medical equipment
data processing accuracy
作者简介
任亦之(1994-),男,本科,助理工程师,研究方向为医学信息。
