基于SOINN结合ADNDD的网络安全动态控制技术研究

医院网络安全动态控制技术对于保障医院网络的安全性和稳定性具有重要意义。传统的网络异常监测和网络安全动态控制无法解决大面积网络入侵的问题。因此,为了解决这些问题,研究构建了基于自组织增量式神经网络算法(Self-Organizing Incremental Neural Network, SOINN)结合数字信息处理的网络技术(Advanced Digital Network Data Design, ADNDD)的医院安全动态控制模型。首先对算法进行优化,其次将SOINN与ADNDD进行融合构建网络安全动态控制模型,最后利用数据集去验证模型的性能。结果表明,在数据集中训练后,模型在对浪涌攻击、偏差攻击和几何攻击数据集中的离群点识别率分别为92.13%、90.04%和89.07%。这说明模式算法经过数据集的应用能够在医院网络异常检测和动态防御控制中满足网络安全的要求。旨为提高医院网络的安全性和稳定性。

Research on hospital network security dynamic control technology based on network anomaly monitoring

Hospital network security dynamic control technology is of great significance to ensure the security and stability of hospital networks. The traditional network anomaly monitoring and network security dynamic control cannot solve the problem of large area network intrusion. Therefore, in order to solve these problems, the study constructs a hospital security dynamic control model based on Self-Organizing Incremental Neural Network (SOINN) algorithm combined with Advanced Digital Network Data Design (ADNDD), a digital information processing network technology. ) for hospital safety dynamic control model. Firstly, the algorithm is optimized, secondly, the SOINN and ADNDD are fused to construct the network security dynamic control model, and finally, the performance of the model is verified using the dataset. The results show that after training in the dataset, the outlier recognition rate of the model in the datasets of surge attack, deviation attack and geometric attack is 92.13%, 90.04% and 89.07%, respectively. This indicates that the model algorithm can meet the requirements of network security in hospital network anomaly detection and dynamic defense control after the application of the dataset. The aim is to improve the security and stability of hospital networks.