Research on prediction of school computer network security situation based on IOT

被引:0
作者
Wei Yan
Lei Qiao
Singamaneni Krishnapriya
Rahul Neware
机构
[1] Jiangsu Ocean University,Department of Computer Science Engineering, Bapatla Engineering College
[2] Information Management,Department of Computing, Mathematics and Physics
[3] Acharya Nagarjuna University,undefined
[4] Høgskulen På Vestlandet,undefined
来源
International Journal of System Assurance Engineering and Management | 2022年 / 13卷
关键词
Network security; Network security situation prediction; Support vector machine (SVM); Prediction method;
D O I
暂无
中图分类号
学科分类号
摘要
The degree of network attack methods is limitless, and the conventional defence and detection mode cannot satisfy the needs of network security monitoring, thanks to the fast growth of network technology and the large-scale expansion of networks. Widely distributed network system, the network system structure becomes increasingly complex, the network is facing increasingly attacks and threats, network security problems are increasingly serious, a variety of security incidents and vulnerabilities are increasingly frequent, including hacker attacks, and network security vulnerability is gradually exposed. Traditional ways of dealing with the problem may be insufficient, resulting in harm to persons and businesses, as well as the loss of property and a reduction in people's faith in the Internet. An IOT (Internet of Things) based orientated model is suggested to increase the accuracy in predicting network security condition for schools. The data is first rebuilt into a multidimensional time series, then fed into the support vector machine for training, and then nonlinear method is utilised to handle the problem of parameter optimization of the training mode to create the network security scenario prediction model. Finally, utilising IOT, the network security scenario prediction model is utilised to forecast network security in the future. The simulation results show that the optimal parameters of the support vector machine (SVM) are C = 10, σ = 0.625, and ε = 0.001. C = 10, σ = 0.625, ε = 0.001 were used to relearn the training set, the optimal network security situation prediction model was established, and the test set was predicted. The projected values were close to the actual values, and the accuracy of the forecast was high. The model, when paired with the nonlinear algorithm and SVM, can accurately reflect the network's overall security operation, enhance network security scenario forecast accuracy, and help the administrator in network security control.
引用
收藏
页码:488 / 495
页数:7
相关论文
共 58 条
[1]  
Abdul-Ghani HA(2018)A comprehensive IoT attacks survey based on a building-blocked reference model Int J Adv Comput Sci Appl 9 3-286
[2]  
Konstantas D(2020)A study of frozen iteratively regularized Gauss–newton algorithm for nonlinear ill-posed problems under generalized normal solvability conditions J Inverse Ill-Posed Problems 28 275-648
[3]  
Mahyoub M(2020)Dynamic input reconstruction algorithm for a nonlinear equation with distributed parameters Differ Equations 56 641-1683
[4]  
Bakushinsky A(2018)A survey on security control and attack detection for industrial cyber-physical systems Neurocomputing 275 1674-87578
[5]  
Smirnova A(2021)SSII: secured and high-quality steganography using intelligent hybrid optimization algorithms for IoT IEEE Access 9 87563-180
[6]  
Blizorukova MS(2019)System architecture and key technologies of network security situation awareness system Yhsas Comput Mater Continua 59 167-82743
[7]  
Maksimov VI(2019)A survey on IoT security: application areas, security threats, and solution architectures IEEE Access 7 82721-6018
[8]  
Ding D(2020)Modified backstepping algorithm with disturbance compensation for nonlinear mimo systems IFAC-PapersOnLine 53 6012-3074
[9]  
Han QL(2021)Secure access control for manufacturing sector with application of ethereum blockchain Peer-to-Peer Netw Appl 14 3058-708
[10]  
Xiang Y(2021)Preserving health care data security and privacy using Carmichael’s theorem-based homomorphic encryption and modified enhanced homomorphic encryption schemes in edge computing systems Big Data 21 699-25