| 摘要: |
| 移动传感器网络的物理层安全问题日益复杂，已经成为了一个研究热点。为了及时处理网络安全事件，研究了移动传感器网络的安全性能预测，提出了一种基于灰狼优化广义回归（Grey Wolf Optimization-Generalized Regression,GWO-GR）神经网络的安全性能智能预测方法。该方法利用发射天线选择策略，推导了非零安全容量概率性能的精确闭合表达式。仿真比较了所提方法、反向传播神经网络、广义回归神经网络、支持向量机等方法，结果表明，所提方法可以实现更好的预测性能，提高安全性能预测的实时性。 |
| 关键词: 移动传感器网络 物理层安全 安全性能智能预测 GWO-GR神经网络 |
| DOI： |
|
| 基金项目:国家自然科学基金资助项目（61901409）；江西省自然科学基金（20202BABL212001） |
|
| Intelligent Prediction for Security Performance of Mobile Sensor Networks |
| LI Zhenhua,WANG Han,DU Wencai |
| (1.Innovation and Entrepreneurship Institute,Yichun University,Yichun 336000,China;1.Innovation and Entrepreneurship Institute,Yichun University,Yichun 336000,China;2.Institute of Data Science,City University of Macau,Macau 999078,China) |
| Abstract: |
| The physical layer security of the mobile sensor network is becoming complex,which has been a research hotspot.In order to deal with network security issues timely,the secrecy performance prediction is investigated,and a grey wolf optimization-generalized regression(GWO-GR) neural network-based secrecy performance prediction method is proposed.With transmit antenna selection(TAS) scheme,the exact closed-form expressions for the probability of strictly positive secrecy capacity is derived.Compared with the back propagation(BP) neural network,generalized regression(GR) neural network,and support vector machine(SVM) methods,the simulation results show that the proposed method can achieve higher prediction results and improve the real-time performance of prediction. |
| Key words: mobile sensor network physical layer security secure performance intelligent prediction GWO-GR neural network |
