摘要
提出一种基于深度学习的智能电视网络安全实时监测系统。该系统通过融合卷积神经网络(Convolutional Neural Networks,CNN)和长短时记忆网络(Long Short-Term Memory,LSTM)构建的HybridNet模型,对网络流量进行特征提取与威胁分类。结合自适应数据清洗(Adaptive Data Cleaning,ADC)算法和改进的孤立森林算法,该系统实现了对网络威胁的实时监测与快速响应。实验结果显示,该系统能够有效提高威胁检测的准确率和响应速度,并有效减少资源消耗。
This paper proposes a real-time security monitoring system for smart television networks based on deep learning.The HybridNet model constructed by Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM),It is used for feature extraction and threat classification of network traffic.Combined with Adaptive Data Cleaning(ADC)algorithm and improved isolated forest algorithm,the system realizes real-time monitoring and rapid response to network threats.The experimental results show that the system can effectively improve the accuracy and response speed of threat detection,and effectively reduce resource consumption.
作者
张岱英
ZHANG Daiying(Tengzhou Media Center,Zaozhuang 277500,China)
出处
《电视技术》
2024年第12期40-42,共3页
Video Engineering
关键词
深度学习
智能电视
网络安全
deep learning
smart television
network security
作者简介
张岱英(1981-),女,本科,工程师,研究方向为广播电视工程。
