基于深度学习的电视台异常无线电信号监测方法

常规的电视台异常无线电信号监测方法主要使用栈式自编码网络重构电信号时空特征,易受自适应门限动态阈值变化影响,导致监测异常,因此需要基于深度学习设计一种全新的电视台异常无线电信号监测方法。分析了无线电信号监测数据空间特征,利用深度学习构建无线电信号监测模型,从而实现了电视台异常无线电信号监测。实验结果表明,设计的电视台异常无线电信号深度学习监测方法的效果较好,在不同频带均能有效监测到异常的无线电信号,监测的准确率可达到98.65%,具有可靠性,有一定的应用价值,为提高电视台播放的可靠性作出了一定的贡献。

Conventional methods for monitoring abnormal radio signals in television stations mainly use a stack type self coding network to reconstruct the spatiotemporal characteristics of electrical signals, which is easily affected by adaptive threshold dynamic threshold changes, leading to abnormal monitoring. Therefore, it is necessary to design a new method for monitoring abnormal radio signals in television stations based on deep learning.By analyzing the spatial characteristics of radio signal monitoring data, a radio signal monitoring model using deep learning is constructed, and abnormal radio signal monitoring of television stations is achieved. The experimental results show that the designed deep learning monitoring method for abnormal radio signals in television stations has a good monitoring effect, and can effectively detect abnormal radio signals in different frequency bands. The monitoring accuracy can reach 98.65%, which is reliable and has certain application value. It has made a certain contribution to improving the reliability of television broadcasting.