基于轻量级卷积神经网络的5G随机接入信道检测增强方法OA
Enhanced 5G Random Access Channel Detection Method Based on Lightweight Convolutional Neural Network
物理随机接入信道(Physical Random Access Channel,PRACH)在5G 系统中发挥着重要作用,而PRACH 检测是无线信号处理领域的关键问题.在低信噪比环境下,传统的 PRACH 检测算法容易受到噪声干扰,导致检测率降低.为提升检测性能,提出一种基于深度学习的 PRACH 检测增强方法.在经典相关性算法的基础上,引入一个由深度可分离卷积构建的轻量级卷积神经网络(Convolutional Neural Network,CNN),以替代传统的固定阈值判决机制.实验验证表明,在维持相同虚警率的条件下,该方法的正确检测率优于传统阈值判决方法.
The Physical Random Access Channel(PRACH)plays an important role in the 5G system,and PRACH detection is a key issue in the field of wireless signal processing.In a low signal to noise ratio environment,the traditional PRACH detection algorithm is prone to noise interference,resulting in a reduced detection rate.To improve the detection performance,an enhanced PRACH detection method based on deep learning is proposed.Based on the classical correlation algorithm,this method introduces a lightweight Convolutional Neural Network(CNN)constructed by depthwise separable convolution to replace the traditional fixed threshold decision mechanism.Experimental verification shows that,under the condition of maintaining the same false alarm rate,the correct detection rate of this method is superior to that of the traditional threshold decision method.
孔欢;刘奕彤;李卓航;孙宇楠;杨鸿文
北京邮电大学 信息与通信工程学院,北京 100876北京邮电大学 信息与通信工程学院,北京 100876北京邮电大学 信息与通信工程学院,北京 100876北京邮电大学 信息与通信工程学院,北京 100876北京邮电大学 信息与通信工程学院,北京 100876
信息技术与安全科学
物理随机接入信道深度学习轻量级模型用户检测
PRACHdeep learninglightweight modeluser detection
《无线电工程》 2026 (3)
436-443,8
应急通信装备创新揭榜挂帅(E08-01) Emergency Communication Equipment Innovation Uncover-the-rank and Assume-the-role(E08-01)
评论