计算机科学
卷积(计算机科学)
人工智能
调制(音乐)
模式识别(心理学)
机器学习
电子工程
人工神经网络
哲学
工程类
美学
作者
Wenxuan Ma,Zhuoran Cai,Chuan Wang
标识
DOI:10.1109/lcomm.2024.3380623
摘要
Automatic modulation classification (AMC) is a typical pattern classification task that is an intermediate process between signal detection and demodulation. Deep learning methods used in AMC, such as convolutional neural network (CNN) have their shortcomings. We propose a new parallel CNN transformer network (PCTNet), which not only possesses the advantages of transformer to capture long-range dependencies, but also utilizes the advantages of CNN to extract local information. PCTNet is a parallel design of CNN and transformer, with a delivery mechanism in the middle. Extensive simulation results show that our proposed PCTNet can achieve superior classification performance than traditional deep models.
科研通智能强力驱动
Strongly Powered by AbleSci AI