计算机科学
调制(音乐)
模式识别(心理学)
人工智能
集合(抽象数据类型)
人工神经网络
信号(编程语言)
质心
相似性(几何)
链路自适应
特征(语言学)
语音识别
频道(广播)
电信
衰退
哲学
语言学
图像(数学)
程序设计语言
美学
作者
Xinliang Zhang,Tianyun Li,Pei Gong,Renwei Liu,Xiong Zha,Wenqi Tang
标识
DOI:10.1109/lcomm.2022.3174035
摘要
This letter proposes a deep learning-based method for wireless communication signal modulation recognition. Modified generalized end-to-end (GE2E) loss is used to train the designed neural network, which can increase the similarity of the feature vectors of the same modulation type and reduce that of different types. The similarities between training samples and centroid vectors are calculated to set the adaptive thresholds for each known modulation type. The experimental results show that the proposed method can reject unknown signals while remaining the recognition quality of known signals, which has higher efficiency and lower complexity than other open set recognition (OSR) algorithms in modulation recognition.
科研通智能强力驱动
Strongly Powered by AbleSci AI