典型文献
A novel approach for unlabeled samples in radiation source identification
文献摘要：
Radiation source identification plays an important role in non-cooperative communication scene and numerous methods have been proposed in this field. Deep learning has gained po-pularity in a variety of computer vision tasks. Recently, it has also been successfully applied for radiation source identification. However, training deep neural networks for classification re-quires a large number of labeled samples, and in non-coopera-tive applications, it is unrealistic. This paper proposes a method for the unlabeled samples of unknown radiation source. It uses semi-supervised learning to detect unlabeled samples and label new samples automatically. It avoids retraining the neural net-work with parameter-transfer learning. The results show that compared with the traditional algorithms, the proposed algo-rithm can offer better accuracy.
文献关键词：
中图分类号：
作者姓名：
YANG Haifen;ZHANG Hao;WANG Houjun;GUO Zhengyang
作者机构：
School of Information and Communication Engineering,University of Electronic Science and Technology of China,Chengdu 611731,China
文献出处：
引用格式：
[1]YANG Haifen;ZHANG Hao;WANG Houjun;GUO Zhengyang-.A novel approach for unlabeled samples in radiation source identification)[J].系统工程与电子技术（英文版）,2022(02):354-359
A类：
pularity
B类：
novel,approach,unlabeled,samples,radiation,source,identification,Radiation,plays,important,role,cooperative,communication,scene,numerous,methods,have,been,proposed,this,field,Deep,learning,has,gained,variety,computer,vision,tasks,Recently,also,successfully,applied,However,deep,neural,networks,classification,quires,large,number,applications,unrealistic,This,paper,proposes,unknown,It,uses,semi,supervised,detect,new,automatically,avoids,retraining,parameter,transfer,results,show,that,compared,traditional,algorithms,can,offer,better,accuracy
AB值：
0.575303
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
