电讯技术2018，Vol.58Issue(6)：625-630,6.DOI:10.3969/j.issn.1001-893x.2018.06.002
采用改进型AlexNet的辐射源目标个体识别方法
Radiation Source Target Individual Recognition Based on Improved AlexNet
摘要
Abstract
For the need of accurately identifying radiation source target and according to machine learning technology represented by deep learning theory,this paper proposes using the improved AlexNet as feature extractor to realize the target's fine feature extraction and solidifying,and form the intelligent recognition network model. With Automatic Dependent Surveillance-Broadcast( ADS-B) signal as the experimental ob-ject,13 targets'ADS-B pulse signal data are collected in an airport as the training and test samples for the radiation source target individual recognition. The experiment uses AlexNet and improved AlexNet to verify the effectiveness of the algorithm. The results show that the improved AlexNet network has faster training time and the comprehensive recognition rate is 98. 32% .关键词
广播式自动相关监视( ADS-B)/目标识别/深度学习/卷积神经网络/改进型 AlexNetKey words
ADS-B/target recognition/deep learning/convolutional neural network/improved AlexNet分类
信息技术与安全科学引用本文复制引用
徐雄..采用改进型AlexNet的辐射源目标个体识别方法[J].电讯技术,2018,58(6):625-630,6.基金项目
国家重点研发计划(2017YFC1404900) （2017YFC1404900）
