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

针对辐射源目标精确识别需求,结合以深度学习为代表的机器学习理论技术,提出将改进型AlexNet作为特征提取器,实现目标细微特征提取固化,形成智能化识别网络模型。以广播式自动相关监视(ADS-B)信号为实验对象,在机场实地采集了13个目标的ADS-B脉冲信号数据作为辐射源目标个体识别的训练和测试样本,利用AlexNet和改进的AlexNet验证了算法的有效性。结果表明,改进的AlexNet网络训练时间更快,综合识别率达到98.32%。

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 object,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%.