基于注意力机制和改进CLDNN的雷达辐射源识别

传统的辐射源识别通过比对、匹配辐射源信号与雷达数据库来识别,这种方法很难满足战时高效、快速和准确的识别要求.随着机器学习方法的提出,诸如支持向量机等算法在辐射源识别领域的运用,可以满足战时高效、快速的识别要求,但这种方法在低信噪比环境下,辐射源识别准确率低.针对上述问题,采用深度学习,引入注意力机制和特征融合方法,提出...

Radar emitter identification based on attention mechanism and improved CLDNN

Traditional emitter identification is based on the comparison and matching of emitter signal and radar database,which is difficult to meet the requirements of high efficiency,fast and accurate identification in wartime.With the development of machine learning methods,such as the application of support vector machine(SVM)and other algorithm in the field of emitter identification,can meet the requirements of efficient and rapid identification in wartime.However,this method has low accuracy of emitter identification in low signal to noise ratio environment.In order to solve the above problems,the deep learning is used,the attention mechanism and feature fusion method is introduced,and a indentification model of attention-mechanism feature-fusion one-dimensional convolution long-short-term-memory deep neural networks(AF1CLDNN)is proposed.The effectiveness of attention mechanism and feature fusion method is verified by experiments,and the new indentification model has high indentification accuracy and indentification speed in low signal to noise ratio environment.