陶志勇,闫明豪,刘 影,杜福廷.基于 AG-CNN 的轻量级调制识别方法[J].电子测量与仪器学报,2022,36(4):241-249 |
基于 AG-CNN 的轻量级调制识别方法 |
Lightweight modulation recognition method based on AG-CNN |
|
DOI: |
中文关键词: 调制盲识别 密度星座图 深度学习 Ghost 模块 双注意力机制 |
英文关键词:modulation blind recognition density constellation deep learning Ghost module dual attention mechanism |
基金项目:国家重点研发计划项目“新兴产业集成化检验检测服务平台研发与应用”(2018YFB1403303)项目资助 |
|
|
摘要点击次数: 893 |
全文下载次数: 834 |
中文摘要: |
针对传统卷积神经网络在调制方式盲识别过程中,存在模型体积大、运算量高、无法部署至移动端等问题,提出了一种
基于双注意力机制与 Ghost 模块的轻量级 CNN 模型 AG-CNN(attention and Ghost convolution neural network)调制识别方法,该方
法首先将调制信号映射至复空间,并根据归一化点密度对映射点进行颜色处理,得到高阶特征密度星座图;将该特征作为 AGCNN 模型的输入进行学习训练,最后使用训练好的模型对接收端接收到的未知信号进行识别。 实验表明,AG-CNN 模型对散点
为 10 000 的密度星座图识别率在 99. 95%以上,与相同层数的 CNN 模型相比,卷积层参数量压缩 6. 01 倍,计算量压缩 6. 76 倍,
且相较于 VGG-16、InceptionV3、ResNet-50、Shufflenet、Efficientnet 等卷积网络模型,参数量与浮点数运算数下降明显,且在大幅节
省学习参数量、降低模型复杂度的情况下,表现出优秀的分类性能。 |
英文摘要: |
In view of the problems of large model volume, high computation and unable to deploy to mobile terminal in the blind
recognition of modulation mode in traditional convolutional neural network, a modulation recognition method of attention and Ghost
convolution neural network (AG- CNN) based on dual attention mechanism and ghost module is proposed. The modulation signal is
mapped to complex space, the map points are processed by the normalized point density, and the higher order feature density
constellation is obtained. The feature is used as input of AG-CNN model for learning training, the trained model is finally used to identify
the unknown signal received by the receiver. The experimental results show that the recognition rate of density constellation map with
sampling point of 10 000 is over 99. 95% by AG-CNN model. Compared with CNN model with the same number of layers, the
convolution layer parameter is compressed by 6. 01 times and the calculation amount is 6. 76 times. Compared with VGG-16, Inception
V3, ResNet-50, Shufflenet, Eficientnet and other convolutional network models, the number of parameters and floating-point operations
decreases significantly, and in the case of saving learning parameters and reducing the complexity of the model, it shows excellent
classification performance. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|