When building an experimental platform for light propagation along an inhomogeneous turbulent path,it is very essential to set up the reasonable distribution of phase screen.Based on multi-layered model of phase scree...When building an experimental platform for light propagation along an inhomogeneous turbulent path,it is very essential to set up the reasonable distribution of phase screen.Based on multi-layered model of phase screen,an iterative optimization algorithm of phase screen position is given in this paper.Thereafter,the optimal position of phase screens is calculated under the Hufnagel-Valley5/7 and Hefei-day turbulence profile.The results show that the positions of phase screen calculated by the iterative algorithm can fit well with the turbulence profile rather than mechanically placed phase screens at equal distance.Compared with the uniform distribution of phase screens position,the residual phase error of the iterative algorithm decreases very significantly.The similarity degree between them is minimal when number of layers is equal to two.展开更多
Deep learning has been fully verified and accepted in the field of electromagnetic signal classification. However, in many specific scenarios, such as radio resource management for aircraft communications, labeled dat...Deep learning has been fully verified and accepted in the field of electromagnetic signal classification. However, in many specific scenarios, such as radio resource management for aircraft communications, labeled data are difficult to obtain, which makes the best deep learning methods at present seem almost powerless, because these methods need a large amount of labeled data for training. When the training dataset is small, it is highly possible to fall into overfitting, which causes performance degradation of the deep neural network. For few-shot electromagnetic signal classification, data augmentation is one of the most intuitive countermeasures. In this work, a generative adversarial network based on the data augmentation method is proposed to achieve better classification performance for electromagnetic signals. Based on the similarity principle, a screening mechanism is established to obtain high-quality generated signals. Then, a data union augmentation algorithm is designed by introducing spatiotemporally flipped shapes of the signal. To verify the effectiveness of the proposed data augmentation algorithm, experiments are conducted on the RADIOML 2016.04C dataset and real-world ACARS dataset. The experimental results show that the proposed method significantly improves the performance of few-shot electromagnetic signal classification.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant No.61308082)
文摘When building an experimental platform for light propagation along an inhomogeneous turbulent path,it is very essential to set up the reasonable distribution of phase screen.Based on multi-layered model of phase screen,an iterative optimization algorithm of phase screen position is given in this paper.Thereafter,the optimal position of phase screens is calculated under the Hufnagel-Valley5/7 and Hefei-day turbulence profile.The results show that the positions of phase screen calculated by the iterative algorithm can fit well with the turbulence profile rather than mechanically placed phase screens at equal distance.Compared with the uniform distribution of phase screens position,the residual phase error of the iterative algorithm decreases very significantly.The similarity degree between them is minimal when number of layers is equal to two.
基金supported by the National Natural Science Foundation of China(No.61772401)the Fundamental Research Funds for the Central Universities(No.RW180177)supported by the Science and Technology on Communication Information Security Control Laboratory。
文摘Deep learning has been fully verified and accepted in the field of electromagnetic signal classification. However, in many specific scenarios, such as radio resource management for aircraft communications, labeled data are difficult to obtain, which makes the best deep learning methods at present seem almost powerless, because these methods need a large amount of labeled data for training. When the training dataset is small, it is highly possible to fall into overfitting, which causes performance degradation of the deep neural network. For few-shot electromagnetic signal classification, data augmentation is one of the most intuitive countermeasures. In this work, a generative adversarial network based on the data augmentation method is proposed to achieve better classification performance for electromagnetic signals. Based on the similarity principle, a screening mechanism is established to obtain high-quality generated signals. Then, a data union augmentation algorithm is designed by introducing spatiotemporally flipped shapes of the signal. To verify the effectiveness of the proposed data augmentation algorithm, experiments are conducted on the RADIOML 2016.04C dataset and real-world ACARS dataset. The experimental results show that the proposed method significantly improves the performance of few-shot electromagnetic signal classification.
