Radar signal identification and positioning method based on MobileNet model transfer learning

Abstract

The invention belongs to the technical field of radar signal modulation mode identification, and particularly relates to a radar signal identification and positioning method based on MobileNet model transfer learning. According to the method, based on MobileNet model transfer learning and gradient weighted class activation mapping, the network model is built by using depth separable convolution, so that model parameters can be effectively reduced, and the calculation efficiency of the model is improved; transfer learning training is carried out by loading the pre-training model in the training process, so that the convergence speed and generalization performance of the model can be improved; and meanwhile, a prediction result of the network model is visualized by adopting a gradient weighted category activation mapping method, so that the interpretability and transparency of the deep learning model are improved.

Description

technical field [0001] The invention belongs to the technical field of radar signal modulation mode identification, and in particular relates to a radar signal identification and positioning method based on MobileNet model transfer learning. Background technique [0002] Traditional radar signal recognition algorithms use manually extracted features to classify signals, such as high-order cumulants, cyclostationary features, distribution distances, probability distances, spectral correlations, autocorrelation functions, and time-frequency image features. These features work well for specific radar signals, but the method is computationally complex, has high development costs, and lacks flexibility and universality. In recent years, with the continuous improvement of computer hardware level, deep learning has achieved remarkable results in computer vision and other fields because of its excellent performance. At the same time, deep learning has also produced a large number o...

AI Technical Summary

Problems solved by technology

[0004] Although the current convolutional neural network has made unprecedented breakthroughs in many fields, deep learning models are often regarded as black boxes because they lack proper interpretability and cannot intuitively analyze their internal working principles, thus making research Humans and users lack the necessary trust in deep learning models and intelligent systems

Images