Abstract
Analyzing radar signals is a critical task in modern Electronic Warfare (EW) environments. However, the pulse streams emitted by radars have flexible features and complex patterns which are difficult to be identified from a statistical perspective. To solve this problem, pulse repetition interval (PRI) is used as a distinguishing parameter of emitters to be identified. However, traditional PRI modulation recognition methods can only deal with simple PRI modulations and their performance will further degrade with the increasing number of emitters or noisy environments. In this paper, we introduce an attention-based recognition framework based on recurrent neural network (RNN) to categorize pulse streams with complex PRI modulations and in environments with high ratios of missing and spurious pulses. Simulation results show that our model is robust to noisy environments and has a better performance than conventional methods.
Highlights
With the rapid development and usage of advanced communications [1], [2], navigation [3]–[5] and radar systems [6], [7], the Electronic Warfare (EW) environment is more crowded nowadays
We introduce an attentionbased recognition framework based on recurrent neural network (RNN) to categorize pulse streams with complex pulse repetition interval (PRI) modulations and in environments with high ratios of missing and spurious pulses
Four different ratios of lost pulses and six ratios of spurious pulses for each PRI modulation mode are put into the well-trained model separately to understand how the proposed RNN model is performed in different environments
Summary
With the rapid development and usage of advanced communications [1], [2], navigation [3]–[5] and radar systems [6], [7], the Electronic Warfare (EW) environment is more crowded nowadays. Kauppi et al [19] utilized a two-stage hierarchical classification scheme and extracted subpatterns to identify the PRI modulation mode This method seeks for features of PRI sequences to distinguish different types of PRI, but it cannot work when there are high ratios of noise which breaks the regularity of the subpatterns. We propose to use the recurrent neural networks [23] and the attention mechanism [24] to solve the PRI modulation recognition problem. We introduce an attentionbased recognition framework based on recurrent neural network (RNN) to categorize pulse streams with complex PRI modulations and in environments with high ratios of missing and spurious pulses. Experiment results illustrate that the proposed attention-based RNN model can recognize six complex PRI modulation modes with high ratios of spurious and lost pulses. One-hot features can be processed more by machine learning techniques than their numerical counterparts [34]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
