This paper introduces the time-frequency analyzed long short-term memory (TF-LSTM) neural network method for jamming signal recognition over the Global Navigation Satellite System (GNSS) receiver. The method introduces the long short-term memory (LSTM) neural network into the recognition algo-rithm and combines the time-frequency (TF) analysis for signal preprocessing. Five kinds of navigation jamming signals includ-ing white Gaussian noise (WGN), pulse jamming, sweep jam-ming, audio jamming, and spread spectrum jamming are used as input for training and recognition. Since the signal parame-ters and quantity are unknown in the actual scenario, this work builds a data set containing multiple kinds and parameters jam-ming to train the TF-LSTM. The performance of this method is evaluated by simulations and experiments. The method has higher recognition accuracy and better robustness than the exis-ting methods, such as LSTM and the convolutional neural net-work (CNN).

FU Dong;LI Xiangjun;MOU Weihua;MA Ming;OU Gang

College of Electronic Science and Technology,National University of Defense Technology,Changsha 410005,China

系统工程与电子技术（英文版）

[1]FU Dong;LI Xiangjun;MOU Weihua;MA Ming;OU Gang-.Navigation jamming signal recognition based on long short-term memory neural networks)[J].系统工程与电子技术（英文版）,2022(04):835-844

WGN

Navigation,jamming,recognition,long,short,term,memory,neural,networks,This,paper,introduces,frequency,analyzed,TF,over,Global,Satellite,System,GNSS,receiver,into,algo,rithm,combines,analysis,preprocessing,Five,kinds,navigation,signals,includ,white,Gaussian,noise,pulse,sweep,audio,spread,spectrum,are,used,input,training,Since,quantity,unknown,actual,scenario,this,builds,data,set,containing,multiple,parameters,performance,evaluated,by,simulations,experiments,has,higher,accuracy,better,robustness,than,exis,ting,methods,such,convolutional

0.493999