Intra-pulse modulation recognition using short-time ramanujan Fourier transform spectrogram

Ma, Xu; Liu, Dan; Shan, Yunlong

doi:10.1186/s13634-017-0469-9

Cited by 13 publications

(11 citation statements)

References 30 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional recognition methods of feature extraction can be divided into two parts: feature extraction and classification. For feature extraction, scholars have proposed feature extraction methods based on fractional Fourier transform [6], [8], short-time Ramanujan Fourier transform [7], integrated quadratic phase function [8] and other feature extraction methods. However, the generalization performance and anti-noise performance of these methods are poor, and it is difficult to meet the needs of current radar intra-pulse modulation recognition.…”

Section: Introductionmentioning

confidence: 99%

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

Hou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Intra-pulse modulation recognition of radar signals is an important part of modern electronic intelligence reconnaissance and electronic support systems. With the increasing density of radar signals, the analysis and processing of multi-component radar signals have become an urgent problem in the current radar reconnaissance system. In this paper, an intra-pulse modulation recognition approach for singlecomponent and dual-component radar signals is proposed. First, in order to adapt to the time-frequency energy distribution characteristics of various radar signals, we propose to extract the time-frequency images (TFIs) of received signals by Cohen class time-frequency distribution (CTFD) with multiple kernel functions. Besides, the image processing methods are used to suppress noise and adjust the size and amplitude of the TFIs. Second, we design and pre-train a TFI feature extraction network for radar signals based on a convolutional neural network (CNN). Finally, to improve the probability of successful recognition (PSR) of the recognition system in the pulse overlapping environment, a multi-label classification network based on a deep Q-learning network (DQN) is explored. Besides, two sub-networks take TFIs based on special kernel functions as input and re-judge the recognition results of some specific signals to further enhance the recognition effect of the recognition system. The proposed approach can identify 8 kinds of random overlapping radar signals. The simulation results show that the overall PSR of dual-component radar signals and single-component radar signals can reach 94.83% and 94.43%, respectively, when the signal-to-noise ratio (SNR) is −6 dB. INDEX TERMS Radar signal recognition, Cohen class time-frequency distribution, convolutional neural network, deep Q-learning network.

show abstract

Section: Introductionmentioning

confidence: 99%

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

Hou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The proposed method based on EC-STFT and RDBN achieves a higher recognition rate than other radar emitter intra-pulse signal recognizing methods. In the simulations, we selected four recognition methods with similar study objects and constraints: STFT + SCDAEs [ 2 ], 3DDF + TL [ 21 ], TFI + CNN [ 22 ] and ST-RFT + PZMs [ 23 ]. These four methods all focus on radar emitter intra-pulse signal recognition with five to seven types.…”

Section: Simulations and Discussionmentioning

confidence: 99%

“…The TFD is a good method to study radar emitter intro-pulse signals. In [ 21 , 22 , 23 ], STFT, WVD and CWD were improved and applied to recognition work. In [ 3 ], we combined STFT with CNN to complete the recognition task and found that the noise could disorder the two dimensional distribution, which resulted in a low recognition rate of less than −3 dB.…”

Section: The Proposed Recognition Methods Analysismentioning

confidence: 99%

“…The vectors and matrixes are commonly in large size and cannot directly gives the exact characteristic values, so neural networks, machine learning algorithms and deep learning models are used to extracted the features automatically and then complete the recognition task. In [ 3 , 21 , 22 , 23 ], the short time Fourier transform (STFT), Wigner-Ville distribution (WVD) and Choi-Williams distribution (CWD) are used as feature input to convolutional neural network (CNN) for recognition. All three of these achieve good results, while in [ 3 ], the network is not modified for the best; in [ 22 ], the method refers to the different carrier frequency of the eight waveforms in which the polyphase coding recognition might have little generalization; and in [ 23 ], it shows relatively high recognition results without enumerating the concrete researched radar waveforms, which is a vital factor for evaluating any method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Radar Emitter Recognition Based on the Energy Cumulant of Short Time Fourier Transform and Reinforced Deep Belief Network

Wang

Huang

Zhou

et al. 2018

Sensors

View full text Add to dashboard Cite

To cope with the complex electromagnetic environment and varied signal styles, a novel method based on the energy cumulant of short time Fourier transform and reinforced deep belief network is proposed to gain a higher correct recognition rate for radar emitter intra-pulse signals at a low signal-to-noise ratio. The energy cumulant of short time Fourier transform is attained by calculating the accumulations of each frequency sample value with the different time samples. Before this procedure, the time frequency distribution via short time Fourier transform is processed by base noise reduction. The reinforced deep belief network is proposed to employ the input feature vectors for training to achieve the radar emitter recognition and classification. Simulation results manifest that the proposed method is feasible and robust in radar emitter recognition even at a low SNR.

show abstract

“…For example, non-uniform sampling caused by instability of electronic clock, reconstruction of computed tomography image, radar signal processing, etc. The problem of equally spaced sampling [1] .…”

Section: Introductionmentioning

confidence: 99%

Analysis of speech signals based on short-time Fourier Method

Yu¹

2018

2018 1st International Conference on Engineering, Communication and Computer Sciences (ICECCS 2018)

View full text Add to dashboard Cite

Aiming at the problem that the heterodyne signals inherent in pseudo-random (PN) code modulated speech signals cannot be equally spaced, a new short-time Fourier transform (DFT) method for non-uniform sampling signals is proposed. Firstly, the speech signal system model of distance velocity measurement is given, and the reason why the heterodyne signal can't be equally spaced is pointed out. Then, a new spectrum analysis method of non-uniform sampling signal is proposed by theoretical derivation. Finally, the simulation is verified by simulation. The method can be used to analyze the spectrum of non-equally spaced sampled signals. The results show that the method can still effectively analyze the frequency of unequal interval sampling Doppler signals in the Doppler frequency range generated by road moving targets with the received signal signal-to-noise ratio (SNR) of 0 dB.

show abstract

Intra-pulse modulation recognition using short-time ramanujan Fourier transform spectrogram

Cited by 13 publications

References 30 publications

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

Radar Emitter Recognition Based on the Energy Cumulant of Short Time Fourier Transform and Reinforced Deep Belief Network

Analysis of speech signals based on short-time Fourier Method

Contact Info

Product

Resources

About