109 Hits in 5.1 sec

Radar Emitter Classification with Attribute-specific Recurrent Neural Networks [article]

Paolo Notaro, Magdalini Paschali, Carsten Hopke, David Wittmann, Nassir Navab
2019 arXiv   pre-print
Radar pulse streams exhibit increasingly complex temporal patterns and can no longer rely on a purely value-based analysis of the pulse attributes for the purpose of emitter classification.  ...  In this paper, we employ Recurrent Neural Networks (RNNs) to efficiently model and exploit the temporal dependencies present inside pulse streams.  ...  Macro-averaged test accuracy for emitter classification networks with and without attribute-specific LSTMs along with different normalization schemes. • • • 0.1445 • 0.1449 • • • 0.5894 • 0.6006 • • •  ... 
arXiv:1911.07683v2 fatcat:od7wkyfjkrfyhdjtzjqkuhrxly

Artificial Intelligence Aided Electronic Warfare Systems-Recent Trends and Evolving Applications

Purabi Sharma, Kandarpa Kumar Sarma, Nikos Mastorakis
2020 IEEE Access  
Recurrent neural network (RNN) and nonlinear autoregressive network with exogenous inputs (NARX) are examples of feedback ANN.  ...  Another neural network based radar signal classification system is presented in [27] .  ... 
doi:10.1109/access.2020.3044453 fatcat:iuwn6w4uvbgdhlkiucg3sjadme

Radar Emitter Identification Based on Stacked Long and Short Term Memory

Lei Meng, Wei Qu, Kai Cai
2021 DEStech Transactions on Materials Science and Engineering  
With the increasing complexity of electromagnetic environment and the rising of operating patterns of new radars, emitter identification is becoming more and more difficult.  ...  The timing characteristics of the pulses are automatically extracted by SLSTM, and the optimal network parameters are trained to complete radar signal identification.  ...  With the widely application of the deep learning techniques, the recurrent neural networks (RNNs) have shown an amazing ability in speech recognition, machine translation and other sequential data processing  ... 
doi:10.12783/dtmse/ameme2020/35532 fatcat:xta642cv7ndplcxisw67ob4d6y

Method for functional state recognition of multifunction radars based on recurrent neural networks

Xinsong Xu, Daping Bi, Jifei Pan
2021 IET radar, sonar & navigation  
Inspired by recent progress of deep neural networks, the authors propose to further develop radar signal modelling with recurrent neural networks.  ...  For the multifunction radars (MFRs) with complex dynamical modes, the signal recognition needs to identify not only the emitter but also its current functional state.  ...  There are many studies on radar signal recognition, which mainly focus on radar emitter classification (REC) and specific emitter identification (SEI) [3] [4] [5] .  ... 
doi:10.1049/rsn2.12075 fatcat:67jlgfyg7ndt7d67kgpwp4ahb4

A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing [article]

Ping Lang, Xiongjun Fu, Marco Martorella, Jian Dong, Rui Qin, Xianpeng Meng, Min Xie
2020 arXiv   pre-print
Traditional radar signal processing (RSP) methods have shown some limitations when meeting such requirements, particularly in matters of target classification.  ...  With the rapid development of machine learning (ML), especially deep learning, radar researchers have started integrating these new methods when solving RSP-related problems.  ...  algorithm RNNs recurrent neural networks RS remote sensing RESISC remote sensing image scene classification RBF radial basis function REC radar emitter classification RBM restricted Boltzmann machine  ... 
arXiv:2009.13702v1 fatcat:m6am73324zdwba736sn3vmph3i

Attention-based Radar PRI Modulation Recognition with Recurrent Neural Networks

Xueqiong Li, Zhangmeng Liu, Zhitao Huang
2020 IEEE Access  
INDEX TERMS Attention mechanism, electronic warfare, PRI modulation, recurrent neural network (RNN).  ...  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  ...  A classification method based on convolutional neural network (CNN) is proposed in [21] .  ... 
doi:10.1109/access.2020.2982654 fatcat:kfxiuwkrg5cehl64fvumpho554

Online Non-cooperative Radar Emitter Classification from Evolving and Imbalanced Pulse Streams

Jingping Sui, Zhen Liu, Li Liu, Bo Peng, Tianpeng Liu, Xiang Li
2020 IEEE Sensors Journal  
Recent research treats radar emitter classification (REC) problems as typical closed-set classification problems, i.e., assuming all radar emitters are cooperative and their pulses can be pre-obtained  ...  Specifically, a novel data stream clustering (DSC) algorithm, called dynamic improved exemplar-based subspace clustering (DI-ESC), is proposed, which consists of two phases, i.e., initialization and online  ...  [1] , [13] , and even deep learning networks (e.g., convolutional neural networks (CNN) [14] and recurrent neural networks (RNN) [4] ) are introduced to classify the pulses based on the features.  ... 
doi:10.1109/jsen.2020.2981976 fatcat:qdtlu5khozcbrledyof7bjor2a

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

Zhiyu Qu, Chenfan Hou, Changbo Hou, Wenyang Wang
2020 IEEE Access  
Second, we design and pre-train a TFI feature extraction network for radar signals based on a convolutional neural network (CNN).  ...  INDEX TERMS Radar signal recognition, Cohen class time-frequency distribution, convolutional neural network, deep Q-learning network. 49126 VOLUME 8, 2020  ...  MULTI-LABEL CLASSIFICATION NETWORK In this section, the fully connected layer and the Softmax layer of the neural network in the previous section are replaced by a recurrent neural network (RNN).  ... 
doi:10.1109/access.2020.2980363 fatcat:gfizn2w2yrad7kk75fpcq62cum

A unified method for deinterleaving and PRI modulation recognition of radar pulses based on deep neural networks

Jin-Woo Han, Cheong hee Park
2021 IEEE Access  
In [22] , a method of estimating PRI using pulse width and PRI as inputs of the recurrent neural network was proposed, but this must be repeated continuously through re-input after extracting the pulse  ...  PRI is a key characteristic of radar emitters and refers to the repetition period of the pulses transmitted by the radar.  ...  This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see  ... 
doi:10.1109/access.2021.3091309 fatcat:6fgodii7tncebk3d3c3co6wfki

Deep learning for aircraft classification from VHF radar signatures

Jérémy Fix, Chengfang Ren, Arthur Costa Lopes, Guillaume Morice, Shuwa Kobayashi, Thierry Leterte, Israel D. Hinostroza Sáenz
2021 IET radar, sonar & navigation  
Encouraging initial results were obtained using convolutional or recurrent neural networks to classify aircraft classes, combining simulated bistatic RCS results and real trajectories (collected from automatic  ...  This difference can be exploited to recognize the size of the aeroplanes with respect to these classes.  ...  While both features appear insightful for aeroplane recognition, either convolutional neural networks (CNNs) or recurrent neural networks (RNNs) are proposed to deal with different representations of RCS  ... 
doi:10.1049/rsn2.12067 fatcat:f73wzbdlsbaehcp6yxme54f6kq

Blind Deinterleaving of Signals in Time Series with Self-attention Based Soft Min-cost Flow Learning [article]

Oğul Can, Yeti Z. Gürbüz, Berkin Yıldırım, A. Aydın Alatan
2020 arXiv   pre-print
We then approximate the lower level optimization problem by self-attention based neural networks and provide a trainable framework that clusters the patterns in the input as the distinct flows.  ...  We evaluate our method with extensive experiments on a large dataset with several challenging scenarios to show the efficiency.  ...  Moreover, [12] utilizes recurrent neural networks (RNNs) to capture the current context of the pulse stream and predict attributes of the next PDWs.  ... 
arXiv:2010.12972v1 fatcat:mlzqazr2iffklavstfmd7ht634

Grand Challenges in Radar Signal Processing

Fulvio Gini
2021 Frontiers in Signal Processing  
They also include automatic feature learning such as deep learning (e.g., deep belief networks (DBN), autoencoder (AE), convolutional neural networks (CNN), recurrent neural networks (RNN), generative  ...  In particular, in the scientific literature, we can find many applications of ML to solve problems related to the processing of radar signals, e.g., for the recognition and classification of radar emitters  ... 
doi:10.3389/frsip.2021.664232 fatcat:ekjgx65rhrgxdciw2zhb5bqmqq

Intra-pulse Modulation Radar Signal Recognition Based on CLDN Network

Shunjun Wei, Qizhe Qu, Hao Su, Mou Wang, Jun Shi, Xiaojun Hao
2019 IET radar, sonar & navigation  
In this study, a novel network combined a shallow convolution neural network (CNN), long short-term memory (LSTM) network and deep neural network (DNN) is proposed to recognise six types of radar signals  ...  Automatic modulation classification of radar signals, which plays a significant role in both civilian and military applications, is researched in this study through a deep learning network.  ...  Also, the small rectangle represents a layer of neural network with learnable parameters.  ... 
doi:10.1049/iet-rsn.2019.0436 fatcat:mwxovp65dfdtnjfxje7plojxni

Front Matter: Volume 10646

Ivan Kadar
2018 Signal Processing, Sensor/Information Fusion, and Target Recognition XXVII  
These two-number sets start with 00, 01, 02, 03, 04,  ...  Architectures to incorporate temporal processing in include Recurrent Neural Networks (RNN) and Long Short Term (memory) Networks (LSTM).  ...  Neural Networks) From O.  ... 
doi:10.1117/12.2500434 fatcat:wfvvakrbsrfrbiiglzdvnp34o4

Table of Contents

2021 IEEE Transactions on Signal Processing  
White Balanced Neural Architecture Search and Its Application in Specific Emitter Identification . . . . . . . . . . . . . . . . . . . . . . . . . . . (Contents Continued from Page xvii) D. Lahat, Y.  ...  Vucetic RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection . . . . .K. Pratik, B. D. Rao, and M.  ... 
doi:10.1109/tsp.2021.3136800 fatcat:zhf46mb3rbdlnnh3u2xizgxof4
« Previous Showing results 1 — 15 out of 109 results