Marine Distributed Radar Signal Identification and Classification Based on Deep Learning

Distributed radar is applied extensively in marine environment monitoring. In the early days, the radar signals are identified inefficiently by operators. It is promising to replace manual radar signal identification with machine learning technique. However, the existing deep learning neural networks for radar signal identification consume a long time, owing to autonomous learning. Besides, the training of such networks requires lots of reliable time-frequency features of radar signals. This paper mainly analyzes the identification and classification of marine distributed radar signals with an improved deep neural network. Firstly, the time frequency features were extracted from signals based on short-time Fourier transform (STFT) theory. Then, a target detection algorithm was proposed, which weighs and fuses the heterogenous marine distributed radar signals, and four methods were provided for weight calculation. After that, the frequency-domain priori model feature assistive training was introduced to train the traditional deep convolutional neural network (DCNN), producing a CNN with feature splicing operation. The features of time- and frequency-domain signals were combined, laying the basis for radar signal classification. Our model was proved effective through experiments.

Download Full-text

A Multipulse Radar Signal Recognition Approach via HRF-Net Deep Learning Models

Computational Intelligence and Neuroscience ◽

10.1155/2021/9955130 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Ji Li ◽

Huiqiang Zhang ◽

Jianping Ou ◽

Wei Wang

Keyword(s):

Deep Learning ◽

Feature Fusion ◽

Signal To Noise Ratio ◽

Software Radio ◽

Radar Signal ◽

Time Frequency ◽

Recognition Result ◽

Electronic Countermeasure ◽

Radar Signals ◽

Deep Learning Model

In the field of electronic countermeasure, the recognition of radar signals is extremely important. This paper uses GNU Radio and Universal Software Radio Peripherals to generate 10 classes of close-to-real multipulse radar signals, namely, Barker, Chaotic, EQFM, Frank, FSK, LFM, LOFM, OFDM, P1, and P2. In order to obtain the time-frequency image (TFI) of the multipulse radar signal, the signal is Choi–Williams distribution (CWD) transformed. Aiming at the features of the multipulse radar signal TFI, we designed a distinguishing feature fusion extraction module (DFFE) and proposed a new HRF-Net deep learning model based on this module. The model has relatively few parameters and calculations. The experiments were carried out at the signal-to-noise ratio (SNR) of −14 ∼ 4 dB. In the case of −6 dB, the recognition result of HRF-Net reached 99.583% and the recognition result of the network still reached 97.500% under −14 dB. Compared with other methods, HRF-Nets have relatively better generalization and robustness.

Download Full-text

Estimating the Instantaneous Frequency of Linear and Nonlinear Frequency Modulated Radar Signals—A Comparative Study

Sensors ◽

10.3390/s21082840 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2840

Author(s):

Hubert Milczarek ◽

Czesław Leśnik ◽

Igor Djurović ◽

Adam Kawalec

Keyword(s):

Instantaneous Frequency ◽

Early Warning Systems ◽

Vital Role ◽

Estimation Methods ◽

Radar Signal ◽

Nonlinear Frequency ◽

Modulation Recognition ◽

Electronic Warfare ◽

Time Frequency ◽

Radar Signals

Automatic modulation recognition plays a vital role in electronic warfare. Modern electronic intelligence and electronic support measures systems are able to automatically distinguish the modulation type of an intercepted radar signal by means of real-time intra-pulse analysis. This extra information can facilitate deinterleaving process as well as be utilized in early warning systems or give better insight into the performance of hostile radars. Existing modulation recognition algorithms usually extract signal features from one of the rudimentary waveform characteristics, namely instantaneous frequency (IF). Currently, there are a small number of studies concerning IF estimation methods, specifically for radar signals, whereas estimator accuracy may adversely affect the performance of the whole classification process. In this paper, five popular methods of evaluating the IF–law of frequency modulated radar signals are compared. The considered algorithms incorporate the two most prevalent estimation techniques, i.e., phase finite differences and time-frequency representations. The novel approach based on the generalized quasi-maximum likelihood (QML) method is also proposed. The results of simulation experiments show that the proposed QML estimator is significantly more accurate than the other considered techniques. Furthermore, for the first time in the publicly available literature, multipath influence on IF estimates has been investigated.

Download Full-text

Spatiotemporal Monitoring and Evaluation Method for Sand-Filling of Immersed Tube Tunnel Foundation

Applied Sciences ◽

10.3390/app11031084 ◽

2021 ◽

Vol 11 (3) ◽

pp. 1084

Author(s):

Peng Wu ◽

Ailan Che

Keyword(s):

Neural Network ◽

Elastic Wave ◽

Frequency Domain ◽

Bp Neural Network ◽

Evaluation Method ◽

Monitoring And Evaluation ◽

Strong Nonlinearity ◽

Filling Process ◽

Time Frequency ◽

Feature Parameters

The sand-filling method has been widely used in immersed tube tunnel engineering. However, for the problem of monitoring during the sand-filling process, the traditional methods can be inadequate for evaluating the state of sand deposits in real-time. Based on the high efficiency of elastic wave monitoring, and the superiority of the backpropagation (BP) neural network on solving nonlinear problems, a spatiotemporal monitoring and evaluation method is proposed for the filling performance of foundation cushion. Elastic wave data were collected during the sand-filling process, and the waveform, frequency spectrum, and time–frequency features were analysed. The feature parameters of the elastic wave were characterized by the time domain, frequency domain, and time-frequency domain. By analysing the changes of feature parameters with the sand-filling process, the feature parameters exhibited dynamic and strong nonlinearity. The data of elastic wave feature parameters and the corresponding sand-filling state were trained to establish the evaluation model using the BP neural network. The accuracy of the trained network model reached 93%. The side holes and middle holes were classified and analysed, revealing the characteristics of the dynamic expansion of the sand deposit along the diffusion radius. The evaluation results are consistent with the pressure gauge monitoring data, indicating the effectiveness of the evaluation and monitoring model for the spatiotemporal performance of sand deposits. For the sand-filling and grouting engineering, the machine-learning method could offer a better solution for spatiotemporal monitoring and evaluation in a complex environment.

Download Full-text

Compression of Phase-Only Holograms with JPEG Standard and Deep Learning

Applied Sciences ◽

10.3390/app8081258 ◽

2018 ◽

Vol 8 (8) ◽

pp. 1258 ◽

Cited By ~ 16

Author(s):

Shuming Jiao ◽

Zhi Jin ◽

Chenliang Chang ◽

Changyuan Zhou ◽

Wenbin Zou ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

High Frequency ◽

Critical Issue ◽

Compression Process ◽

Compression Scheme ◽

Quality Degradation ◽

Digital Format ◽

Enormous Amount ◽

Frequency Features

It is a critical issue to reduce the enormous amount of data in the processing, storage and transmission of a hologram in digital format. In photograph compression, the JPEG standard is commonly supported by almost every system and device. It will be favorable if JPEG standard is applicable to hologram compression, with advantages of universal compatibility. However, the reconstructed image from a JPEG compressed hologram suffers from severe quality degradation since some high frequency features in the hologram will be lost during the compression process. In this work, we employ a deep convolutional neural network to reduce the artifacts in a JPEG compressed hologram. Simulation and experimental results reveal that our proposed “JPEG + deep learning” hologram compression scheme can achieve satisfactory reconstruction results for a computer-generated phase-only hologram after compression.

Download Full-text

Recurrent Neural Networks for Narrowband Signal Detection in the Time-Frequency Domain

Symposium - International Astronomical Union ◽

10.1017/s0074180900193751 ◽

2004 ◽

Vol 213 ◽

pp. 483-486

Author(s):

David Brodrick ◽

Douglas Taylor ◽

Joachim Diederich

Keyword(s):

Neural Network ◽

Neural Networks ◽

Signal Detection ◽

Frequency Domain ◽

Recurrent Neural Networks ◽

Radio Frequency Interference ◽

Recurrent Networks ◽

Time Frequency ◽

Narrowband Signal ◽

Radio Signals

A recurrent neural network was trained to detect the time-frequency domain signature of narrowband radio signals against a background of astronomical noise. The objective was to investigate the use of recurrent networks for signal detection in the Search for Extra-Terrestrial Intelligence, though the problem is closely analogous to the detection of some classes of Radio Frequency Interference in radio astronomy.

Download Full-text

Fall Detection Based on Sequential Modeling of Radar Signal Time-Frequency Features

2013 IEEE International Conference on Healthcare Informatics ◽

10.1109/ichi.2013.27 ◽

2013 ◽

Cited By ~ 25

Author(s):

Meng Wu ◽

Xiaoxiao Dai ◽

Yimin D. Zhang ◽

Bradley Davidson ◽

Moeness G. Amin ◽

...

Keyword(s):

Fall Detection ◽

Radar Signal ◽

Time Frequency ◽

Sequential Modeling ◽

Frequency Features ◽

Signal Time

Download Full-text

Arrhythmia detection based on time–frequency features of heart rate variability and back-propagation neural network

Iran Journal of Computer Science ◽

10.1007/s42044-019-00042-1 ◽

2019 ◽

Vol 2 (4) ◽

pp. 245-257 ◽

Cited By ~ 2

Author(s):

Ram Sewak Singh ◽

Barjinder Singh Saini ◽

Ramesh Kumar Sunkaria

Keyword(s):

Neural Network ◽

Heart Rate ◽

Heart Rate Variability ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Arrhythmia Detection ◽

Time Frequency ◽

Frequency Features

Download Full-text

Time-Frequency Domain Deep Convolutional Neural Network for the Classification of Focal and Non-Focal EEG Signals

IEEE Sensors Journal ◽

10.1109/jsen.2019.2956072 ◽

2020 ◽

Vol 20 (6) ◽

pp. 3078-3086 ◽

Cited By ~ 11

Author(s):

Srirangan Madhavan ◽

Rajesh Kumar Tripathy ◽

Ram Bilas Pachori

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Frequency Domain ◽

Deep Convolutional Neural Network ◽

Eeg Signals ◽

Time Frequency

Download Full-text

Recognition of Emotions Using Multichannel EEG Data and DBN-GC-Based Ensemble Deep Learning Framework

Computational Intelligence and Neuroscience ◽

10.1155/2018/9750904 ◽

2018 ◽

Vol 2018 ◽

pp. 1-11 ◽

Cited By ~ 15

Author(s):

Hao Chao ◽

Huilai Zhi ◽

Liang Dong ◽

Yongli Liu

Keyword(s):

Deep Learning ◽

Frequency Domain ◽

Time Domain ◽

Recognition Task ◽

Frequency Characteristics ◽

Time Frequency ◽

Learning Framework ◽

Valence States ◽

Correlation Information ◽

Multiple Domains

Fusing multichannel neurophysiological signals to recognize human emotion states becomes increasingly attractive. The conventional methods ignore the complementarity between time domain characteristics, frequency domain characteristics, and time-frequency characteristics of electroencephalogram (EEG) signals and cannot fully capture the correlation information between different channels. In this paper, an integrated deep learning framework based on improved deep belief networks with glia chains (DBN-GCs) is proposed. In the framework, the member DBN-GCs are employed for extracting intermediate representations of EEG raw features from multiple domains separately, as well as mining interchannel correlation information by glia chains. Then, the higher level features describing time domain characteristics, frequency domain characteristics, and time-frequency characteristics are fused by a discriminative restricted Boltzmann machine (RBM) to implement emotion recognition task. Experiments conducted on the DEAP benchmarking dataset achieve averaged accuracy of 75.92% and 76.83% for arousal and valence states classification, respectively. The results show that the proposed framework outperforms most of the above deep classifiers. Thus, potential of the proposed framework is demonstrated.

Download Full-text