Automatic LPI Radar Waveform Recognition Using CNN
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Detecting and classifying the modulation scheme of the intercepted noisy low probability of intercept (LPI) radar signals in real time is a necessary survival technique required in the electronic warfare systems. Therefore, LPI radar waveform recognition technique (LWRT) has gained an increasing attention recently. In this paper, we propose a convolutional neural network (CNN)-based LWRT, where the input and hyperparameters of the CNN, such as the input size, number of filters, filter size, and number of neurons are designed based on various signal conditions to guarantee the maximum classification performance. In addition, we propose a sample averaging technique to efficiently reduce the large computational cost required when the intercept receiver needs to process a large amount of signal samples to improve the detection sensitivity. We demonstrate the performance of the proposed LWRT with numerous Monte Carlo simulations based on the simulation conditions used in the recent LWRTs introduced in the literature. It is testified that the proposed LWRT offers significant improvement, such as robustness to noise and recognition accuracy, over the recent LWRTs.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“For the determination of the hyper-parameters in the pooling layers, we use the max pooling [26] with 2×2 filter size, stride size 2, and no zero-padding, which are the common choice in [23] and [24].”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 10×
“, from the 13th row to the 22nd row) of the Table 2, we present the test results for various filter sizes of the first and the second convolutional layers, where it is assumed that the filter size of the first layer is larger or equal to that of the second layer [11], [25].”
BackgroundMethodInfluential(2014) · Cited by 33,419
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“This technique has robustness against the CFEE, since the effect of CFEE on the TFI is merely an offset in the object image location and the CNN is generally robust to the changes in the image topology [10].”
MethodMulti-column deep neural networks for image classification
Ciresan, D., Meier, U., & Schmidhuber, J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248110 · Cited by 3,720
Best practices for convolutional neural networks applied to visual document analysis
Simard, P. Y., Steinkraus, D., & Platt, J. C. (2005) · Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. · doi:10.1109/icdar.2003.1227801 · Cited by 2,741 · cited 2×
“For the determination of the hyper-parameters in the pooling layers, we use the max pooling [26] with 2×2 filter size, stride size 2, and no zero-padding, which are the common choice in [23] and [24].”
MethodConvolutional networks and applications in vision
LeCun, Y., Kavukcuoglu, K., & Farabet, C. (2010) · Proceedings of 2010 IEEE International Symposium on Circuits and Systems · doi:10.1109/iscas.2010.5537907 · Cited by 2,213 · cited 1×
“In general, CNN shows a superb performance in image classification problems such as handwriting recognition and various object recognition including human faces, license plates, hand gesture, logos, and texts [22].”
BackgroundSurvey: interpolation methods in medical image processing
Lehmann, T. M., Gonner, C., & Spitzer, K. (1999) · IEEE Transactions on Medical Imaging · doi:10.1109/42.816070 · Cited by 1,340
Improved time-frequency representation of multicomponent signals using exponential kernels
Choi, H.-I., & Williams, W. J. (1989) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/assp.1989.28057 · Cited by 1,299 · cited 1×
“of cohen’s class [13] with an exponential distribution (ED) kernel [17] as”
BackgroundEfficient Learning of Sparse Representations with an Energy-Based Model
Ranzato, M., Poultney, C., Chopra, S., & LeCun, Y. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0147 · Cited by 1,106 · cited 4×
“, from the 13th row to the 22nd row) of the Table 2, we present the test results for various filter sizes of the first and the second convolutional layers, where it is assumed that the filter size of the first layer is larger or equal to that of the second layer [11], [25].”
BackgroundMethodInfluentialReview on Methods to Fix Number of Hidden Neurons in Neural Networks
Sheela, K. G., & Deepa, S. N. (2013) · Mathematical Problems in Engineering · doi:10.1155/2013/425740 · Cited by 941
Comparison of Interpolating Methods for Image Resampling
Parker, J. A., Kenyon, R. V., & Troxel, D. E. (1983) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.1983.4307610 · Cited by 829 · cited 1×
“In the proposed LWRT, we use P = Q = 2048 for the rectangular windowWP(τ ) andWQ(μ) so that the produced CWD-TFI has 2048×2048 pixels, and we resize the TFI into 128×128 pixels using the nearestneighbor interpolation (NNI) technique [20].”
MethodDetecting and Classifying Low Probability of Intercept Radar
Pace, P. E. (2009) · Cited by 498
Some features of time-frequency representations of multicomponent signals
Flandrin, P. (2005) · ICASSP '84. IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1984.1172741 · Cited by 239 · cited 1×
“Since the CWD is generated from the AF using the kernel function and the 2-dimensional (2D) Fourier transform, the CWD of the intercepted signal y[k] comprised of multiple frequency components has high power spectrum intensity near the center frequency and some power spectrum components away from the center frequency…”
MethodAutomatic Radar Waveform Recognition
Lundn, J., & Koivunen, V. (2007) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2007.897055 · Cited by 238 · cited 10×
“The signal features and the TFI features are then used as an input to an ANN based on MLP [7] or based on RNN [8].”
BackgroundMethodInfluentialConvolutional Neural Networks for Automatic Cognitive Radio Waveform Recognition
Zhang, M., Diao, M., & Guo, L. (2017) · IEEE Access · doi:10.1109/access.2017.2716191 · Cited by 232 · cited 10×
“On the other hand, for the classification techniques, there are hierarchical decision tree (HDT) [3], [9] and artificial neural networks (ANN) based on multilayer perceptron (MLP) [2], [5], [7], recurrent neural networks (RNN) [8], and convolutional neural networks (CNN) [4], [6].”
BackgroundMethodResultInfluentialAutomatic Intrapulse Modulation Classification of Advanced LPI Radar Waveforms
Kishore, T. R., & Rao, K. D. (2017) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2017.2667142 · Cited by 214 · cited 12×
“On the other hand, for the classification techniques, there are hierarchical decision tree (HDT) [3], [9] and artificial neural networks (ANN) based on multilayer perceptron (MLP) [2], [5], [7], recurrent neural networks (RNN) [8], and convolutional neural networks (CNN) [4], [6].”
BackgroundMethodResultInfluentialWang, C., Wang, J., & Zhang, X. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952594 · Cited by 196 · cited 2×
“On the other hand, for the classification techniques, there are hierarchical decision tree (HDT) [3], [9] and artificial neural networks (ANN) based on multilayer perceptron (MLP) [2], [5], [7], recurrent neural networks (RNN) [8], and convolutional neural networks (CNN) [4], [6].”
BackgroundMethodEaves, J. L. (1987) · Principles of Modern Radar · doi:10.1007/978-1-4613-1971-9_1 · Cited by 178
Digital channelized receiver based on time-frequency analysis for signal interception
López-Risueño, G., Grajal, J., & Sanz-Osorio, A. (2005) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2005.1541437 · Cited by 168 · cited 19×
“On the other hand, for the classification techniques, there are hierarchical decision tree (HDT) [3], [9] and artificial neural networks (ANN) based on multilayer perceptron (MLP) [2], [5], [7], recurrent neural networks (RNN) [8], and convolutional neural networks (CNN) [4], [6].”
BackgroundMethodInfluentialLPI Radar Waveform Recognition Based on Time-Frequency Distribution
Ming, Z., Liu, L., & Diao, M. (2016) · Sensors · doi:10.3390/s16101682 · Cited by 140 · cited 10×
“The signal features and the TFI features are then used as an input to an ANN based on MLP [7] or based on RNN [8].”
BackgroundMethodInfluential
Metadata
- Authors
- Kong, S.-H., Kim, M., Hoang, L. M., & Kim, E.
- Venue
- IEEE Access
- Published
- 2018
- Volume
- 6
- Pages
- 4207-4219
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2781731889
- Cited by
- 178
- References
- 22
- FWCI
- 9.90
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.