Convolutional neural networks for radar emitter classification

Cain, Lindsay R.; Clark, J.J.; Pauls, Eric; Ausdenmoore, Ben; Clouse, R.L.; Josue, Ted

doi:10.1109/ccwc.2018.8301627

Cited by 26 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the radar emitter identification task, deep learning models can often achieve the best results. Therefore, in this section, we construct the CNN model [6] and the U-CNN model [7] to compare with our method proposed in this paper. In the two deep learning models, radar pulse description words are used to represent radar signals, and as input to the model, which is the same as the processing of our method, so it is appropriate to compare CNN, U-CNN and our method together.…”

Section: Results Discussionmentioning

confidence: 99%

“…Zhou Z et al [5] developed a novel deep architecture for automatic waveform recognition, which outperformed the existing shallow algorithms and other hand-crafted, feature-based methods. Cain L et al [6] investigated an application of convolutional neural networks (CNN) for rapid and accurate classification of electronic warfare emitters. Sun J et al [7] proposed a deep learning model named as unidimensional convolutional neural network (U-CNN) to classify the encoded high-dimension sequences with big data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Unknown Radar Emitter Identification Method Based on Semi-Supervised and Transfer Learning

et al. 2019

View full text Add to dashboard Cite

Aiming at the current problem that it is difficult to deal with an unknown radar emitter in the radar emitter identification process, we propose an unknown radar emitter identification method based on semi-supervised and transfer learning. Firstly, we construct the support vector machine (SVM) model based on transfer learning, using the information of labeled samples in the source domain to train in the target domain, which can solve the problem that the training data and the testing data do not satisfy the same-distribution hypothesis. Then, we design a semi-supervised co-training algorithm using the information of unlabeled samples to enhance the training effect, which can solve the problem that insufficient labeled data results in inadequate training of the classifier. Finally, we combine the transfer learning method with the semi-supervised learning method for the unknown radar emitter identification task. Simulation experiments show that the proposed method can effectively identify an unknown radar emitter and still maintain high identification accuracy within a certain measurement error range.

show abstract

Section: Results Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Unknown Radar Emitter Identification Method Based on Semi-Supervised and Transfer Learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Apiculture, Medical science and others similar type of science field facing the lack of automated analysis tool base on experienced data where, these types of institutions are yielding the huge data on daily basis. Seeing the potential medical field requirement, several studies are being done using deep transfer learning [3] [4][14] algorithm. There the several pre-trained models existed at present like that VGG, Mobile Net, Inception and Mask R-CNN etc.…”

Section: A Related Workmentioning

confidence: 99%

“…In supervised machine learning algorithm, the learning is based on input data using labeled example to predict future problems [19], Where as in unsupervised learning algorithm the machine learns from the input data that is non-classified and without labeling to train [19]. Deep learning is several levels of representation by making of hierarchy of features, in which higher and lower levels help mutually to define higher levels features [4]. The DNN is extended form of traditional ANN, in which complex and non-linear, real-world problems resolve by increasing hidden layers between input and output layer.…”

Section: Introductionmentioning

confidence: 99%

Honey Bee Bearing Pollen and Non-Pollen Image Classification, VGG16 Transfer Learning Method using Different Optimizing Functions.

Kandpal*,

Mehta,

Sharma

2019

IJITEE

View full text Add to dashboard Cite

The deep leaning has been the prominent and interesting field for researchers for last few years. There are several studies are being done on real problems in several streams of Science. In the deep leaning there are huge resources and labeled dataset are required to train the model. In convolutional neural network (CNN) training with random weights take a considerable amount of time to optimize the weights. To minimize efforts and other resources and deal with large, challenging dataset; which generally very complexed to use in the conventional training methods. New concept of deep learning has been evolved and emerge as prominent methods called transfer learning in last few years. In the transfer leaning, pre-trained model VGG16, which had been trained using 1000 different classes of Images. The VGG16 architecture having 16 CCN layers with ReLu activation function. In this study we took the Honey Bee image dataset consists of two type of the images of honey bee, some images are bearing pollen honey bees and remaining are non-bearing pollen honey bees. We got learn the model with dataset and classified problems using three optimization functions: Adaptive Moment Estimation Algorithm (ADAM), Root Mean Square Propagation (RMSprop) and Stochastic gradient descent (SGD). we compared the results, and found that Adaptive Moment Estimation (ADAM) function performed best, and got 91.94 percent Accuracy and 0.2027 losses.

show abstract

“…Furthermore, mapping separable features requires large input dimensions, while our pulses have only a few parameters. In radar signal processing, NNs have been mostly applied to address classification and identification problems [13][14][15]. Recently, Recurrent NNs (RNNs) have been deployed to cluster pulses [16].…”

Section: Introductionmentioning

confidence: 99%

Signal Clustering With Class-Independent Segmentation

Gasperini

Paschali

Hopke

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Radar signals have been dramatically increasing in complexity, limiting the source separation ability of traditional approaches. In this paper we propose a Deep Learning-based clustering method, which encodes concurrent signals into images, and, for the first time, tackles clustering with image segmentation. Novel loss functions are introduced to optimize a Neural Network to separate the input pulses into pure and non-fragmented clusters. Outperforming a variety of baselines, the proposed approach is capable of clustering inputs directly with a Neural Network, in an end-to-end fashion.

show abstract

Convolutional neural networks for radar emitter classification

Cited by 26 publications

References 5 publications

An Unknown Radar Emitter Identification Method Based on Semi-Supervised and Transfer Learning

An Unknown Radar Emitter Identification Method Based on Semi-Supervised and Transfer Learning

Honey Bee Bearing Pollen and Non-Pollen Image Classification, VGG16 Transfer Learning Method using Different Optimizing Functions.

Signal Clustering With Class-Independent Segmentation

Contact Info

Product

Resources

About