Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection

Zhang, Xiwen; Seyfi, Tolunay; Ju, Shengtai; Ramjee, Sharan; Gamal, Aly El; Eldar, Yonina C.

doi:10.1109/spawc.2019.8815481

Cited by 44 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RF signal classification with DL has mostly been studied in the context of either Automatic Modulation Classification (AMC) [13], [14], [18] or Wireless Interference Identification (WII) [6]- [8]. These are essentially the same tasks with the difference being the signals involved.…”

Section: Literature Reviewmentioning

confidence: 99%

“…For WII, frequency domain representations have performed better since the frequency components of a signal remain more distinctive even under lower SNR. WII can appear as different use cases, such as classifying different UAVs [4], [9], [11], [20], detecting/classifying different Radar Waveforms [2], [21], identifying specific technologies in the ISM band [8], securing Global Navigation Satellite Systems (GNSS) signals [22], and more. Like time-domain representations, frequencydomain representations can also be kept as a vector of values (such as DFT coefficients) used in [4] or further transforms can be applied to make a PSD image, or STFT image (also known as a spectrogram), used in [9], [11] and others.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Radio Frequency Signal Classification with Hybrid Images

Elyousseph¹,

Altamimi²

2021

Preprint

View full text Add to dashboard Cite

In recent years, Deep Learning (DL) has been successfully applied to detect and classify Radio Frequency (RF) Signals. A DL approach is especially useful since it identifies the presence of a signal without needing full protocol information, and can also detect and/or classify non-communication waveforms, such as radar signals. In this work, we focus on the different pre-processing steps that can be used on the input training data, and test the results on a fixed DL architecture. While previous works have mostly focused exclusively on either time-domain or frequency domain approaches, we propose a hybrid image that takes advantage of both time and frequency domain information, and tackles the classification as a Computer Vision problem. Our initial results point out limitations to classical pre-processing approaches while also showing that it's possible to build a classifier that can leverage the strengths of multiple signal representations.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Deep Learning Radio Frequency Signal Classification with Hybrid Images

Elyousseph¹,

Altamimi²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This method exploits realtime extraction of envelope and model-aided spectral features, specifically designed considering the physical properties of the signals captured with commercial off-the-shelf (COTS) hardware. [7] studies the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies, i.e., Bluetooth, Zigbee, and WiFi. Four different deep neural network architectures, i.e., CNN, ResNet, CLDNN, and LSTM are used as the classifier, the research demonstrated the generality of the effectiveness of deep learning at the considered task.…”

Section: Introductionmentioning

confidence: 99%

Time-Frequency Analysis based Deep Interference Classification for Frequency Hopping System

Xu¹,

Ren²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

In a hostile environment, interference identification plays an important role in protecting the authorized communication system and avoiding its performance degradation. In this paper, the interference identification problem for the frequency hopping communication system is discussed. Considering presence of multiple and compound interference in the frequency hopping system, in order to fully extracted effective features of the interferences from the received signals, a composite time-frequency analysis method based on both the linear and bilinear transform is proposed. The time-frequency spectrograms obtained from the time-frequency analysis are constructed as matching pairs and input into the deep neural network for identification. In particular, the Siamese neural network is adopted as the classifier to perform the interference identification. That is, the paired spectrograms are input into the two subnetworks of the Siamese neural network to extract the features of the paired spectrograms. The Siamese neural network is trained and tested by calculating the gap between the generated features, and the interference type identification is realized by the trained Siamese neural network. The simulation results confirm that the proposed algorithm can obtain higher identification accuracy than both traditional single time-frequency representation based approach and the AlexNet transfer learning or convolutional neural network based methods.

show abstract

“…The dataset contains received signals corresponding to 15 different channels of WiFi, Bluetooth, and ZigBee. Efficient training algorithms for this problem were investigated in [6] through training with only a subset of frequency bands, a subset of input vector samples, and a subset of SNR values.…”

Section: Introductionmentioning

confidence: 99%

“…We use the aforementioned datasets for modulation classification and channel identification to validate the proposed methods and obtained insights. We first start by improving the preliminary results on training SNR selection of [4] and [6], obtained through training with only the test SNR value. We then show that if we can only estimate a test SNR range, it is better to train with optimistic estimates.…”

mentioning

confidence: 99%

Efficient Training of Deep Classifiers for Wireless Source Identification Using Test SNR Estimates

Wang

Zhang

et al. 2020

IEEE Wireless Commun. Lett.

Self Cite

View full text Add to dashboard Cite

We investigate the potential of training time reduction for deep learning algorithms that process received wireless signals, if an accurate test Signal to Noise Ratio (SNR) estimate is available. Our focus is on two tasks that facilitate source identification: 1-Identifying the modulation type, 2-Identifying the wireless technology and channel index in the 2.4 GHZ ISM band. For benchmarking, we rely on a fast growing recent literature on testing deep learning algorithms against two well-known synthetic datasets. We first demonstrate that using training data corresponding only to the test SNR value leads to dramatic reductions in training time -that can reach up to 35x -while incurring a small loss in average test accuracy, as it improves the accuracy for low test SNR values. Further, we show that an erroneous test SNR estimate with a small positive offset is better for training than another having the same error magnitude with a negative offset. Secondly, we introduce a greedy training SNR Boosting algorithm that leads to uniform improvement in test accuracy across all tested SNR values, while using only a small subset of training SNR values at each test SNR. Finally, we discuss, with empirical evidence, the potential of bootstrap aggregating (Bagging) based on training SNR values to improve generalization at low test SNR values with scarcity of training data.

show abstract

Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection

Cited by 44 publications

References 7 publications

Deep Learning Radio Frequency Signal Classification with Hybrid Images

Deep Learning Radio Frequency Signal Classification with Hybrid Images

Time-Frequency Analysis based Deep Interference Classification for Frequency Hopping System

Efficient Training of Deep Classifiers for Wireless Source Identification Using Test SNR Estimates

Contact Info

Product

Resources

About