An Efficient Radio Frequency Interference (RFI) Recognition and Characterization Using End-to-End Transfer Learning

Ujan, Sahar; Navidi, Néda; Landry, René

doi:10.3390/app10196885

Cited by 22 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [118] study a problem of recognizing radio frequency interference type and its characteristics, i.e., modulation class. They first compute scalograms, i.e., a visual representation of a waveform, for collected signal data, then feed them into a CNN-based classifier.…”

Section: B Modulation Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning for Future Wireless Networks: A Comprehensive Survey

Nguyen,

Van Huynh,

Chu

et al. 2021

Preprint

View full text Add to dashboard Cite

With outstanding features, Machine Learning (ML) has been the backbone of numerous applications in wireless networks. However, the conventional ML approaches have been facing many challenges in practical implementation, such as the lack of labeled data, the constantly changing wireless environments, the long training process, and the limited capacity of wireless devices. These challenges, if not addressed, will impede the effectiveness and applicability of ML in future wireless networks. To address these problems, Transfer Learning (TL) has recently emerged to be a very promising solution. The core idea of TL is to leverage and synthesize distilled knowledge from similar tasks as well as from valuable experiences accumulated from the past to facilitate the learning of new problems. Doing so, TL techniques can reduce the dependence on labeled data, improve the learning speed, and enhance the ML methods' robustness to different wireless environments. This article aims to provide a comprehensive survey on applications of TL in wireless networks. Particularly, we first provide an overview of TL including formal definitions, classification, and various types of TL techniques. We then discuss diverse TL approaches proposed to address emerging issues in wireless networks. The issues include spectrum management, localization, signal recognition, security, human activity recognition and caching, which are all important to nextgeneration networks such as 5G and beyond. Finally, we highlight important challenges, open issues, and future research directions of TL in future wireless networks.

show abstract

Section: B Modulation Recognitionmentioning

confidence: 99%

“…A part of the pre-trained model CNN Inductive [111] A part of the pre-trained model CNN Inductive [116] The pre-trained model CNN Inductive [114] A part of the pre-trained model CNN Inductive [118] A part of the pre-trained model CNN Transductive [117] Modulation Recognition…”

Section: Signal Classificationmentioning

confidence: 99%

Transfer Learning for Future Wireless Networks: A Comprehensive Survey

Nguyen,

Van Huynh,

Chu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Prior to this study, several protection methods for Satcom communication have been researched. Artificial intelligence techniques is an emerging topic for RFI detection and characterization [18]. Research [1] extracts different features from the input signal and utilizes them as the input for machine learning (ML) and multi-layer perceptron (MLP) for RFI recognition and automatic classification.…”

Section: Literature Reviewmentioning

confidence: 99%

Multiple Narrowband Interferences Characterization, Detection and Mitigation Using Simplified Welch Algorithm and Notch Filtering

et al. 2021

View full text Add to dashboard Cite

By increasing the demand for radio frequency (RF) and access of hackers and spoofers to low price hardware and software defined radios (SDR), radio frequency interference (RFI) became a more frequent and serious problem. In order to increase the security of satellite communication (Satcom) and guarantee the quality of service (QoS) of end users, it is crucial to detect the RFI in the desired bandwidth and protect the receiver with a proper mitigation mechanism. Digital narrowband signals are so sensitive into the interference and because of their special power spectrum shape, it is hard to detect and eliminate the RFI from their bandwidth. Thus, a proper detector requires a high precision and smooth estimation of input signal power spectral density (PSD). By utilizing the presented power spectrum by the simplified Welch method, this article proposes a solid and effective algorithm that can find all necessary interference parameters in the frequency domain while targeting practical implantation for the embedded system with minimum complexity. The proposed detector can detect several multi narrowband interferences and estimate their center frequency, bandwidth, power, start, and end of each interference individually. To remove multiple interferences, a chain of several infinite impulse response (IIR) notch filters with multiplexers is proposed. To minimize damage to the original signal, the bandwidth of each notch is adjusted in a way that maximizes the received signal to noise ratio (SNR) by the receiver. Multiple carrier wave interferences (MCWI) is utilized as a jamming attack to the Digital Video Broadcasting-Satellite-Second Generation (DVB-S2) receiver and performance of a new detector and mitigation system is investigated and validated in both simulation and practical tests. Based on the obtained results, the proposed detector can detect a weak power interference down to −25 dB and track a hopping frequency interference with center frequency variation speed up to 3 kHz. Bit error ratio (BER) performance shows 3 dB improvement by utilizing new adaptive mitigation scenario compared to non-adaptive one. Finally, the protected DVB-S2 can receive the data with SNR close to the normal situation while it is under the attack of the MCWI jammer.

show abstract

“…The radio frequency interference (RFI) dataset was generated by authors of paper [146]. The dataset was created by combining the signal of interest (SOI) with three popular jammers: continuous-wave interference (CWI), multi-continuous-wave interference (MCWI) and chirp interference (CI).…”

Section: B Radio Frequency Interference Datasetmentioning

confidence: 99%

“…The receiver used was a MegaBee modem. Details of their dataset generation can be found in [146]. Fig.…”

Section: B Radio Frequency Interference Datasetmentioning

confidence: 99%

Interference Suppression Using Deep Learning: Current Approaches and Open Challenges

Oyedare,

Shah,

Jakubisin

et al. 2021

Preprint

View full text Add to dashboard Cite

In light of the finite nature of the wireless spectrum and the increasing demand for spectrum use arising from recent technological breakthroughs in wireless communication, the problem of interference continues to persist. Despite recent advancements in resolving interference issues, interference still presents a difficult challenge to effective usage of the spectrum. This is partly due to the rise in the use of license-free and managed shared bands for Wi-Fi, long term evolution (LTE) unlicensed (LTE-U), LTE licensed assisted access (LAA), 5G NR, and other opportunistic spectrum access solutions. As a result of this, the need for efficient spectrum usage schemes that are robust against interference has never been more important. In the past, most solutions to interference have addressed the problem by using avoidance techniques as well as non-AI mitigation approaches (for example, adaptive filters). The key downside to non-AI techniques is the need for domain expertise in the extraction or exploitation of signal features such as cyclostationarity, bandwidth and modulation of the interfering signals. More recently, researchers have successfully explored AI/ML enabled physical (PHY) layer techniques, especially deep learning which reduces or compensates for the interfering signal instead of simply avoiding it. The underlying idea of ML based approaches is to learn the interference or the interference characteristics from the data, thereby sidelining the need for domain expertise in suppressing the interference. In this paper, we review a wide range of techniques that have used deep learning to suppress interference. We provide comparison and guidelines for many different types of deep learning techniques in interference suppression. In addition, we highlight challenges and potential future research directions for the successful adoption of deep learning in interference suppression.

show abstract

An Efficient Radio Frequency Interference (RFI) Recognition and Characterization Using End-to-End Transfer Learning

Cited by 22 publications

References 21 publications

Transfer Learning for Future Wireless Networks: A Comprehensive Survey

Transfer Learning for Future Wireless Networks: A Comprehensive Survey

Multiple Narrowband Interferences Characterization, Detection and Mitigation Using Simplified Welch Algorithm and Notch Filtering

Interference Suppression Using Deep Learning: Current Approaches and Open Challenges

Contact Info

Product

Resources

About