A DNN Autoencoder for Automotive Radar Interference Mitigation

Chen, Shengyi; Taghia, Jalal; Fei, Tai; Kühnau, Uwe; Pohl, Nils; Martin, Rainer

doi:10.1109/icassp39728.2021.9413619

Cited by 13 publications

(8 citation statements)

References 17 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the supervised learning techniques, CNN-based suppression techniques were discussed in [71]- [74], deep neural network (DNN) based techniques were discussed in [33], [75]- [85], and recurrent neural network (RNN) based techniques were investigated in [86]- [90]. For the unsupervised learning techniques, autoencoder-based suppression techniques were discussed in [91]- [98].…”

Section: Figure 2: Interference Suppression Techniquesmentioning

confidence: 99%

“…Further, Chen et al [98] investigated an approach that combined an autoencoder network with an interference detection filter to suppress automotive radar interference. The authors found that using a gated convolution, the encoder network can learn the pattern of the residual signal free of interference.…”

Section: Contributions For Interference Suppression Using Autoencodersmentioning

confidence: 99%

“…Fig. 9, taken from [98], shows a plot of the SINR (in dB) against the percentage of discarded samples that compares different interference mitigation techniques such as zeroing, auto-regressive (AR) models, autoencoders and the original signals. We see that at 15% (or greater) of discarded samples, the SINR of both AR and zeroing methods decreased while the autoencoder has a more robust performance.…”

Section: Contributions For Interference Suppression Using Autoencodersmentioning

confidence: 99%

See 2 more Smart Citations

Interference Suppression Using Deep Learning: Current Approaches and Open Challenges

2022

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 as well as 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 mitigation approaches based on expert systems. More recently, researchers have successfully explored artificial intelligence/machine learning enabled physical layer techniques, especially deep learning which reduces or compensates for the interfering signal instead of simply avoiding it. In this paper, we address the knowledge gap in literature with respect to the state-of-the-art in deep learning-based interference suppression. Specifically, we review a wide range of techniques that have used deep learning to suppress interference by learning interference characteristics directly from data, rather than relying on expert systems. We provide a thorough technical discussion of the prominent deep learning algorithms that have been proposed in the literature and provide comparison and guidelines regarding their successful implementation in this application. In addition, we highlight challenges and potential future research directions for the successful adoption of deep learning in this critical field.

show abstract

Section: Figure 2: Interference Suppression Techniquesmentioning

confidence: 99%

Section: Contributions For Interference Suppression Using Autoencodersmentioning

confidence: 99%

Section: Contributions For Interference Suppression Using Autoencodersmentioning

confidence: 99%

See 1 more Smart Citation

Interference Suppression Using Deep Learning: Current Approaches and Open Challenges

2022

View full text Add to dashboard Cite

show abstract

“…[91]- [98] • CNN-based AE is used to de-noise interfered range-Doppler (RD) images [92]. • Autoencoder is used to learn the distribution of the interference component so that it can be suppressed.…”

Section: Autoencoders (Denoising Ae and Cnn-based Ae)mentioning

confidence: 99%

“…• Signal is reconstructed without any knowledge about symbol structure and channel response. • AE is combined with an interference detection filter to suppress automotive radar interference in [98] • Using real-world data measurement further improves the performance of AE methods. • DAEs perform well when the interfering power is larger than the amplitude of the desired signal.…”

Section: Autoencoders (Denoising Ae and Cnn-based Ae)mentioning

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

A Two-Stage DNN Model With Mask-Gated Convolution for Automotive Radar Interference Detection and Mitigation

Chen¹,

Taghia

Kühnau

et al. 2022

IEEE Sensors J.

View full text Add to dashboard Cite

A DNN Autoencoder for Automotive Radar Interference Mitigation

Cited by 13 publications

References 17 publications

Interference Suppression Using Deep Learning: Current Approaches and Open Challenges

Interference Suppression Using Deep Learning: Current Approaches and Open Challenges

Interference Suppression Using Deep Learning: Current Approaches and Open Challenges

A Two-Stage DNN Model With Mask-Gated Convolution for Automotive Radar Interference Detection and Mitigation

Contact Info

Product

Resources

About