Deep Learning for Polar Codes over Flat Fading Channels

Irawan, Ade; Witjaksono, Gunawan; Wibowo, Wahyu Kunto

doi:10.1109/icaiic.2019.8669025

Cited by 15 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the methods, the DIR-Net method with attention-based denoising and attention-based decoding was denoted as “dno_dec”. In order to evaluate the decoder performance, we used the DIR-Net method without denoiser as the comparison, which is denoted as “only_dec”, whereas “only_fc_dec” denotes the fully connected decoder proposed in [ 27 ], which does not contain a denoiser, and “fc_dec” denotes the addition of the attention-based denoiser in our paper to [ 27 ]. To further evaluate the performance of the attention-based denoiser and decoder, we compared it with the residual decoder, which was proposed in [ 29 ], denoted as “res_dec”.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…In order to compare the speed of each decoding technique more comprehensively, we test the denoiser speed, decoder speed, and denoiser-decoder speed of DIR-Net method with different code lengths, including (16, 8), (32, 16), (64, 32), (128, 64), and (256, 128) polar codes. To further evaluate the speed of DIR-Net, it is compared with traditional SC algorithms, BP algorithms, and deep learning-based methods only_fc_dec [ 27 ], FC_Decoder [ 28 ], and res_dec [ 29 ]. The decoding time for each method listed in Table 3 .…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…A deep feed-forward neural network was introduced in [ 26 ] to directly decode the input polar codes. A fully connected network was proposed in [ 27 ] to decode polar-coded short packets over a flat fading channel. Wei et al demonstrated that the neural network could learn the entire coding structure by comparing the three network structures of MLP, CNN, and RNN under the same conditions [ 28 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DIR-Net: Deep Residual Polar Decoding Network Based on Information Refinement

Song

Feng

Wang

2022

Entropy

View full text Add to dashboard Cite

Polar codes are closer to the Shannon limit with lower complexity in coding and decoding. As traditional decoding techniques suffer from high latency and low throughput, with the development of deep learning technology, some deep learning-based decoding methods have been proposed to solve these problems. Usually, the deep neural network is treated as a black box and learns to map the polar codes with noise to the original information code directly. In fact, it is difficult for the network to distinguish between valid and interfering information, which leads to limited BER performance. In this paper, a deep residual network based on information refinement (DIR-NET) is proposed for decoding polar-coded short packets. The proposed method works to fully distinguish the effective and interference information in the codewords, thus obtaining a lower bit error rate. To achieve this goal, we design a two-stage decoding network, including a denoising subnetwork and decoding subnetwork. This structure can further improve the accuracy of the decoding method. Furthermore, we construct the whole network solely on the basis of the attention mechanism. It has a stronger information extraction ability than the traditional neural network structure. Benefiting from cascaded attention modules, information can be filtered and refined step-by-step, thus obtaining a low bit error rate. The simulation results show that DIR-Net outperforms existing decoding methods in terms of BER performance under both AWGN channels and flat fading channels.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DIR-Net: Deep Residual Polar Decoding Network Based on Information Refinement

Song

Feng

Wang

2022

Entropy

View full text Add to dashboard Cite

show abstract

“…In the realm of wireless communication ML has recently been adapted for many uses such as equalization [5], spectrum sensing [6], channel coding [7], signal classification [8], etc. One important use of ML in wireless communication is modulation classification (MC).…”

Section: Introductionmentioning

confidence: 99%

Adversarial Filters for Secure Modulation Classification

Berian¹,

Kory²,

Teku³

et al. 2020

Preprint

View full text Add to dashboard Cite

Modulation Classification (MC) refers to the problem of classifying the modulation class of a wireless signal. In the wireless communications pipeline, MC is the first operation performed on the received signal and is critical for reliable decoding. This paper considers the problem of secure modulation classification, where a transmitter (Alice) wants to maximize MC accuracy at a legitimate receiver (Bob) while minimizing MC accuracy at an eavesdropper (Eve). The contribution of this work is to design novel adversarial learning techniques for secure MC. In particular, we present adversarial filtering based algorithms for secure MC, in which Alice uses a carefully designed adversarial filter to mask the transmitted signal, that can maximize MC accuracy at Bob while minimizing MC accuracy at Eve. We present two filtering based algorithms, namely gradient ascent filter (GAF), and a fast gradient filter method (FGFM), with varying levels of complexity. Our proposed adversarial filtering based approaches significantly outperform additive adversarial perturbations (used in the traditional ML community and other prior works on secure MC) and also have several other desirable properties. In particular, GAF and FGFM algorithms are a) computational efficient (allow fast decoding at Bob), b) power-efficient (do not require excessive transmit power at Alice); and c) SNR efficient (i.e., perform well even at low SNR values at Bob).

show abstract

“…In [11] the authors considered a deep feed-forward neural network for polar codes and investigated its decoding performances with respect to numerous configurations: the number of hidden layers, the number of nodes for each layer, and activation functions. Later, more discussion on the activation function of the neural network for decoding polar codes and decoding under Reighlay fading channels using NND can be found in [12] and [13], respectively. In [14], the authors compared the decoding performance of three types of neural network, i.e., multi-layer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN) with the same parameter magnitude.…”

Section: Introductionmentioning

confidence: 99%

Learning to Denoise and Decode: A Novel Residual Neural Network Decoder for Polar Codes

Cao¹,

Zhu²,

Zhao³

et al. 2019

Preprint

View full text Add to dashboard Cite

Polar codes have been adopted as the control channel coding scheme in the fifth generation new radio (5G NR) standard due to its capacity-achievable property. Traditional polar decoding algorithms such as successive cancellation (SC) suffer from high latency problem because of their sequential decoding nature. Neural network decoder (NND) has been proved to be a candidate for polar decoder since it is capable of oneshot decoding and parallel computing. Whereas, the bit-errorrate (BER) performance of NND is still inferior to that of SC algorithm. In this paper, we propose a residual neural network decoder (RNND) for polar codes. Different from previous works which directly use neural network for decoding symbols received from the channel, the proposed RNND introduces a denoising module based on residual learning before NND. The proposed residual learning denoiser is able to remove remarkable amount of noise from received signals. Numerical results show that our proposed RNND outperforms traditional NND with regard to the BER performance under comparable latency.

show abstract

Deep Learning for Polar Codes over Flat Fading Channels

Cited by 15 publications

References 9 publications

DIR-Net: Deep Residual Polar Decoding Network Based on Information Refinement

DIR-Net: Deep Residual Polar Decoding Network Based on Information Refinement

Adversarial Filters for Secure Modulation Classification

Learning to Denoise and Decode: A Novel Residual Neural Network Decoder for Polar Codes

Contact Info

Product

Resources

About