Progressive Bit-Flipping Decoding of Polar Codes over Layered Critical Sets

2019 IEEE 30th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

Zhang

et al. 2019

Self Cite

The key to successive cancellation (SC) flip decoding of polar codes is to accurately identify the first error bit. The optimal flipping strategy is considered difficult due to lack of an analytical solution. Alternatively, we propose a deep learning aided SC flip algorithm. Specifically, before each SC decoding attempt, a long short-term memory (LSTM) network is exploited to either (i) locate the first error bit, or (ii) undo a previous "wrong" flip. In each SC attempt, the sequence of log likelihood ratios (LLRs) derived in the previous SC attempt is exploited to decide which action to take. Accordingly, a two-stage training method of the LSTM network is proposed, i.e., learn to locate first error bits in the first stage, and then to undo "wrong" flips in the second stage. Simulation results show that the proposed approach identifies error bits more accurately and achieves better performance than the state-of-the-art SC flip algorithms.

“…• The LSTM network has been trained without human knowledges in this paper. Human knowledges, e.g., critical set [6], may help improving the performance further.…”

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning to Flip Successive Cancellation Decoding of Polar Codes with LSTM Networks

2019 IEEE 30th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

Zhang

et al. 2019

Self Cite

“…Later in [11], [12], the segmentation method is further introduced in SC-Flip decoding. The progressive SC-Flip decoding proposed in [13] constructs a critical set (CS) including the first error bit and then develops a multiple-layer-flip decoding. The Fast-SSC-Flip decoding, which merges the SCF [4] with the fast-simplified SC (Fast-SSC) [14], [16], was proposed in [17].…”

Section: Introductionmentioning

confidence: 99%

Improved Multiple Bit-Flipping Fast-SSC Decoding of Polar Codes

et al. 2020

IEEE Access

Polar codes can provably achieve channel capacity and have been used in standards of the 5th generation wireless communication. As the first decoding algorithm of polar codes, successive cancellation (SC) suffers a significant error-correction performance loss at the moderate to short code length. The SC-Flip decoding aims to correct the first error in the SC decoding, and has the competitive error-correction performance compared with the SC decoding at the cost of high decoding latency. However, there may exist more than one errors in the SC decoding. Therefore, this paper proposes to enhance the fast-simplified SC (Fast-SSC) decoding to incorporate multiple bit-flipping, and further proposes two enhanced Fast-SSC-Flip decoding algorithms. One is a two-bit-flipping Fast-SSC (Fast-SSC-2Flip-E 2) decoding algorithm based on the distribution of the second error (E 2) in the Fast-SSC decoding, and is further expanded to flip multiple bits based on the distribution of multiple errors. The other is a partitioned Fast-SSC-Flip (PA-Fast-SSC-Flip) decoding algorithm. The Fast-SSC decoder tree is divided into several partitions, on which the Fast-SSC-Flip decoding is performed. Compared with the traditional Fast-SSC-Flip decoding, the proposed Fast-SSC-2Flip-E 2 has an error-correction performance gain up to 0.2 dB while keeping the average complexity close to that of the traditional Fast-SSC-Flip. The decoding speed of the PA-Fast-SSC-Flip is up to 6 times faster than that of traditional Fast-SSC-Flip, and has an error-correction performance gain up to 0.16dB. INDEX TERMS Polar codes, error-correction performance, fast-simplified SC flip decoding, partitioned decoding, multiple bit-flipping.

“…In order to enhance the performance of SCF decoding, several improvements have been proposed to correct more erroneous decisions [8][9][10][11][12]. In [8], they subdivide the codeword into several partitions, on which SCF is run individually.…”

Section: Introductionmentioning

confidence: 99%

Algorithm and Architecture for Path Metric Aided Bit-Flipping Decoding of Polar Codes

Chen

2019 IEEE Wireless Communications and Networking Conference (WCNC)

et al. 2019

Polar codes attract more and more attention of researchers in recent years, since its capacity achieving property. However, their error-correction performance under successive cancellation (SC) decoding is inferior to other modern channel codes at short or moderate blocklengths. SC-Flip (SCF) decoding algorithm shows higher performance than SC decoding by identifying possibly erroneous decisions made in initial SC decoding and flipping them in the sequential decoding attempts. However, it performs not well when there are more than one erroneous decisions in a codeword. In this paper, we propose a path metric aided bit-flipping decoding algorithm to identify and correct more errors efficiently. In this algorithm, the bit-flipping list is generated based on both log likelihood ratio (LLR) based path metric and bit-flipping metric. The path metric is used to verify the effectiveness of bit-flipping. In order to reduce the decoding latency and computational complexity, its corresponding pipeline architecture is designed. By applying these decoding algorithm and pipeline architecture, an improvement on error-correction performance can be got up to 0.25dB compared with SCF decoding at frame error rate of 10 −4 , with low average decoding latency.