https://scholars.lib.ntu.edu.tw/handle/123456789/611197
標題: | Convolutional neural network-aided bit-flipping for Belief propagation decoding of polar codes | 作者: | AN-YEU(ANDY) WU | 關鍵字: | Belief propagation; Bitflipping; Convolutional neural network; Polar codes | 公開日期: | 2021 | 卷: | 2021-June | 起(迄)頁: | 7898-7902 | 來源出版物: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | 摘要: | Known for their capacity-achieving abilities, polar codes have been selected as the control channel coding scheme for 5G communications. To satisfy high throughput and low latency, belief propagation (BP) is ideal as the decoding algorithm due to its nature of parallel processing. However, the error performance of BP is in general worse than that of enhanced successive cancellation (SC). Recently, bit-flipping (BF) mechanism is applied to BP decoding to lower the error rate. However, its trial-and-error process results in longer latency. In this work, we propose a convolutional neural network-aided bit-flipping (CNN-BF) mechanism to further enhance BP decoding. With carefully designed input data and model architecture, our proposed CNN-BF can achieve better error correction capability with less flipping attempts than prior works. It also achieves a lower block error rate (BLER) than SC list (SCL). © 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115134329&doi=10.1109%2fICASSP39728.2021.9413808&partnerID=40&md5=057a9dbf0edeac76ea447411ee57210a https://scholars.lib.ntu.edu.tw/handle/123456789/611197 |
ISSN: | 15206149 | 其他識別: | IPROD | DOI: | 10.1109/ICASSP39728.2021.9413808 | SDG/關鍵字: | 5G mobile communication systems; Backpropagation; Bit error rate; Channel coding; Convolution; Decoding; Error correction; Network coding; Belief propagation; Belief propagation decoding; Decoding algorithm; Error correction capability; Model architecture; Parallel processing; Successive cancellation; Trial-and-error process; Convolutional neural networks |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。