https://scholars.lib.ntu.edu.tw/handle/123456789/611209
標題: | A neural network-aided viterbi receiver for joint equalization and decoding | 作者: | AN-YEU(ANDY) WU | 關鍵字: | Channel Decoding; Convolutional Code; Neural Network; Symbol Detection; Viterbi Algorithm | 公開日期: | 2020 | 卷: | 2020-September | 來源出版物: | IEEE International Workshop on Machine Learning for Signal Processing, MLSP | 摘要: | In recent years, many works have been focusing on applying machine learning techniques to assist with communication system design. Instead of replacing the functional blocks of communication systems with neural networks, a hybrid manner of ViterbiNet symbol detection was proposed to combine the advantages of Viterbi algorithm and neural networks, which achieves guaranteed performance with reasonable complexity. However, this block-based design not only degrades the system performance but also increases hardware complexity. In this work, we propose a ViterbiNet receiver for joint equalization and channel decoding, which simultaneously considers both the code structure and channel effects, thus achieving global optimum with 3 dB gain. Furthermore, a dedicated neural network model is proposed to avoid the need for perfect channel state information (CSI). It is shown to be more robust under CSI uncertainty with 1.7 dB gain. © 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096471285&doi=10.1109%2fMLSP49062.2020.9231847&partnerID=40&md5=fb9498c1d57b2882b815af26c0de9391 https://scholars.lib.ntu.edu.tw/handle/123456789/611209 |
ISBN: | 9.78173E+12 | ISSN: | 21610363 | DOI: | 10.1109/MLSP49062.2020.9231847 | SDG/關鍵字: | Channel state information; Complex networks; Decoding; Equalizers; Machine learning; Viterbi algorithm; Block based design; Guaranteed performance; Hardware complexity; Joint equalization and decoding; Machine learning techniques; Neural network model; Perfect channel state information; Symbol detection; 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。