计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240900122-6.doi: 10.11896/jsjkx.240900122
王婵飞, 杨婧, 许亚美, 何继爱
WANG Chanfei, YANG Jing, XU Yamei, HE Jiai
摘要： 在探讨正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM) 系统的优化中,一个显著挑战在于其信号检测性能的相对不足。同时,针对基于深度神经网络的索引调制(Deep Neural Network Based Index Modulation,DNN-IM) 检测算法,普遍存在着误码率及损失值偏高的问题。为了弥补上述难题,文中提出一种基于多层感知机(Multilayer Perceptron,MLP) 的索引调制检测算法,即MLP-IM算法。该算法采用融合两个连接层与一个输出层的架构设计,通过挑选的激活函数实现对OFDM索引调制系统中数据比特的精准还原。首先将OFDM索引调制系统的基础理论巧妙应用于数据的预处理阶段,随后利用仿真数据集对MLP神经网络模型进行全面而深入的离线训练,确保模型的稳健性与准确性。在检测阶段,通过MLP-IM检测算法实现了对OFDM索引调制系统的高效检测。仿真结果表明,所提出的MLP-IM算法在误码率控制和损失值两个方面的性能表现与最大似然检测算法相媲美,甚至在某些场景下超越了现有DNN-IM算法的性能,其性能改善幅度在0.2~6 dB的区间内。
中图分类号:
| [1]SUN S,JU Y,YAMAO Y.Overlay cogn-itive radio OFDM system for 4G cellular networks [J].IEEE Wireless Commu-nications,2013,20(2):68-73. [2]KIM K H.Dither signal design for PAPR red-uction in OFDM-IM over a rayleigh fading channel[J].IEICE Transactions on Comm-unications,2024,7(2):505-512. [3]MAO T,WANG Q,WANG Z,et al.Novel index modulationtechniques:a survey [J].IEEE Communications Surveys & Tutorials,2019,21(1):315-348. [4]BASAR E,AYGOLU U,PANAYIRCI E,et al.Orthogonal frequency division mult-iplexing with index modulation[J].IEEE Transactions on Signal Processing,2013,61(22):5536-5549. [5]SIDDIQ A I.Low complexity OFDM-IM detector by encoding all possible subcarrier activation patterns[J].IEEE Communications Letters,2016,20(3):446-449. [6]ZHUANG L,DAI L,LIU S Z,et al.Opt-imized scheme for spectrum and energy efficiency of multiple-mode OFDM with index modulation[J].Systems Engineering and Electronics,2020,42(3):719-726. [7]ZHENG B,CHEN F,WEN M,et al.Low-complexity ML detector and performance analysis for OFDM with in-phase/quadrature index modulation[J].IEEE Communications Letters,2015,19(11):1893-1896. [8]SABUD S,KUMAR P.A low complexity two-stage LLR detector for downlink OFDM-IM NOMA[J].IEEE Communications Letters,2022,26(10):2247-2251. [9]CRAWFORD J,CHATZIANTONIOU E,KO Y.On the SEPanalysis of OFDM index modulation with hybrid low complexity greedy detection and diversity reception[J].IEEE Transactions on Vehicular Technology,2017,66(9):8103-8118. [10]CRAWFORD J,KO Y.Low complexity greedy detection method with generalized multicarrier index keying OFDM[C]//2015 IEEE 26th Annual International Symposium on Personal,Indoor,and Mobile Radio Communications(PIMRC).2015:688-693. [11]SUI Z,YAN S,ZHANG H,et al.Approximate Message Passing Algori-thms for Low Complexity OFDM-IM Detection[J].IEEE Transactions on Vehicular Technology,2021,70(9):9607-9612. [12]YE H,LI Y G,JUAN H B.Power of deep learning for channel estimation and signal detection in OFDM systems[J].IEEE Wireless Communications Letters,2018,7(1):114-117. [13]GAO X,JIN S,WEN C K,et al.Comb-ination of deep learning and expert knowledge in OFDM receivers[J].IEEE Communications Society,2018,22(12):2627-2630. [14]ALACA O,ALTHUNIBAT S,YARKAN S,et al.CNN-Based Signal Detector for IM-OFDMA[C]//2021 IEEE Global Communications Conference(GLOBECOM).2021. [15]CHANG D N,ZHOU J.Deep learning-based signal detection in OFDM systems[J].Journal of Southeast University(Natural Science Edition),2020,50(5):912-917. [16]KIM J,PARK H.Deep learning-based dete-ctor with modulation parameter-independent structure for OFDM with index mod-ulation[J].IEEE Access,2023,11,130358-130367. [17]WANG T,YANG F,SONG J,et al.Deep con-volutional neural network-based detector for index modulation[J].IEEE Wireless Comm-unications Letters,2020,9(10):1705-1709. [18]LUONG T V,KO Y,VIEN N A,et al.Deep learning-based detector for OFDM-IM[J].IEEE Wireless Communications Letters,2019,8(4):1159-1162. |
|
||
首页