2021/12/01 by Chenwu Zhang, Zhang, Chenwu, Hancheng Lu +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Advanced Wireless Communication Technologies #Advanced biosensing and bioanalysis techniques #FOS: Computer and information sciences #FOS: Electrical engineering #Information Theory (cs.IT) #Signal Processing (eess.SP) #Wireless Signal Modulation Classification #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2112.00910
openalex publication_date 2021/12/01 · openalex created_date 2022/11/09 · openalex updated_date 2026/07/28
Index modulation (IM) reduces the power consumption and hardware cost of the\nmultiple-input multiple-output (MIMO) system by activating part of the antennas\nfor data transmission. However, IM significantly increases the complexity of\nthe receiver and needs accurate channel estimation to guarantee its\nperformance. To tackle these challenges, in this paper, we design a deep\nlearning (DL) based detector for the IM aided MIMO (IM-MIMO) systems. We first\nformulate the detection process as a sparse reconstruction problem by utilizing\nthe inherent attributes of IM. Then, based on greedy strategy, we design a DL\nbased detector, called IMRecoNet, to realize this sparse reconstruction\nprocess. Different from the general neural networks, we introduce complex value\noperations to adapt the complex signals in communication systems. To the best\nof our knowledge, this is the first attempt that introduce complex valued\nneural network to the design of detector for the IM-MIMO systems. Finally, to\nverify the adaptability and robustness of the proposed detector, simulations\nare carried out with consideration of inaccurate channel state information\n(CSI) and correlated MIMO channels. The simulation results demonstrate that the\nproposed detector outperforms existing algorithms in terms of antenna\nrecognition accuracy and bit error rate under various scenarios.\n