In this paper, we propose an intelligent analog beam selection strategy in a terahertz (THz) band beamspace multiple-input multiple-output (MIMO) system. First inspired by transfer learning, we fine-tune the pre-trained off-the-shelf GoogleNet classifier to learn analog beam selection as a multi-class mapping problem. Simulation results show 83% accuracy for the analog beam selection, which subsequently results in 12% spectral efficiency (SE) gain over the existing counterparts. For a more accurate classifier, we replace the conventional rectified linear unit (ReLU) activation function of the GoogleNet with the recently proposed Swish and retrain the fine-tuned GoogleNet to learn analog beam selection. It is numerically indicated that the fine-tuned Swish-driven GoogleNet achieves 86% accuracy, as well as 18% improvement in achievable SE, over the similar schemes. Eventually, a strong ensembled classifier is developed to learn analog beam selection by sequentially training multiple fine-tuned Swish-driven GoogleNet classifiers. According to the simulations, the strong ensembled model is 90% accurate and yields 27% gain in achievable SE in comparison with prior methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMO


    Contributors:


    Publication date :

    2022-06-01


    Size :

    806519 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Data-Driven Beams Selection for Beamspace Channel Estimation in Massive MIMO

    Bychkov, Roman / Osinsky, Alexander / Ivanov, Andrey et al. | IEEE | 2021


    IRS-Assisted Beamspace Millimeter-wave Massive MIMO with Interference-Aware Beam Selection

    Elganimi, Taissir Y. / Elmajdub, Retaj I. / Nauryzbayev, Galymzhan et al. | IEEE | 2022


    Citroe͏̈n SM - Swift and swish

    Online Contents | 1999


    Deep learning algorithm for autonomous driving using GoogLeNet

    Al-Qizwini, Mohammed / Barjasteh, Iman / Al-Qassab, Hothaifa et al. | IEEE | 2017


    Sequentical beamspace beamforming

    Tidd, William / Huang, Yikun / Zhao, Yufei | IEEE | 2012