15 February 2023 in IEEE Communications Letters
The orthogonal frequency division multiplexing (OFDM) technique has received wide attention because of its high spectrum utilization. However, the drawback of inter-subcarrier interference in OFDM systems makes the channel estimation and signal detection performance of OFDM systems with few pilots and short cyclic prefixes (CP) poor. In this paper, we use deep learning to assist OFDM in recovering nonlinearly distorted transmission data. Specifically, we use a self-normalizing network (SNN) for channel estimation, combined with a convolutional neural network (CNN) and a bidirectional gated recurrent unit (BiGRU) for signal detection, thus proposing a novel SNN-CNN-BiGRU network structure (SCBiGNet). The simulation results show that the SCBiGNet model outperforms the existing techniques for the different numbers of pilots and lengths of CPs. The BER performance is improved by 0.2~9 dB.
20 May 2025 in Biosensors and Bioelectronics
11 May 2023 in Journal of Lightwave Technology
Active and effective control over terahertz (THz) waves is essential for THz applications, and the incorporation of dynamic materials into metasurfaces offers opportunities to realize highly efficient THz manipulation. Here, optically controlled THz metasurface devices (meta-devices) based on either perovskite or graphene are experimentally demonstrated, each exhibiting ultra-sensitive THz modulation under extremely low external optical power. We achieve a maximum modulation depth of 237.5% in the THz transmission amplitude of a metal-perovskite hybrid meta-device when the power density is as low as 13.7483 mW/cm 2 . Moreover, a metal-graphene hybrid meta-device also shows ultra-sensitive optically induced characteristics, with a maximum modulation depth of 403.36% under the extremely low power density of 11.1846 mW/cm 2 . These devices offer a meaningful guide for the design of tunable terahertz meta-devices that will find utility in applications that require the ultra-sensitive optical modulation of terahertz waves.
9 December 2022 in IEEE Access
The application of deep learning in compressed sensing reconstruction has achieved some excellent results. The deep neural network based on iterative algorithm can not only reflect the excellent performance of deep learning, but also reflect the interpretability of traditional compressed sensing reconstruction algorithm. The existing deep neural networks based on iterative algorithm mainly include learned iterative shrinkage threshold algorithm(LISTA), analytic learned iterative shrinkage threshold algorithm(ALISTA), etc., but each of them has its own shortcomings.We improved the network structure on the basis of predecessors, and proposed a new custom loss function to effectively improve the reconstruction performance of compressed sensing. Experiments show that our proposed neural network reduces the normalized mean square error(NMSE) by 10 dB compared with ALISTA and 15 dB compared with LISTA, and the support set accuracy of the recovered sparse signal can be optimized by our proposed custom loss function by at least 5%, especially LISTA, which has been improved by at least 80%.