Yu Wang

TL;DR: A deep learning-based method, combined with two convolutional neural networks trained on different datasets, to achieve higher accuracy AMR, demonstrating the ability to classify QAM signals even in scenarios with a low signal-to-noise ratio.

TL;DR: Experimental results show that the proposed LightAMC method can effectively reduce model sizes and accelerate computation with the slight performance loss, and enforce scaling factors sparsity via compressive sensing.

TL;DR: Simulation results demonstrated that the proposed CVNN-based SEI method is superior to the existing DL-based methods in both identification performance and convergence speed, and the identification accuracy of CVNN can reach up to nearly 100% at high signal-to-noise ratios (SNRs).

TL;DR: Four deep neural networks are considered for remote sensing images with various changes and multi-scene classes, and SMDTR-CNN obtained the best overall accuracy and kappa coefficient while also improving the precision of parking lot and resident samples by 1% and 4%, respectively.

TL;DR: A novel multi-task learning (MTL)-based generalized AMC method is proposed, and a more realistic scenario is considered, including white non-Gaussian noise and synchronization error, showing that the proposed architecture can achieve higher robustness and generalization than the conventional ones.