Guixing Cao

TL;DR: A supervised deep learning-based encoder-decoder scheme was proposed to improve recinstruction quality recovery channel state information and compared with the traditional compression-based sensing algorithm, Residual Attention-Net can still maintain good performance when compression is low.

TL;DR: The proportion optimal RMSTA (PO-RMSTA) heuristic algorithm with three sorting strategies is proposed and proved to obtain the approximate optimal solutions, and the compromise between two indices, both AET and AAS provided satisfying results.

TL;DR: In this article, the authors proposed a satellite network self-adaption joint spectrum sensing method based on link sensing by means of the method, two judgment threshold values (one high threshold value and one low threshold value) are figured out according to current satellite link parameters which are obtained by a link sensing technology, energy of a to-be-detected signal is calculated according to an energy detecting method and compared with the two threshold values, if the energy is larger than or equal to the high value, a master user signal is determined to exist and if the signal is smaller than or

TL;DR: This paper proposes a node stability factor based on node received power, which does not need to calculate the specific distance between nodes and can only judge the relative motion between the nodes according to the transmitting power and the received power of the node.

TL;DR: In this article, a novel evaluation algorithm of turbulent influence is presented for influence investigation of Gaussian beam and Airy beams in atmospheric turbulence, in which a parameter to quantify the influence of turbulence is proposed and named by Intensity Variation Index.