Zhiyong Zhao

Dr. Zhiyong Zhao


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 September 2024 in Electronics
Verified
Journal Article
Open access
PDF file
ZZZhiyong Zhao
Zhiyong Zhao
ZMZhongyang Mao
Zhongyang Mao
ZZZhilin Zhang
Zhilin Zhang
YPYaozong Pan
Yaozong Pan
JXJianwu Xu
Jianwu Xu
The existing collaborative channel perception suffers from unreasonable data fusion weight allocation, which mismatches the channel perception capability of the node devices. This often leads to significant deviations between the channel perception results and the actual channel state. To solve this issue, this paper integrates the data fusion algorithm from evidence fusion theory with data link channel state perception. It applies the data fusion advantages of evidence fusion theory to evaluate the traffic pulse statistical capability of network node devices. Specifically, the typical characteristic parameters describing the channel perception capability of node devices are regarded as evidence parameter sets under the recognition framework. By calculating the credibility and falsity of the characteristic parameters, the differences and conflicts between nodes are measured to achieve a comprehensive evaluation of the traffic pulse statistical capabilities of node devices. Based on this evaluation, the geometric mean method is adopted to calculate channel state perception weights for each node within a single-hop range, and a weight allocation strategy is formulated to improve the accuracy of channel state perception.

2 January 2016 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
ZCZhaonan Chen
Zhaonan Chen
HWHongxing Wang
Hongxing Wang
ZZZhiyong Zhao
Zhiyong Zhao
XLXiguo LIU
Xiguo LIU

17 September 2024 in Electronics
Verified
Journal Article
Open access
PDF file
ZMZhongyang Mao
Zhongyang Mao
ZZZhilin Zhang
Zhilin Zhang
FLFaping Lu
Faping Lu
YPYaozong Pan
Yaozong Pan
TZTianqi Zhang
Tianqi Zhang
YYYang You
Yang You
As humans continue to exploit the ocean, the number of UAV nodes at sea and the demand for their services are increasing. Given the dynamic nature of marine environments, traditional resource allocation methods lead to inefficient service transmission and ping-pong effects. This study enhances the alignment between network resources and node services by introducing an attention mechanism and double deep Q-learning (DDQN) algorithm that optimizes the service-access strategy, curbs action outputs, and improves service-node compatibility, thereby constituting a novel method for UAV network resource allocation in marine environments. A selective suppression module minimizes the variability in action outputs, effectively mitigating the ping-pong effect, and an attention-aware module is designed to strengthen node-service compatibility, thereby significantly enhancing service transmission efficiency. Simulation results indicate that the proposed method boosts the number of completed services compared with the DDQN, soft actor–critic (SAC), and deep deterministic policy gradient (DDPG) algorithms and increases the total value of completed services.

12 August 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
ZZZhiyong Zhao
Zhiyong Zhao
ZMZhongyang Mao
Zhongyang Mao
ZZZhilin Zhang
Zhilin Zhang
YPYaozong Pan
Yaozong Pan
JXJianwu Xu
Jianwu Xu
The existing collaborative channel perception suffered from unreasonable data fusion weight allocation, which mismatched the channel perception capability of node devices. This often led to significant deviations between the channel perception results and the actual channel state. To solve this issue, this paper integrated the data fusion algorithm from evidence fusion theory with data link channel state perception. It applied the data fusion advantages of evidence fusion theory to evaluate the traffic pulse statistical capability of network node devices. Specifically, the typical characteristic parameters describing the channel perception capability of node devices were regarded as evidence parameter sets under the recognition framework. By calculating the credibility and falsity of the characteristic parameters, the differences and conflicts between nodes were measured to achieve a comprehensive evaluation of the traffic pulse statistical capabilities of node devices. Based on this evaluation, the geometric mean method was adopted to calculate channel state perception weights for each node within a single-hop range, and a weight allocation strategy was formulated to improve the accuracy of channel state perception.