Xiangyu Yang

Dr. Xiangyu Yang

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
20 January 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XYXiangyu Yang
Xiangyu Yang
Xuezhi YangXuezhi Yang
Xuezhi Yang
CZChunju Zhang
Chunju Zhang
JWJun Wang
Jun Wang
Classification algorithms integrated with convolutional neural networks (CNN) display high accuracies in synthetic aperture radar (SAR) image classification. However, their consideration of spatial information is not comprehensive and effective, which causes poor performance in edges and complex regions. This paper proposes a Markov random field (MRF)-based algorithm for SAR image classification which fully considers the spatial constraints between superpixel regions. Firstly, the initialization of region labels is obtained by the CNN. Secondly, a probability field is constructed to improve the distribution of spatial relationships between adjacent superpixels. Thirdly, a novel region-level MRF is employed to classify the superpixels, which combines the intensity field and probability field in one framework. In our algorithm, the generation of superpixels reduces the misclassification at the pixel level, and region-level misclassification is rectified by the improvement of spatial description. Experimental results on simulated and real SAR images confirm the efficacy of the proposed algorithm for classification.

1 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HZHuaping Zhou
Huaping Zhou
SXShuai Xu
Shuai Xu
MCMan Chen
Man Chen
KSKelei Sun
Kelei Sun
YHYongjie Huang
Yongjie Huang
HLHanwen Liu
Hanwen Liu

8 September 2025 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
GYGaoming Yang
Gaoming Yang
PZPeng Zhu
Peng Zhu
JZJi Zhang, Zhang
Ji Zhang, Zhang
XYXiangyu Yang
Xiangyu Yang

17 October 2026 in Sensors
Verified
Journal Article
Open access
PDF file
XYXiangyu Yang
Xiangyu Yang
JWJianjian Wu
Jianjian Wu
JWJun Wang
Jun Wang
This paper studies joint antenna allocation, subcarrier allocation, user activation, and superuser grouping in sparse-code-and-blind-interference-alignment-based multiple access (SBMA), where these decisions also determine the feasible transmission configuration. We formulate the problem as a constrained integer optimization and evaluate a hybrid constraint-aware genetic algorithm (HCAGA) using SBMA as a case study. HCAGA combines a compact integer encoding, feasibility-first selection, uniform crossover, multi-mode mutation, hierarchical structural and rate repair, and periodic QoS-aware local search. Its objective is to maximize the number of users whose rate meets a prescribed threshold. In 50 Monte Carlo realizations with 20 transmit antennas, 5 clusters, 20 subcarriers, and 20 candidate users per cluster, HCAGA serves 54.70 users at 10 dB and 93.54 at 20 dB on average, compared with 48.10 and 85.52 for a Standard GA and 25.00 for the tested budgeted random-search (BRS) implementation. The gain is operating-region dependent: Standard GA is significantly better at 6 dB, whereas the 4 dB difference is not significant and HCAGA is higher at most other tested SNRs. Paired ablations show positive average contributions from hierarchical repair and local search, with repair gains remaining statistically detectable at the tested 6, 12, and 18 dB points. HCAGA also requires substantially more rate evaluations; equal-evaluation-budget performance has not been established.