Yaohong Zhang

Yaohong Zhang

Auto-generated profile, based on publicly available information

Yaohong Zhang

Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
13 September 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
HYHui Yan
Hui Yan
WBWeidong Bao
Weidong Bao
XLXiaoqing Li
Xiaoqing Li
Xiaomin ZhuXiaomin Zhu
Xiaomin Zhu
YZYaohong Zhang
Yaohong Zhang
LLLing Liu
Ling Liu
Unmanned aerial vehicle (UAV)-enabled data collection is considered a promising paradigm of emergency data transmission for IoT applications when the communication infrastructure is damaged. UAV scheduling for data collection as the critical technology has attracted widespread attention. Most studies default to the absolute reliability of UAVs for data collection, yet it is inevitable for UAVs to fail in flight. It is unacceptable if some critical data is lost due to UAV faults. Therefore, we research fault-tolerant scheduling for data collection enabled by heterogeneous UAVs. First, a three-layer data collection motivation scenario is proposed, where the fault tolerance issue is involved for the first time. Then, we propose a utility-based fault tolerance model (UBFT) to balance the reliability and efficiency of data collection. The UAV fault-tolerant scheduling is modeled as a multiobjective optimization problem to concurrently optimize the data throughput and load balancing of data collection. Combining the characteristics of optimization objectives, an alternating coordinate optimization method—ACTOR is presented to solve this problem efficiently. Numerous simulation experiments and real-machine experiments demonstrate that ACTOR-UBFT achieves excellent performance in fault tolerance, data throughput, adaptation, algorithm complexity, etc.

12 August 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XZXiongtao Zhang
Xiongtao Zhang
JWJi Wang
Ji Wang
WBWeidong Bao
Weidong Bao
YZYaohong Zhang
Yaohong Zhang
Xiaomin ZhuXiaomin Zhu
Xiaomin Zhu
XZXiang Zhao
Xiang Zhao
Conventional federated learning (FL) assumes the homogeneity of models, necessitating clients to expose their model parameters to enhance the performance of the server model. However, this assumption cannot reflect real-world scenarios. Sharing models and parameters raises security concerns for users, and solely focusing on the server-side model neglects clients’ personalization requirements, potentially impeding expected performance improvements of users. On the other hand, prioritizing personalization may compromise the generalization of the server model, thereby hindering extensive knowledge migration. To address these challenges, we put forth an important problem: How can FL ensure both generalization and personalization when clients’ models are heterogeneous? In this work, we introduce FedTED, which leverages a twin-branch structure and data-free knowledge distillation (DFKD) to address the challenges posed by model heterogeneity and diverse objectives in FL. The employed techniques in FedTED yield significant improvements in both personalization and generalization, while effectively coordinating the updating process of clients’ heterogeneous models and successfully reconstructing a satisfactory global model. Our empirical evaluation demonstrates that FedTED outperforms many representative algorithms, particularly in scenarios where clients’ models are heterogeneous, achieving a remarkable 19.37% enhancement in generalization performance and up to 9.76% improvement in personalization performance.

11 September 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
XZXiongtao Zhang
Xiongtao Zhang
JWJi Wang
Ji Wang
WBWeidong Bao
Weidong Bao
HPHao Peng
Hao Peng
YZYaohong Zhang
Yaohong Zhang
Xiaomin ZhuXiaomin Zhu
Xiaomin Zhu

31 July 2024 in Future Generation Computer Systems
Verified
Journal Article
Closed access
XZXiongtao Zhang
Xiongtao Zhang
JWJi Wang
Ji Wang
WBWeidong Bao
Weidong Bao
WXWenhua Xiao
Wenhua Xiao
YZYaohong Zhang
Yaohong Zhang
LLLihua Liu
Lihua Liu

29 October 2021
Verified
Conference Paper
Closed access
WZWen Zhou
Wen Zhou
YZYaohong Zhang
Yaohong Zhang
JWJi Wang
Ji Wang
XSXiaomin Sun
Xiaomin Sun
ZCZhihao Chen
Zhihao Chen
XYXifu Yan
Xifu Yan
At present, the implementation of Decision-Centered Warfare faces important challenges, and the Mosaic Warfare provides a solution to its challenges, while the Effects Web construction is a core element of the Mosaic Warfare, which is the key and difficult point of Mosaic Warfare implementation. Current research on the Effects Web construction in Mosaic Warfare is very scarce and mostly stays at the conceptual stage. To make up for the lack of current research on the Effects Web, we proposed EW2BPaaS, a framework for Effects Web-based battle platform as a service, drawing on the theoretical and practical foundations of IoT service architecture, and specify the framework by taking time-sensitive target strikes as an example. Our research provides a reference solution to deepen the understanding of and advance the research of Effects Web.

14 July 2024
Verified
Conference Paper
Open access
JHJie He
Jie He
YZYaohong Zhang
Yaohong Zhang
JWJi Wang
Ji Wang
XLXiaoqing Li
Xiaoqing Li
WBWeidong Bao
Weidong Bao
Multi-objective optimization algorithms have a wide range of applications in various fields. NSGA-II (Non-dominated Sorting Genetic Algorithm II) is a well-known multi-objective optimization algorithm. However, when solving high-dimensional problems using NSGA-II, the algorithm complexity increases linearly with the problem dimension. To address this issue, this paper proposes the HNSGA-II (Hypernetwork Non-dominated Sorting Genetic Algorithm II) algorithm based on hypernetwork modeling. The HNSGA-II algorithm introduces a binary tree data structure and uses hypernetworks to model candidate solutions. A new crowding calculation is designed to improve the algorithm's convergence. Horizontal and vertical comparative experiments were conducted on standard test sets ZDT and BT using the newly proposed algorithm, NSGA-II, MOEAD, and other algorithms. The results demonstrate that the HNSGA-II algorithm achieves a maximum improvement of about 10% in time efficiency when solving high-dimensional problems and exhibits better algorithmic convergence than the original NSGA-II algorithm.