Bo Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bo Yang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Hongge Yao
School of Computer Science and Engineering, Xi’an Technological University, Xi’an 710064, China
3 shared publications - Haipeng Ren
National Key Laboratory of Land and Air Based Information Perception and Control, No. 10 Zhangba East Road, Yanta District, Xi’an 710065, China
2 shared publications - Hong Jiang
School of Computer Science and Engineering, Xi’an Technological University, Xi’an, China
2 shared publications - Jin Wang
School of Computer Science and Engineering, Xi’an Technological University, Xi’an, China
2 shared publications - Wei Li
School of Mechanical and Electrical Engineering, Xi’an Technological University, Xi’an, China
2 shared publications - Xunhang Shang
School of Computer Science and Engineering, Xi’an Technological University, Xi’an, China
2 shared publications
Latest Publications
- 30 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (5) , 228
Few-shot remote sensing image scene classification based on variational meta-learning
- 30 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (5) , 228
Few-shot remote sensing image scene classification based on variational meta-learning
- Open Access
- 9 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (12) , 2361
A Coordination Optimization Framework for Multi-Agent Reinforcement Learning Based on Reward Redistribution and Experience Reutilization
Cooperative multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for addressing complex real-world challenges, including autonomous robot control, strategic decision-making, and decentralized coordination in unmanned swarm systems. However, it still faces challenges in learning proper coordination among multiple agents. The lack of effective knowledge sharing and experience interaction mechanisms among agents has led to substantial performance decline, especially in terms of low sampling efficiency and slow convergence rates, ultimately constraining the practical applicability of MARL. To address these challenges, this paper proposes a novel framework termed Reward redistribution and Experience reutilization based Coordination Optimization (RECO). This innovative approach employs a hierarchical experience pool mechanism that enhances exploration through strategic reward redistribution and experience reutilization. The RECO framework incorporates a sophisticated evaluation mechanism that assesses the quality of historical sampling data from individual agents and optimizes reward distribution by maximizing mutual information across hierarchical experience trajectories. Extensive comparative analyses of computational efficiency and performance metrics across diverse environments reveal that the proposed method not only enhances training efficiency in multi-agent gaming scenarios but also significantly strengthens algorithmic robustness and stability in dynamic environments.
- 9 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (12) , 2361
Open AccessA Coordination Optimization Framework for Multi-Agent Reinforcement Learning Based on Reward Redistribution and Experience Reutilization
Cooperative multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for addressing complex real-world challenges, including autonomous robot control, strategic decision-making, and decentralized coordination in unmanned swarm systems. However, it still faces challenges in learning proper coordination among multiple agents. The lack of effective knowledge sharing and experience interaction mechanisms among agents has led to substantial performance decline, especially in terms of low sampling efficiency and slow convergence rates, ultimately constraining the practical applicability of MARL. To address these challenges, this paper proposes a novel framework termed Reward redistribution and Experience reutilization based Coordination Optimization (RECO). This innovative approach employs a hierarchical experience pool mechanism that enhances exploration through strategic reward redistribution and experience reutilization. The RECO framework incorporates a sophisticated evaluation mechanism that assesses the quality of historical sampling data from individual agents and optimizes reward distribution by maximizing mutual information across hierarchical experience trajectories. Extensive comparative analyses of computational efficiency and performance metrics across diverse environments reveal that the proposed method not only enhances training efficiency in multi-agent gaming scenarios but also significantly strengthens algorithmic robustness and stability in dynamic environments.
- Open Access
- 2 May 2025
- Published by Springer Nature in Research Square
Few-Shot Remote Sensing Image Scene Classification Based on Variational Meta-Learning
As a typical meta-learning method, model-agnostic meta-learning has attracted widespread attention in the remote sensing field due to its flexibility and applicability to various problems. However, the diversity and uniqueness of meta-tasks are constrained by the influence of remote sensing datasets from different imaging devices, resolutions, and diverse application requirements, which affects the algorithm’s ability to handle different tasks. To address this issue, this paper introduces a new concept called ”central points” starting from the distribution of meta-parameters, within a variational meta-learning framework [7](VML). Based on the concept of central points, we propose a variational meta-learning framework (VML) to obtain ”task central points” through variational inference and generate model parameters from these task central points, enabling the model to adapt to different tasks. To evaluate the utility of VML, experiments were conducted on three public datasets: UC Merced, WHU-RS19, and NWPU-RESISC45. The experimental results demonstrate that compared to some common meta-learning methods, VML effectively addresses the issues of 1 task diversity and heterogeneity in remote sensing datasets, and improves the classification accuracy of remote sensing datasets.
- 2 May 2025
- Published by Springer Nature in Research Square
Open AccessFew-Shot Remote Sensing Image Scene Classification Based on Variational Meta-Learning
As a typical meta-learning method, model-agnostic meta-learning has attracted widespread attention in the remote sensing field due to its flexibility and applicability to various problems. However, the diversity and uniqueness of meta-tasks are constrained by the influence of remote sensing datasets from different imaging devices, resolutions, and diverse application requirements, which affects the algorithm’s ability to handle different tasks. To address this issue, this paper introduces a new concept called ”central points” starting from the distribution of meta-parameters, within a variational meta-learning framework [7](VML). Based on the concept of central points, we propose a variational meta-learning framework (VML) to obtain ”task central points” through variational inference and generate model parameters from these task central points, enabling the model to adapt to different tasks. To evaluate the utility of VML, experiments were conducted on three public datasets: UC Merced, WHU-RS19, and NWPU-RESISC45. The experimental results demonstrate that compared to some common meta-learning methods, VML effectively addresses the issues of 1 task diversity and heterogeneity in remote sensing datasets, and improves the classification accuracy of remote sensing datasets.
- Open Access
- 21 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 828-833
A Factorization Machines-based Participant Recruitment Approach in Mobile Crowdsensing
- 21 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 828-833
Open AccessA Factorization Machines-based Participant Recruitment Approach in Mobile Crowdsensing
- Open Access
- 1 September 2013
- Published by Wiley in BioMed Research International
- Vol. 2013, 1-12
Network-Based Inference Framework for Identifying Cancer Genes from Gene Expression Data
Great efforts have been devoted to alleviate uncertainty of detected cancer genes as accurate identification of oncogenes is of tremendous significance and helps unravel the biological behavior of tumors. In this paper, we present a differential network-based framework to detect biologically meaningful cancer-related genes. Firstly, a gene regulatory network construction algorithm is proposed, in which a boosting regression based on likelihood score and informative prior is employed for improving accuracy of identification. Secondly, with the algorithm, two gene regulatory networks are constructed from case and control samples independently. Thirdly, by subtracting the two networks, a differential-network model is obtained and then used to rank differentially expressed hub genes for identification of cancer biomarkers. Compared with two existing gene-based methods (t-test and lasso), the method has a significant improvement in accuracy both on synthetic datasets and two real breast cancer datasets. Furthermore, identified six genes (TSPYL5, CD55, CCNE2, DCK, BBC3,andMUC1) susceptible to breast cancer were verified through the literature mining, GO analysis, and pathway functional enrichment analysis. Among these oncogenes,TSPYL5andCCNE2have been already known as prognostic biomarkers in breast cancer,CD55has been suspected of playing an important role in breast cancer prognosis from literature evidence, and other three genes are newly discovered breast cancer biomarkers. More generally, the differential-network schema can be extended to other complex diseases for detection of disease associated-genes.
- 1 September 2013
- Published by Wiley in BioMed Research International
- Vol. 2013, 1-12
Open AccessNetwork-Based Inference Framework for Identifying Cancer Genes from Gene Expression Data
Great efforts have been devoted to alleviate uncertainty of detected cancer genes as accurate identification of oncogenes is of tremendous significance and helps unravel the biological behavior of tumors. In this paper, we present a differential network-based framework to detect biologically meaningful cancer-related genes. Firstly, a gene regulatory network construction algorithm is proposed, in which a boosting regression based on likelihood score and informative prior is employed for improving accuracy of identification. Secondly, with the algorithm, two gene regulatory networks are constructed from case and control samples independently. Thirdly, by subtracting the two networks, a differential-network model is obtained and then used to rank differentially expressed hub genes for identification of cancer biomarkers. Compared with two existing gene-based methods (t-test and lasso), the method has a significant improvement in accuracy both on synthetic datasets and two real breast cancer datasets. Furthermore, identified six genes (TSPYL5, CD55, CCNE2, DCK, BBC3,andMUC1) susceptible to breast cancer were verified through the literature mining, GO analysis, and pathway functional enrichment analysis. Among these oncogenes,TSPYL5andCCNE2have been already known as prognostic biomarkers in breast cancer,CD55has been suspected of playing an important role in breast cancer prognosis from literature evidence, and other three genes are newly discovered breast cancer biomarkers. More generally, the differential-network schema can be extended to other complex diseases for detection of disease associated-genes.