Yongfeng Yin

Prof. Dr. Yongfeng Yin

School of Software, Beihang University, Beijing, China
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
20 August 2022 in Drones
Verified
Journal Article
Open access
PDF file
Yongfeng YinYongfeng Yin
Yongfeng Yin
YGYang Guo
Yang Guo
QSQingran Su
Qingran Su
ZWZhetao Wang
Zhetao Wang
With the development of UAV technology, the task allocation problem of multiple UAVs is remarkable, but most of these existing heuristic methods are easy to fall into the problem of local optimization. In view of this limitation, deep transfer reinforcement learning is applied to the task allocation problem of multiple unmanned aerial vehicles, which provides a new idea about solving this kind of problem. The deep migration reinforcement learning algorithm based on QMIX is designed. The algorithm first compares the target task with the source task in the strategy base to find the task with the highest similarity, and then migrates the network parameters obtained from the source task after training, stored in the strategy base, so as to accelerate the convergence of the QMIX algorithm. Simulation results show that the proposed algorithm is significantly better than the traditional heuristic method of allocation in terms of efficiency and has the same running time.

21 June 2024 in Electronics
Verified
Journal Article
Open access
PDF file
Yongfeng YinYongfeng Yin
Yongfeng Yin
ZWZhetao Wang
Zhetao Wang
LZLili Zheng
Lili Zheng
QSQingran Su
Qingran Su
YGYang Guo
Yang Guo
Unmanned aerial vehicle (UAV) navigation plays a crucial role in its ability to perform autonomous missions in complex environments. Most of the existing reinforcement learning methods to solve the UAV navigation problem fix the flight altitude and velocity, which largely reduces the difficulty of the algorithm. But the methods without adaptive control are not suitable in low-altitude environments with complex situations, generally suffering from weak obstacle avoidance. Some UAV navigation studies with adaptive flight only have weak obstacle avoidance capabilities. To address the problem of UAV navigation in low-altitude environments, we construct autonomous UAV navigation in 3D environments with adaptive control as a Markov decision process and propose a deep reinforcement learning algorithm. To solve the problem of weak obstacle avoidance, we creatively propose the guide attention method to make a UAV’s decision focus shift between the navigation task and obstacle avoidance task according to changes in the obstacle. We raise a novel velocity-constrained loss function and add it to the original actor loss to improve the UAV’s velocity control capability. Simulation experiment results demonstrate that our algorithm outperforms some of the state-of-the-art deep reinforcement learning algorithms performing UAV navigation tasks in a 3D environment and has outstanding performance in algorithm effectiveness, with the average reward increasing by 9.35, the success rate of navigation tasks increasing by 14%, and the collision rate decreasing by 14%.

17 January 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Ruinan QiuRuinan Qiu
Ruinan Qiu
Yongfeng YinYongfeng Yin
Yongfeng Yin
QSQingran Su
Qingran Su
TGTianyi Guan
Tianyi Guan
In the field of ensemble learning, bagging and stacking are two widely used ensemble strategies. Bagging enhances model robustness through repeated sampling and weighted averaging of homogeneous classifiers, while stacking improves classification performance by integrating multiple models using meta-learning strategies, taking advantage of the diversity of heterogeneous classifiers. However, the fixed weight distribution strategy in traditional bagging methods often has limitations when handling complex or imbalanced datasets. This paper combines the concept of heterogeneous classifier integration in stacking with the weighted averaging strategy of bagging, proposing a new adaptive weight distribution approach to enhance bagging’s performance in heterogeneous ensemble settings. Specifically, we propose three weight generation functions with “high at both ends, low in the middle” curve shapes and demonstrate the superiority of this strategy over fixed weight methods on two datasets. Additionally, we design a specialized neural network, and by training it adequately, validate the rationality of the proposed adaptive weight distribution strategy, further improving the model’s robustness. The above methods are collectively called func-bagging. Experimental results show that func-bagging has an average 1.810% improvement in extreme performance compared to the base classifier, and is superior to stacking and bagging methods. It also has better dataset adaptability and interpretability than stacking and bagging. Therefore, func-bagging is particularly effective in scenarios with class imbalance and is applicable to classification tasks with imbalanced classes, such as anomaly detection.

30 November 2025 in Aerospace
Verified
Journal Article
Open access
PDF file
XOXulang Ouyang
Xulang Ouyang
YZYanqiang Zhang
Yanqiang Zhang
LHLu Hua
Lu Hua
Yongfeng YinYongfeng Yin
Yongfeng Yin
This paper presents AF-TAD, which stands for Aircraft Fuel Transformer Anomaly Detection, a Transformer-based reconstruction model specifically designed for time-series anomaly detection in aircraft fuel systems. The model improves anomaly detection by encoding and fusing key features such as fuel mass, overload, and RPM. Additionally, it incorporates global information, a multi-scale time window compression technique, and a conditional coding layer that integrates flight-specific information to enhance time-series data analysis, adaptability, and detection accuracy. Experimental results demonstrate that AF-TAD significantly outperforms other state-of-the-art anomaly detection models in detecting interval anomalies, achieving superior performance in key metrics. An ablation study further confirms that critical components, such as multi-window encoding and global trend information, contribute to improving the model’s detection capabilities. Overall, AF-TAD not only demonstrates powerful anomaly detection capabilities in the complex domain of aircraft fuel systems, but also offers new technical methods for fault prediction and maintenance in this field. Additionally, it holds broad potential for application in other complex systems.

13 February 2018 in PLOS ONE
Verified
Journal Article
Open access
PDF file
ZZZenghu Zhang
Zenghu Zhang
Yongfeng YinYongfeng Yin
Yongfeng Yin
XZXin Zhang
Xin Zhang
LLLijun Liu
Lijun Liu
Controllability of complex networks has been a hot topic in recent years. Real networks regarded as interdependent networks are always coupled together by multiple networks. The cascading process of interdependent networks including interdependent failure and overload failure will destroy the robustness of controllability for the whole network. Therefore, the optimization of the robustness of interdependent network controllability is of great importance in the research area of complex networks. In this paper, based on the model of interdependent networks constructed first, we determine the cascading process under different proportions of node attacks. Then, the structural controllability of interdependent networks is measured by the minimum driver nodes. Furthermore, we propose a parameter which can be obtained by the structure and minimum driver set of interdependent networks under different proportions of node attacks and analyze the robustness for interdependent network controllability. Finally, we optimize the robustness of interdependent network controllability by redundant design including node backup and redundancy edge backup and improve the redundant design by proposing different strategies according to their cost. Comparative strategies of redundant design are conducted to find the best strategy. Results shows that node backup and redundancy edge backup can indeed decrease those nodes suffering from failure and improve the robustness of controllability. Considering the cost of redundant design, we should choose BBS (betweenness-based strategy) or DBS (degree based strategy) for node backup and HDF(high degree first) for redundancy edge backup. Above all, our proposed strategies are feasible and effective at improving the robustness of interdependent network controllability.

19 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
QSQingran Su
Qingran Su
XLXingze Li
Xingze Li
YRYuming Ren
Yuming Ren
Ruinan QiuRuinan Qiu
Ruinan Qiu
CHChunming Hu
Chunming Hu
Yongfeng YinYongfeng Yin
Yongfeng Yin
Continuous integration (CI), a crucial technology for accelerating software delivery, employs prioritization methods to optimize testing efficiency. Reinforcement-learning-based prioritization techniques of test cases can dynamically adjust the prioritization strategy based on test feedback. However, existing reinforcement learning models either use feature information from individual test cases or the complete feature of all test cases as input. The model’s input is fixed and does not vary based on the characteristics of the test case set. This leads to the model’s inability to handle various ranking scenarios in CI. In this paper, we propose a novel Attention Transfer Reinforcement Learning for Test Case Prioritization (ATRL-TCP) method. ATRL-TCP first leverages the richness of historical information and error rates to assess the test case set. It then determines whether the model’s input should be the feature information of a single test case or the relative order between them. This method allows for the shifting of focus based on the dataset characteristics. We validate the method on four industrial datasets and examine the impact of historical information length and error rate on its performance. The results demonstrate that ATRL-TCP has good generalization ability and achieves good ranking performance within an acceptable time.