检索结果-内蒙古大学图书馆

A meta-reinforcement learning method for adaptive payload transportation with variations

Neurocomputing 2025年 638卷

作者： Chen, Jingyu Ma, Ruidong Xu, Meng Candan, Fethi Mihaylova, Lyudmila Oyekan, John Institute of Software Chinese Academy of Sciences Beijing China Department of Automatic Control and Systems Engineering The University of Sheffield Sheffield United Kingdom School of Information Technology & Management University of International Business and Economics Beijing China Department of Computer Science University of York York United Kingdom

The safe transport of cable-suspended payloads by a group of Unmanned Aerial Vehicles (UAVs) depends on their capacity to effectively respond to fluctuations in the dynamics caused by external variations, such as wind gusts. For group transportation with obstacles, internal variations, such as changes in formation, can also alter the space occupancy of the system related to collision detection. However, traditional adaptive learning methods are challenging to adapt to these two variations. In this paper, we present a learning-based method for collision-free dual-UAV–payload transportation in the presence of varied wind force and formation change. It consists of an adaptive trajectory tracking controller based on meta-model-based reinforcement learning with online adaptation and a novel correction policy, and a path planner that can sample collision-free goal states of the system for the controller based on the meta-collision predictor. The simulation results demonstrate that the proposed trajectory tracking controller outperforms state-of-the-art model-free, model-based, and variational inference methods in terms of payload tracking error reduction and robustness when dealing with the variations mentioned above. Specifically, the proposed controller reduces the average payload tracking error to less than 0.1 metres in most tasks without obstacles. Furthermore, by following the adapted paths generated by the path planner, the trajectory tracking controller can effectively track the payload while ensuring collision-free safety of the dual-UAV–payload system during navigation among obstacles. The success rate of the proposed method is more than 80% in all scenarios with obstacles. Our project website can be seen at https://***/view/meta-payload-fly/ and the source code is available at https://***/wawachen/Meta-load-fly. © 2025

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Images

arXiv

引用

arXiv 2025年

作者： Feng, Fuxiang Cong, Runmin Wei, Shoushui Zhang, Yipeng Li, Jun Kwong, Sam Zhang, Wei The School of Control Science and Engineering Shandong University Jinan250061 China The Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan250061 China The University of California Los Angeles United States The Hubei Key Laboratory of Intelligent Geo-Information Processing The School of Computer Science China University of Geo-sciences Wuhan430078 China The Lingnan University Hong Kong

Reconstructing Hyperspectral Images (HSI) from RGB images can yield high spatial resolution HSI at a lower cost, demonstrating significant application potential. This paper reveals that local correlation and global continuity of the spectral characteristics are crucial for HSI reconstruction tasks. Therefore, we fully explore these inter-spectral relationships and propose a Correlation and Continuity Network (CCNet) for HSI reconstruction from RGB images. For the correlation of local spectrum, we introduce the Group-wise Spectral Correlation Modeling (GrSCM) module, which efficiently establishes spectral band similarity within a localized range. For the continuity of global spectrum, we design the Neighborhood-wise Spectral Continuity Modeling (NeSCM) module, which employs memory units to recursively model the progressive variation characteristics at the global level. In order to explore the inherent complementarity of these two modules, we design the Patch-wise Adaptive Fusion (PAF) module to efficiently integrate global continuity features into the spectral features in a patch-wise adaptive manner. These innovations enhance the quality of reconstructed HSI. We perform comprehensive comparison and ablation experiments on the mainstream datasets NTIRE2022 and NTIRE2020 for the spectral reconstruction task. Compared to the current advanced spectral reconstruction algorithms, our designed algorithm achieves State-Of-The-Art (SOTA) performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint high-resolution feature learning and vessel-shape aware convolutions for efficient vessel segmentation

引用

computers in Biology and Medicine 2025年 191卷 109982-109982页

作者： Zhang, Xiang Zhu, Qiang Hu, Tao Guo, Song Bian, Genqing Dong, Wei Hong, Rao Lin, Xia Ling Wu, Peng Zhou, Meili Yan, Qingsen Mohi-ud-din, Ghulam Ai, Chen Li, Zhou College of Information and Control Engineering Xi'an University of Architecture and Technology Xi'an China Shaanxi Provincial Key Lab of Bigdata of Energy and Intelligence Processing School of Physics and Electronic Information Yanan University Yanan China School of Computer Science and Engineering Northwestern Polytechnical University Xi'an China School of Software Nanchang University Nanchang China School of Cyber Security Zhejiang University Hangzhou China Department of Basic Education and Research Jiangxi Police College Nanchang China Northwestern Polytechnical University China

Clear imagery of retinal vessels is one of the critical shreds of evidence in specific disease diagnosis and evaluation, including sophisticated hierarchical topology and plentiful-and-intensive capillaries. In this work, we propose a new topology- and shape-aware model named Multi-branch Vessel-shaped Convolution Network (MVCN) to adaptively learn high-resolution representations from retinal vessel imagery and thereby capture high-quality topology and shape information thereon. Two steps are involved in our pipeline. The former step is proposed as Multiple High-resolution Ensemble Module (MHEM) to enhance high-resolution characteristics of retinal vessel imagery via fusing scale-invariant hierarchical topology thereof. The latter is a novel vessel-shaped convolution that captures the retinal vessel topology to emerge from unrelated fundus structures. Moreover, our MVCN of separating such topology from the fundus is a dynamical multiple sub-label generation via using epistemic uncertainty, instead of manually separating raw labels to distinguish definitive and uncertain vessels. Compared to other existing methods, our method achieves the most advanced AUC values of 98.31%, 98.80%, 98.83%, and 98.65%, and the most advanced ACC of 95.83%, 96.82%, 97.09%,and 96.66% in DRIVE, CHASE_DB1, STARE, and HRF datasets. We also employ correctness, completeness, and quality metrics to evaluate skeletal similarity. Our method's evaluation metrics have doubled compared to previous methods, thereby demonstrating the effectiveness thereof. © 2025 Elsevier Ltd

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

A 3D-printed smartphone-based platform for in-situ and rapid monitoring of aquaculture pathogens using polydimethylsiloxane (PDMS) microchip with multiplex loop-mediated isothermal amplification (M-LAMP)

Biosensors and Bioelectronics: X

引用

Biosensors and Bioelectronics: X 2025年 25卷

作者： Li, Liyan Fu, Jing Ching Chiang, Elaine Li Yoo, Jerald Bae, Sungwoo Department of Civil and Environmental Engineering National University of Singapore Singapore Key Laboratory of Organic Compound Pollution Control Engineering School of Environmental and Chemical Engineering Shanghai University China Yong Loo Lin School of Medicine National University of Singapore Singapore Department of Electrical and Computer Engineering Seoul National University South Korea Department of Environmental Engineering Korea University South Korea

Aquaculture pathogens pose serious risks to aquatic livestock and global food safety. Key threats in shrimp farming include white spot syndrome virus (WSSV), Vibrio parahaemolyticus (causing acute hepatopancreatic necrosis disease, AHPND), and Enterocytozoon hepatopenaei (EHP). Rapid, on-site detection is critical for early detection and outbreak prevention. In this study, we developed a portable, smartphone-based diagnostic platform utilizing multiplex loop-mediated isothermal amplification (LAMP) for simultaneous detection of multiple pathogens in a single reaction. A PDMS microchip with 30 reaction wells (5 × 6 array) and a temperature control well was fabricated for efficient multiplexing. Immobilized LAMP reagents with freeze-drying lyophilization were preloaded into wells to streamline preparation and enhance stability. The system successfully identified both waterborne indicator bacteria (E. coli, E. faecalis, Salmonella) and major shrimp pathogens (WSSV, AHPND, EHP) in samples from Penaeus vannamei, Penaeus monodon, and aquaculture water. The microchip maintained stable isothermal conditions (65.1 ± 0.6 °C), enabling visual detection via color change at low DNA concentrations (as low as 4 copies/μL). All WSSV and EHP infections in shrimp tissues and water samples were correctly identified using LAMP reaction within 35 min (excluding the DNA extraction process), demonstrating 100% positive detection rates. The smartphone interface allowed real-time imaging and result interpretation, offering a rapid, user-friendly tool for in situ pathogen monitoring. This platform represents a practical, low-cost solution for field diagnostics and improved disease management in aquaculture. © 2025 The Authors

关键词： Lyophilized primers Multiplex LAMP Pathogen detection PDMS microchip Rapid and on-site detection Smartphone-based diagnostics

来源：评论

学校读者我要写书评

暂无评论

Hybrid dimension-based analysis of the energy, exergy, and dynamic response of cross-flow SOFC-CHP system

引用

Applied Thermal engineering 2025年 274卷

作者： Xia, Lei Madonski, Rafal Sun, Li National Engineering Research Center of Power Generation Control and Safety School of Energy and Environment Southeast University Nanjing210096 China Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology ul. Akademicka 16 Gliwice44-100 Poland

Some of the solid oxide fuel cell (SOFC) poly-generation systems currently have the problem of high exergy destruction of the air-side heat exchangers, which exceeds that of SOFC. Meanwhile, there are fewer studies on the variable distribution of key components, especially the dynamic distribution characteristics. In this study, a combined heat and power (CHP) system integrating a cross-flow SOFC, an organic Rankine cycle (ORC), and a heating unit is proposed, and distributed parameter modeling is applied to develop a dynamic mechanism model for a two-dimensional cross-flow SOFC and a one-dimensional methane reformer. Then the steady state performance and dynamic response characteristics of the system and key components are comprehensively analyzed. The results show that the total exergy destruction of the air-side heat exchangers is always lower than that of the SOFC under each operating condition. The maximum temperature and current density of SOFC are located at nodes (8,8) and (5,8), respectively. With the increase in fuel utilization (FU), the total system efficiency increases and then decreases, peaking at 83.36 %. Increases in SOFC internal reforming rate and the decrease in inlet gas temperature exacerbate the SOFC temperature distribution non-uniformity. A step change in current causes rapid fluctuations in system performance and in the internal variables of the SOFC. A step change in air flow first changes the cathode oxygen concentration, causing voltage changes. The current density variation trends at each node of the SOFC are different depending on the reactant concentration and temperature. © 2025

关键词： Cross-flow Distributed parameter modeling Dynamic responses Exergy analysis Solid oxide fuel cell

来源：评论

学校读者我要写书评

暂无评论

Outage Analysis of RSMA Enabled Integrated Satellite-Terrestrial Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Hu, Chenbo Yang, Hongjuan Zhou, Zhiquan Li, Bo Jiang, Xu Zhao, Nan Nallanathan, Arumugam Weihai264209 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Department of Electronic Engineering Kyung Hee University Yongin-si Gyeonggi-do 17104 China

Rate splitting multiple access (RSMA) has emerged in the integrated satellite-terrestrial networks (ISTNs). However, the satellite-terrestrial channel suffers serious shadow fading and cannot maintain stable communication links effectively. From the perspective of reliability, this correspondence takes the lead in focusing on the outage probability (OP) of ISTNs based on the combination of RSMA and hybrid automatic repeat request with chase combining (HARQ-CC). The lower and upper bounds of OP are derived firstly according to the inclusion-exclusion principle. Then, the diversity order is deduced, pointing out the conditions for full time diversity. Monte Carlo simulations confirm the accuracy of the theoretical results, and superior outage performance of HARQ-CC-aided RSMA is present compared with benchmarks. © 1967-2012 IEEE All rights reserved.

关键词： Satellite links

来源：评论

学校读者我要写书评

暂无评论

Battery State of Energy Estimation Method Based on Conditional Selection Neural Network Model 8th

Battery State of Energy Estimation Method Based on Condition...

引用

8th International Conference on Life System Modeling and Simulation, LSMS 2024 and 8th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2024

作者： Liu, Kaituo Li, Yihuan Peng, Qiao School of Control and Computer Engineering North China Electric Power University Beijing102206 China Group of Information Technology Analytics and Operations Queen’s University Belfast BelfastBT9 5EE United Kingdom

ISBN: (纸本)9789819602315

There are differences in the discharge data of batteries at different life stages. Considering these differences, this paper proposes a conditional selection neural network model for estimating the SOE. It can flexibly select the appropriate network for prediction based on a set selection mechanism under different conditions, thereby improving the model’s applicability and generalization ability. Firstly, the concept of Squeeze-and-Excitation is incorporated into the CNN and the resulting SE-CNN model is pretrained. Next, a selection mechanism is designed according to the degree of battery aging, thus the training data is divided into four parts based on the number of discharge cycles to further train the pre-trained network to form a "four-in-one" CS-SE-CNN model. During SOE estimation, the CS-SE-CNN model selects the prediction network based on the number of discharge cycles in the input data. The results demonstrate that the proposed method exhibits high accuracy and robustness in estimating the SOE of lithium-ion batteries. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

SIBW: A Swarm Intelligence-Based Network Flow Watermarking Approach for Privacy Leakage Detection in Digital Healthcare Systems

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Qiao, Sibo Guo, Qiang Shi, Fengdong Wang, Min Zhu, Haohao Khan, Fazlullah Rodrigues, Joel J.P.C. Lyu, Zhihan School of Software Tiangong University Tianjin300387 China School of Artificial Intelligence Tiangong University Tianjin300387 China National Demonstration Center for Experimental Engineering Training Education Tiangong University Tianjin300387 China School of Life Sciences Tiangong University Tianjin300387 China School of Control Sciences and Engineering Tiangong University Tianjin300387 China School of Computer Science Faculty of Science and Engineering University of Nottingham Ningbo China Zhejiang Ningbo315104 China Higher School of Technology Amazonas State University Amazonas Manaus69050-010 Brazil Department of Game Design Faculty of Arts Uppsala University Uppsala Sweden

The exponential growth of sensitive patient information and diagnostic records in digital healthcare systems has increased the complexity of data protection, while frequent medical data breaches severely compromise system security and reliability. Existing privacy protection techniques often lack robustness and real-time capabilities in high-noise, high-packet-loss, and dynamic network environments, limiting their effectiveness in detecting healthcare data leaks. To address these challenges, we propose a Swarm Intelligence-Based Network Watermarking (SIBW) method for real-time privacy data leakage detection in digital healthcare systems. SIBW integrates fountain codes with outer error correction codes and employs a Multi-Phase Synergistic Swarm Optimization Algorithm (MPSSOA) to dynamically optimize encoding parameters, significantly enhancing the robustness and interference resistance of watermark detection. Additionally, a reliable synchronization sequence and lightweight embedding mechanism are designed to ensure adaptability to complex, dynamic networks. Experimental results demonstrate that SIBW achieves over 90% detection accuracy under high latency jitter and packet loss conditions, surpassing existing methods in both robustness and efficiency. With a compact design of only 3.7 MB, SIBW is particularly suited for rapid deployment in resource-constrained digital healthcare systems. © 2013 IEEE All rights reserved.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Model Reference Adaptive Stabilizing control for Leader-following Consensus

引用

IEEE Transactions on Automatic control 2025年

作者： Yue, Dongdong Shi, Jiantao Shi, Ling Frasca, Paolo Baldi, Simone Nanjing Tech University College of Electrical Engineering and Control Science Nanjing211816 China Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay China Univ. Grenoble Alpes Cnrs Inria Grenoble Inp GIPSALab Grenoble38000 France Southeast University School of Mathematics Nanjing210096 China

Complex networks, neuroscience, and other applications have shown examples of multi-agent adaptive systems that must follow (over possibly short times) reference dynamics that are neither Hurwitz nor neutrally stable. However, such leader-following behavior would be impossible with existing adaptive consensus methods, e.g., based on model reference adaptive control (MRAC), since the stability of the reference dynamics is required. To fill this gap, we propose a novel model reference adaptive stabilizing control (MRASC) framework for leader-following consensus of multi-agent systems with unknown and heterogeneous dynamics. Differently from several approaches in the leader-following consensus literature, the proposed framework is free of any extra distributed observer layer for the leader's signal, as the reconstruction of such signals is intrinsic in the adaptive laws. Besides, the framework does not require Hurwitz or neutral stability of the leader and generalizes existing acyclic requirements on the communication graph among the follower. Starting from any weakly connected communication digraph, the proposed method allows to derive a lower bound, useful from the network design point of view, for the minimum number of followers that should be pinned by the leader. © 2025 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：