检索结果-内蒙古大学图书馆

Solar Compass 2025年 14卷

作者： Nkouna Paul Lionnel, Ella Obono Biyobo, Arnaud Owoundi Etouke, Paul Dangwe Sounsoumou, Yves Paulin Jean Jacques Molu, Reagan Dzonde Naoussi, Serge Raoul Computer and Automatic Engineering Research Laboratory ENSET University of Douala Douala Cameroun PB: 1872 Douala Cameroon Faculty of Science Renewable Energies Department University of Garoua Garoua Cameroon PB 346 Garoua Cameroon Technologies and Applied Sciences Laboratory University Institute of Technology of Douala University of Douala P.O. Box: 8689 Douala Cameroon

This paper proposes a Maximum Power Point Tracking (MPPT) strategy for a photovoltaic (PV) panel, combining the Perturb and Observe (P&O) technique, Particle Swarm Optimization (PSO), and an optimal Duty Cycle Modulation (DCM) circuit. The Boost chopper, regulated by a Proportional-Integral-Derivative controller with a first-order low-pass filter (PIDF), serves as an interface between the photovoltaic source (PV) and the load, maximizing the extraction of energy produced by the solar panel. The results obtained in virtual simulation in the MATLAB/Simulink environment are satisfactory: we observe in standard conditions, namely temperature T = 25 °C and solar irradiation of 1000W/m², a response without overshoot, a zero static error, a system stability time of 0.32 s, 0.13 s and 0.15 s respectively for three respective load values (R₀ = 50 Ω, R₀₁ = 37.5 Ω and R₀₂ = 25 Ω) in steady state. In transient state, taking into account the variation in solar irradiation, it can be seen that despite the fluctuations, the system manages to remain stable, attesting to the robustness of the controller used. To control the DCM Boost chopper. The comparative study carried out with other MPPT techniques such as (VSS-P&O, MIC, FOCV, FSS-RBFA, VSS-RBFA, AFLC, PSO and CS) applied to conventional boost converters attests that the proposed new prototype offers quite satisfactory performances compared to the latter. © 2025 The Author(s)

关键词： DCM (duty cycle modulation) LQR (linear quadratic regulator) P&O (Perturb and Observe) PIDF (Proportional, Integral, Derivative with low-pass Filter) PSO (Particle Swarm Optimization)

来源：评论

学校读者我要写书评

暂无评论

Dexterous Manipulation through Imitation Learning: A Survey

arXiv

引用

arXiv 2025年

作者： An, Shan Meng, Ziyu Tang, Chao Zhou, Yuning Liu, Tengyu Ding, Fangqiang Zhang, Shufang Mu, Yao Song, Ran Zhang, Wei Hou, Zeng-Guang Zhang, Hong School of Electrical and Information Engineering Tianjin University Tianjin300072 China School of Control Science and Engineering Shandong University Jinan250061 China State Key Laboratory of General Artificial Intelligence Beijing100086 China Department of Mechanical and Process Engineering ETH Zurich Zurich8092 Switzerland Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China School of Informatics University of Edinburgh EH8 9AB United Kingdom Department of Computer Science University of Hong Kong 999077 Hong Kong State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology 999078 China

Dexterous manipulation, which refers to the ability of a robotic hand or multi-fingered end-effector to skillfully control, reorient, and manipulate objects through precise, coordinated finger movements and adaptive force modulation, enables complex interactions similar to human hand dexterity. With recent advances in robotics and machine learning, there is a growing demand for these systems to operate in complex and unstructured environments. Traditional model-based approaches struggle to generalize across tasks and object variations due to the high-dimensionality and complex contact dynamics of dexterous manipulation. Although model-free methods such as reinforcement learning (RL) show promise, they require extensive training, large-scale interaction data, and carefully designed rewards for stability and effectiveness. Imitation learning (IL) offers an alternative by allowing robots to acquire dexterous manipulation skills directly from expert demonstrations, capturing fine-grained coordination and contact dynamics while bypassing the need for explicit modeling and large-scale trial-and-error. This survey provides an overview of dexterous manipulation methods based on imitation learning (IL), details recent advances, and addresses key challenges in the field. Additionally, it explores potential research directions to enhance IL-driven dexterous manipulation. Our goal is to offer researchers and practitioners a comprehensive introduction to this rapidly evolving domain. Copyright © 2025, The Authors. All rights reserved.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors

arXiv

引用

arXiv 2025年

作者： Li, Siyu Cao, Yihong Shi, Hao Zang, Yongsheng He, Xuan Yang, Kailun Li, Zhiyong School of Robotics the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Hunan Vanguard Group Corporation Limited Changsha410100 China

The exploration of Bird’s-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of unsupervised domain adaptation models an essential path. However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks. To address this gap, this paper proposes HierDAMap, a universal and holistic BEV domain adaptation framework with hierarchical perspective priors. Unlike existing research that solely focuses on image-level learning using prior knowledge, this paper explores the guiding role of perspective prior knowledge across three distinct levels: global, sparse, and instance levels. With these priors, HierDA consists of three essential components, including Semantic-Guided Pseudo Supervision (SGPS), Dynamic-Aware Coherence Learning (DACL), and Cross-Domain Frustum Mixing (CDFM). SGPS constrains the cross-domain consistency of perspective feature distribution through pseudo labels generated by vision foundation models in 2D space. To mitigate feature distribution discrepancies caused by spatial variations, DACL employs uncertainty-aware predicted depth as an intermediary to derive dynamic BEV labels from perspective pseudo-labels, thereby constraining the coarse BEV features derived from corresponding perspective features. CDFM, on the other hand, leverages perspective masks of view frustum to mix multi-view perspective images from both domains, which guides cross-domain view transformation and encoding learning through mixed BEV labels. Furthermore, this paper introduces intra-domain feature exchange data augmentation to enhance the efficiency of domain adaptation learning. The proposed method is verified on multiple BEV mapping tasks, such as BEV semantic segmentation, high-definition semantic, and vectorized mapping. It demonstrates competitive perfo

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Data-Driven Granular Model for Battery Remaining Useful Life Prediction

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Jing, TaiLong Du, Sheng Wang, Cong Wu, Chao Pedrycz, Witold Sharaf, Mohamed Li, ZhiWu Luoyang Institute of Science and Technology School of Electrical Engineering and Automation Luoyang471023 China China University of Geosciences School of Automation Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Xi’an710072 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland King Saud University College of Engineering Department of Industrial Engineering Riyadh11421 Saudi Arabia Institute of Systems Engineering Macau University of Science and Technology Macau China

Accurate and meaningful prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs) provides a significant guide for the maintenance and management of these LIBs. A singular numerical predictive result by numerous conventional models is insufficient to furnish decision-makers with comprehensive or nuanced insights. To address this issue, predictive RUL results in the form of information granules are essential. In this study, a hybrid data-driven granular model is established for battery RUL prediction with granular (interval-based) quantification for LIBs. This granular model is designed and formulated in a way that it produces comprehensive prediction outcomes realized as information granules, which are expressed in a more descriptive and comprehensive manner. Thus, the resulting information granules can effectively reflect and communicate the confidence associated with the predictions. The granular model is realized in two steps: 1) probabilistic prediction results are produced by a hybrid numeric predictive model and 2) a comprehensive granulation of the probabilistic results is achieved under the principle of information granularity. The granular predictive results are holistically evaluated and optimized by the two associated criteria of granularity (coverage and specificity). This transformation of information granules provides an intuitive and interpretable display for battery maintenance and safe work. The proposed granular model is verified by using an open-access LIBs dataset, and the experimental results demonstrate that the proposed granular model outperforms other comparative methods. © 2025 IEEE. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

HEART: Achieving Timely Multi-Model Training for Vehicle-Edge-Cloud-Integrated Hierarchical Federated Learning

arXiv

引用

arXiv 2025年

作者： Yang, Xiaohong Liwang, Minghui Wang, Xianbin Cheng, Zhipeng Hosseinalipour, Seyyedali Dai, Huaiyu Jiao, Zhenzhen School of Informatics Xiamen University Fujian China Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Japan Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai China Department of Electrical and Computer Engineering Western University ON Canada School of Future Science and Engineering Soochow University Suzhou China Department of Electrical Engineering University at Buffalo-SUNY BuffaloNY United States Department of Electrical and Computer Engineering NC State University RaleighNC United States iF-Labs Beijing Teleinfo Technology Company Ltd. CAICT Beijing China

The rapid growth of AI-enabled Internet of Vehicles (IoV) calls for efficient machine learning (ML) solutions that can handle high vehicular mobility and decentralized data. This has motivated the emergence of Hierarchical Federated Learning over vehicle-edge-cloud architectures (VEC-HFL). Nevertheless, one aspect which is underexplored in the literature on VEC-HFL is that vehicles often need to execute multiple ML tasks simultaneously, where this multi-model training environment introduces crucial challenges. First, improper aggregation rules can lead to model obsolescence and prolonged training times. Second, vehicular mobility may result in inefficient data utilization by preventing the vehicles from returning their models to the network edge. Third, achieving a balanced resource allocation across diverse tasks becomes of paramount importance as it majorly affects the effectiveness of collaborative training. We take one of the first steps towards addressing these challenges via proposing a framework for multi-model training in dynamic VEC-HFL with the goal of minimizing global training latency while ensuring balanced training across various tasks—a problem that turns out to be NP-hard. To facilitate timely model training, we introduce a hybrid synchronous-asynchronous aggregation rule. Building on this, we present a novel method called Hybrid Evolutionary And gReedy allocaTion (HEART). The framework operates in two stages: first, it achieves balanced task scheduling through a hybrid heuristic approach that combines improved Particle Swarm Optimization (PSO) and Genetic Algorithms (GA);second, it employs a low-complexity greedy algorithm to determine the training priority of assigned tasks on vehicles. Experiments on real-world datasets demonstrate the superiority of HEART over existing methods. © 2025, CC BY-NC-ND.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Joint Data Compression and Task Scheduling for LEO Satellite Networks

引用

IEEE Transactions on Vehicular technology 2025年

作者： He, Lijun Li, Shiyin Jia, Ziye Wang, Juncheng Han, Zhu China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Xidian University State Key Laboratory of Integrated Services Networks Shaanxi Xi'an710071 China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing210000 China Hong Kong Baptist University Department of Computer Science China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

We investigate a joint data compression and task scheduling problem for Low Earth Orbit Satellite Networks (LEOSNs), to maximize the sum weights of tasks while simultaneously minimizing the total data loss. First, we propose a novel Multi-Resource Conflict Graph (MRCG) model to characterize the intertwined communication and computation allocation conflicts inherent in typical data offloading processes of LEOSNs. Leveraging the proposed MRCG model, we then formulate the studied problem for LEOSNs as a linear integer program, to maximize the normalized weighted sum of both the sum task weight and the total data loss. We further explore the intrinsic structure of the linear integer program to propose an efficient solution using the Semi-Definite Relaxation (SDR) technique. Finally, the simulation results underscore that the synergistic optimization of data compression and task scheduling significantly facilitates the data offloading efficiency of LEOSNs, and the performances surpass existing benchmarks across a broad range of system parameters. © 1967-2012 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Underwater Perception and Autonomous Operation for Underwater Vehicle-Manipulator Systems: Methodology and Experiment

引用

IEEE/ASME Transactions on Mechatronics 2025年

作者： Jiang, Chaicheng Xiong, Xinyang Xiang, Xianbo Zeng, Zhigang Zhang, Fumin Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan 430074 China Huazhong University of Science and Technology School of Naval Architecture and Ocean Engineering Wuhan 430074 China Huazhong University of Science and Technology School of Naval Architecture and Ocean Engineering School of Artificial Intelligence and Automation State Key Lab of Intelligent Manufacturing Equipment and Technology Wuhan 430074 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control The Education Ministry of China Wuhan 430074 China Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Hong Kong Hong Kong

Camera-equipped underwater vehicle-manipulator systems (UVMS) can achieve autonomous underwater operations through visual servoing. However, current methods excessively rely on auxiliary means for target's visual information and do not sufficiently consider the target's pose when designing visual servoing schemes. As a result, UVMS can only perform dynamic positioning or grasp simple-shaped targets like sea urchins. In this article, we are devoted to making the UVMS autonomously complete more complex underwater operations, such as valve switching and pipe handling. First, an underwater target perception system is proposed to address the issue of discontinuous target position estimation caused by various interferences. Second, a deep neural network-based grasping mechanism controller is proposed to enable the manipulator to grasp targets in various initial poses using the target image. Third, a decoupled visual servoing scheme is proposed for the motion control of the UVMS, and in collaboration with a designed task supervisor to ensure that the UVMS can complete the underwater operation autonomously. To validate the effectiveness of the proposed methods, underwater experiments are conducted based on a UVMS prototype. The UVMS succeeds to autonomously switch different types of valves and handle the pipe. Experiments conducted under dynamic currents validated the reliability and robustness of the proposed methods. © 1996-2012 IEEE.

关键词： Autonomous underwater operations deep neural network underwater vehicle-manipulator systems (UVMS) visual perception visual servoing

来源：评论

学校读者我要写书评

暂无评论

Channel and space-based joint rate allocation algorithm

Channel and space-based joint rate allocation algorithm

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dayong Wang Chao Yuan Yu Sun Xin Lu Hui Guo Frederic Dufaux Ce Zhu Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications China Department of Computer Science University of Central Arkansas Faculty of Computing Engineering and Media (CEM) De Montfort University UK Université Paris-Saclay CNRS CentraleSupélec Laboratoire Des Signaux et Systèmes France School of Information and Communication Engineering University of Electronic Science and Technology of China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Rate control is a critical component for image and video compression Particularly under limited network bandwidth conditions, bitrate control is essential to ensure efficient image transmission by effectively allocation channel resources. In this research, since both Channel and Spatial have relationship with rate allocation, we first propose a joint Channel-wise and Spatial-wise Quantization scheme to determine optimal quantization parameters. Subsequently, we develop a quantization step estimation network to obtain parameters to efficiently allocate rate according to target rate. Experiments demonstrate that our algorithm significantly improve compressed image quality with minimal bitrate distortion and achieve accurate rate control with nearly 3% average bitrate error.

关键词： Image quality Quantization (signal) Image coding Bit rate Signal processing algorithms Estimation Rate-distortion Video compression Resource management Speech processing

来源：评论

学校读者我要写书评

暂无评论

Self-Powered Broadband Photodetectors Based on WS2-Anchored MoS2 with Enhanced Responsivity and Detectivity

引用

Small 2025年第20期21卷 e2502900页

作者： Kumar, Ashok Chakkar, Atul G. Das, Chayan Kumar, Pradeep Sahu, Satyajit Saliba, Michael Kumar, Mahesh Department of Cybernetics Nanotechnology and Data Processing Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland School of Physical Sciences Indian Institute of Technology Mandi Himachal Pradesh Mandi175005 India Department of Physics Indian Institute of Technology Jodhpur Rajasthan Jodhpur342030 India University of Stuttgart Stuttgart70569 Germany Helmholtz Young Investigator Group FRONTRUNNERIEK5-Photovoltaik Forschungszentrum Jülich Jülich52425 Germany Department of Electrical Engineering Indian Institute of Technology Jodhpur Rajasthan Jodhpur342030 India

Self-powered broadband photodetectors utilizing 2D transition metal dichalcogenides (TMDs) are highly promising due to their remarkable light absorption capabilities and high sensitivity, making them suitable for applications such as military surveillance and wireless light detection systems. However, their performance is constrained by inadequate absorption, suboptimal charge carrier separation, and slow response times. In response to these limitations, the study fabricates a self-powered photodetector employing a heterostructure composed of WS2 nanoparticles anchored to CVD-synthesized MoS2, operating within the visible to near-infrared spectrum. The device demonstrates a responsivity of 283 mA W−1 and a detectivity 6.44 × 1012 Jones, alongside an external quantum efficiency of 61% under exposure of 580 nm. In comparison to pristine MoS2, the MoS2-WS2 photodetector exhibited approximately 12-fold and 11-fold enhancements in responsivity and detectivity, respectively, in addition to fast response time of ≈375 µs and 6 ms. Additionally, density functional theory (DFT) calculations are used to analyze the increase in dark current that is observed following WS₂ nanoparticle anchored on MoS₂. This investigation highlights the potential of 2D heterostructures in the development of high-performance broadband photodetectors, which offer improved responsivity, stability, and self-powered operation for advanced optoelectronic applications. © 2025 Wiley-VCH GmbH.

关键词： Layered semiconductors

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：