检索结果-内蒙古大学图书馆

Tightly coupled stereo vision-inertial odometry based on point and line feature

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第1期36卷

作者： Peng, Gang Cao, Yihao Chen, Shanliang Guo, Yubo He, Dingxin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Minist Educ China Engn Res Ctr Autonomous Intelligent Unmanned Syst Wuhan 430074 Peoples R China

To improve the accuracy and robustness of visual simultaneous localization and mapping (SLAM) in low-texture environments, this paper proposes a robust and fast stereo vision inertial SLAM pose estimation method that combines point and line features with an inertial measurement unit (IMU). The method tightly couples visual point and line features with IMU constraints, forming a least-squares problem through the error of each constraint term for nonlinear optimization. To address the issues of over-segmentation and time consumption in traditional line segment detection (LSD) algorithms, an improved LSD algorithm is adopted to accelerate line feature extraction. This approach merges nearby line segments based on spatial geometric relationships and filters out invalid segments, improving the time efficiency of the algorithm. Finally, experiments conducted in low-texture environments demonstrate that our algorithm achieves high localization accuracy and robustness.

关键词： line feature pose measurement tightly coupled real time visual-inertial odometry

来源：评论

学校读者我要写书评

暂无评论

Spatial Distillation based Distribution Alignment (SDDA) for Cross-Headset EEG Classification

arXiv

引用

arXiv 2025年

作者： Liu, Dingkun Li, Siyang Wang, Ziwei Li, Wei Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518000 China

A non-invasive brain-computer interface (BCI) enables direct interaction between the user and external devices, typically via electroencephalogram (EEG) signals. However, decoding EEG signals across different headsets remains a significant challenge due to differences in the number and locations of the electrodes. To address this challenge, we propose a spatial distillation based distribution alignment (SDDA) approach for heterogeneous cross-headset transfer in non-invasive BCIs. SDDA uses first spatial distillation to make use of the full set of electrodes, and then input/feature/output space distribution alignments to cope with the significant differences between the source and target domains. To our knowledge, this is the first work to use knowledge distillation in cross-headset transfers. Extensive experiments on six EEG datasets from two BCI paradigms demonstrated that SDDA achieved superior performance in both offline unsupervised domain adaptation and online supervised domain adaptation scenarios, consistently outperforming 10 classical and state-of-the-art transfer learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Multi-View Contrastive Network (MVCNet) for Motor imagery Classification

arXiv

引用

arXiv 2025年

作者： Wang, Ziwei Li, Siyang Chen, Xiaoqing Li, Wei Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518000 China

Objective: An electroencephalography (EEG)-based brain-computer interface (BCI) serves as a direct communication pathway between the human brain and an external device. While supervised learning has been extensively explored for motor imagery (MI) EEG classification, small data quantity has been a key factor limiting the performance of deep feature learning. Methods: This paper proposes a knowledge-driven time-space-frequency based multi-view contrastive network (MVCNet) for MI EEG decoding in BCIs. MVCNet integrates knowledge from the time, space, and frequency domains into the training process through data augmentations from multiple views, fostering more discriminative feature learning of the characteristics of EEG data. We introduce a cross-view contrasting module to learn from different augmented views and a cross-model contrasting module to enhance the consistency of features extracted between knowledge-guided and data-driven models. Results: The combination of EEG data augmentation strategies was systematically investigated for more informative supervised contrastive learning. Experiments on four public MI datasets and three different architectures demonstrated that MVCNet outperformed 10 existing approaches. Significance: Our approach can significantly boost EEG classification performance beyond designated networks, showcasing the potential to enhance the feature learning process for better EEG decoding. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Finite-time sliding-mode control for semi-Markov systems with delayed impulses

引用

IEEE/CAA Journal of Automatica Sinica 2025年

作者： Ren, Fangmin Wang, Xiaoping Li, Yangmin Zeng, Zhigang The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Hubei Key Laboratory of Braininspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China The Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong999077 Hong Kong

来源：评论

学校读者我要写书评

暂无评论

A dynamic multi-objective optimization approach for integrated timetabling and vehicle scheduling

引用

Swarm and Evolutionary Computation 2025年 95卷

作者： Shen, Yindong Xie, Wenliang Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The MOE Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China

Dynamic integrated timetabling and vehicle scheduling (D-ITVS) is essential for mitigating the negative impacts of service disruptions arising from the stochastic nature of traffic flow and passenger demand fluctuations in public transit. Existing optimization approaches for the D-ITVS problem typically conduct optimization independently at each rescheduling stage. In contrast, this paper proposes a novel dynamic multi-objective optimization approach that considers evolving patterns across different rescheduling stages from a holistic perspective. This approach formulates the optimization problem for all rescheduling stages during a day's operation as a dynamic multi-objective optimization problem, modeled using a dynamic time-space network flow framework. To leverage these evolving patterns for achieving optimal solutions throughout, a dynamic multi-objective optimization approach for the D-ITVS problem (DMO-TVS) is introduced. The DMO-TVS approach learns the evolving patterns, and incorporates a dynamic solution representation alongside three key mechanisms: (1) change detection mechanism, (2) change response mechanism, and (3) multi-objective optimization mechanism. These mechanisms work in tandem to dynamically adjust the initial solution set at each rescheduling stage based on predicted optimal solutions derived from learned evolving patterns, balance conflicting objectives in the D-ITVS problem, and select optimal solutions with diversity throughout the optimization process. Experimental results demonstrate that the dynamic multi-objective optimization approach is capable of generating timetables and vehicle schedules with reduced costs, enhanced robustness, and improved convergence and diversity across all rescheduling stages. By balancing operational costs and passenger service quality, these improvements benefit transit operators, and during daily operations, passengers enjoy reduced travel costs and enhanced service reliability. © 2025

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A CFD model for analyzing multiphysics coupling and efficiency optimization in a PEMEC

引用

JOURNAL OF POWER SOURCES 2025年 625卷

作者： Hu, Chenyang Wang, Jingjing Xu, Yuanwu Fu, Xiaowei Deng, Zhonghua Kim, Jung-Sik Li, Xi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Educ Minist Wuhan 430074 Hubei Peoples R China Shenzhen Huazhong Univ Sci & Technol Res Inst Shenzhen 518055 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Wuhan Huamao Automat Co Ltd Wuhan 430205 Hubei Peoples R China Beihang Univ Sch Gen Engn Beijing 100191 Peoples R China

Proton exchange membrane electrolysis cell (PEMEC) is a promising hydrogen energy storage technology, which is very suitable for energy scheduling in microgrids. The multiple physical fields inside it are affected by many factors and form complex coupling states. In electrolysis, this complexity manifests as uneven distribution of temperature, current density, and liquid water volume fraction, which can lead to local hot spots, reactant starvation, and performance degradation. These challenges pose a threat to PEMEC's service life and operational safety in microgrid systems. Although several studies have explored their Computational Fluid Dynamics (CFD) modeling, the effects of certain operating parameters on their performance are unclear, and few studies have effectively evaluated energy efficiency, which is key to optimizing the operating conditions of the PEMEC system. Therefore, this study is employing a 2D (two dimensional) multiphysics model to investigate the electrochemical processes within PEMEC. The model's validity is being confirmed through comparison with electrochemical experimental data. Subsequently, the effects of applied voltage, anode inlet flow rate, and cathode inlet flow rate on the multiphysics are being examined, and trends in efficiency changes are being analyzed. Moreover, by optimizing operational conditions, maximum energy efficiency (79.0 %) can be achieved. This study is laying the groundwork for future investigations into control strategies and multi-objective optimization, and promoting the application of PEMEC in energy scheduling.

关键词： Multiphysical modeling Proton exchange membrane electrolyzer optimization Energy efficiency optimization PEM electrolyzer performance

来源：评论

学校读者我要写书评

暂无评论

Advancing facility accessibility analysis across hierarchies and scales in mainland China

引用

APPLIED GEOGRAPHY 2025年 179卷

作者： Zhang, Hui Zhu, Yutong Du, Chongyang Hong, Liu Ouyang, Min Xu, Min Wuhan Univ Sch Informat Management Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Dongbei Univ Finance & Econ Sch Publ Adm Dalian 116025 Liaoning Peoples R China

With rapid urbanization and the expansion of national transportation system, versatile service facilities have emerged, ranging from urban services meeting daily needs to national facilities catering to specialized demands. Ensuring efficient and equitable access to multi-level facilities is critical for promoting a nation's sustainable development. Despite extensive research on urban facility accessibility, an integrative assessment of multi-level facility access-particularly inter-regional access to national facilities-remains underexplored. To fill this gap, this study proposes a nationwide hierarchical classification system, categorizing facilities into three levels-urban, provincial, and national-based on service range and spatial distribution. Tailored accessibility calculation methods are developed for each level, incorporating road, rail, and air transport. Results from mainland China reveal stark disparities across facility levels: Urban healthcare services exhibit the highest accessibility but significant spatial inequality, whereas national-level theme parks show the lowest accessibility yet the highest spatial equality. Additionally, accessibility determinants display a hierarchical pattern: facility density dominates urban facility accessibility, while administrative area size and GDP govern access to provincial and national facilities, respectively. Furthermore, HSR and air transport enhance access to national facilities while reducing inequality. These findings provide actionable insights for optimizing facility distribution and accessibility across hierarchical spatial scales.

关键词： Facility accessibility Cross-hierarchy Multi-scale Multi-modal transport

来源：评论

学校读者我要写书评

暂无评论

Multimodal Brain-Computer Interfaces: AI-powered Decoding Methodologies

arXiv

引用

arXiv 2025年

作者： Li, Siyang Wang, Hongbin Chen, Xiaoqing Wu, Dongrui The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Henan Key Laboratory of Brain Science and Brain Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University China

Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices. This review highlights the core decoding algorithms that enable multimodal BCIs, including a dissection of the elements, a unified view of diversified approaches, and a comprehensive analysis of the present state of the field. We emphasize algorithmic advancements in cross-modality mapping, sequential modeling, besides classic multi-modality fusion, illustrating how these novel AI approaches enhance decoding of brain data. The current literature of BCI applications on visual, speech, and affective decoding are comprehensively explored. Looking forward, we draw attention on the impact of emerging architectures like multimodal Transformers, and discuss challenges such as brain data heterogeneity and common errors. This review also serves as a bridge in this interdisciplinary field for experts with neuroscience background and experts that study AI, aiming to provide a comprehensive understanding for AI-powered multimodal BCIs. © 2025, CC BY-NC-ND.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Autonomous Path Planning via Sand Cat Swarm Optimization With Multi-Strategy Mechanism for Unmanned Aerial Vehicles in Dynamic Environment

引用

IEEE Internet of Things Journal 2025年

作者： Deng, Wu Feng, Jiayi Zhao, Huimin Civil Aviation University of China College of Electronic Information and Automation Tianjin300300 China Civil Aviation University of China Tianjin Key Lab Intelligent Signal and Image Processing Tianjin300300 China State Key Laboratory of Rail Transit Vehicle System of Southwest Jiaotong University Chengdu610031 China

Unmanned Aerial Vehicles (UAVs) face critical challenges in path planning in dynamic environment. Sand Cat Swarm Optimization (SCSO) algorithm has demonstrated promise in addressing complex optimization challenges. However, SCSO is limited by slow convergence, susceptibility to local optima, and insufficient adaptability. To overcome these shortcomings, an enhanced SCSO with the spiral search, Livy flight, tent chaotic mapping, and adaptive sparrow alert mechanism, namely TSLS-SCSO is developed to propose an autonomous path planning method for UAVs in dynamic environment. In TSLS-SCSO, a new population initialization strategy with tent chaotic mapping is designed to achieve a large dynamic range and coverage capability. Then a new spiral search strategy is designed to broaden the search range in the search phase. And a new Livy flight strategy is employed to enrich the diversity of population in the attacking prey phase. A new sparrow alert mechanism with integrating the sand cat group with the sparrow alert is designed to obtain faster convergence speed and accuracy. The experiment results on CEC 2017 and CEC 2022 show that the TSLS-SCSO obtains higher accuracy and more stable solutions and exhibits better competitiveness. Furthermore, the proposed UAV path planning method successfully found effective paths with an obstacle avoidance effectiveness of 95.5%. The obtained results validate the effectiveness and competitiveness of TSLS-SCSO in UAV path planning in the dynamic environment. © 2014 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Flocking with nonlinear systems based on distributed observers

引用

NEUROCOMPUTING 2025年 619卷

作者： Chi, Jun An, Qing Wang, Xiaoling Su, Housheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Minist China Luoyu Rd 1037 Wuhan 430074 Hubei Peoples R China Wuchang Univ Technol Articial Intelligence Sch 16 Jiangxia Ave Wuhan 430223 Hubei Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Wenyuan Rd 9 Nanjing 210023 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Wenyuan Rd 9 Nanjing 210023 Jiangsu Peoples R China

This paper investigates the output feedback-based flocking control problem for nonlinear dynamical systems (NDSs). To address this, distributed observers and consensus-based leader-following control algorithms are incorporated into each sensor in the network. By combining state estimation with flocking control algorithms, the observed state information of the NDS serves as the virtual leader for each sensor. To handle scenarios involving obstacles, we propose enclosing obstacles of various shapes within circles and developing a flocking control algorithm using artificial potential functions. Simulation results validate the effectiveness of the proposed algorithm.

关键词： Nonlinear observers Flocking Mobile sensor network Output feedback

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：