检索结果-内蒙古大学图书馆

2024 International Conference on Optical and Photonic engineering, icOPEN 2024

作者： Miao, Huisi Liu, Wan Yan, Ziyu Xu, Weidong Zhang, Dongbo Zhang, Hui School of Automation and Electronic Information Xiangtan University Xiangtan411105 China Xiangtan Electric Manufacturing Co..Ltd. Xiangtan411105 China National Engineering Research Center of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

ISBN: (数字)9781510688117

ISBN: (纸本)9781510688100

Traditional fringe projection profilometry (FPP) struggles with robust imaging and high-precision three-dimensional (3D) reconstruction in complex lighting environments with strong inter-reflection. This paper proposes a method combining frequency-shifted fringe projection and epipolar constraint to achieve high-precision 3D profilometry in such scenarios. First, environmental light interference is mitigated and the maximum fringe frequency is reduced through window function analysis (WFA) and a four-step phase-shifting (PS). Then, direct and indirect illumination are separated in the Fourier domain. Direct illumination positions are identified using threshold segmentation and epipolar geometry constraint, enhancing imaging robustness in strong inter-reflection contexts. Experimental results demonstrate that the method constructs direct and indirect illumination feature models, accurately obtaining direct illumination information and eliminating multi-path interference. Additionally, in tests with complex geometrical surfaces, imaging efficiency and robustness significantly improve, with effective point cloud data increasing by over 30% and planar accuracy improving by 50%. © 2025 SPIE.

关键词： Light interference

来源：评论

学校读者我要写书评

暂无评论

A Novel Micro-Defects Imaging system for High-Reflective Material Surfaces

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： He, Zhiyong Lin, Song Xiao, Yafeng Fang, Hao Sun, Lining Soochow University School of Mechatronic Engineering Department of Automation Engineering Suzhou215000 China Robotics and Microsystems Research Center Soochow University Suzhou215000 China Harbin Institute of Technology Institute of Robotics School of Mechatronic Engineering Harbin150000 China

Highly reflective materials, owing to their reflective characteristics, pose challenges in imaging micro-defects under conventional lighting, resulting in a substantial number of missed detections. This paper presents an imaging method tailored for micro-defects on the surfaces of such materials. An investigation into the imaging mechanisms of micro-defects under varying illumination conditions is conducted, leading to the proposal of an edge-light scanning technique. Initially, this technique enhances the contrast of defect imaging optically, yielding a sequence of images with high-contrast defects. Subsequently, a contrast-weighted image synthesis algorithm is introduced to effectively mitigate the interference caused by bright and dark stripe backgrounds. Experimental evaluations of defect detection based on different algorithms demonstrate that the proposed imaging method is applicable to defects of various sizes and significantly improves the detection accuracy of micro-defects. © 2025 IEEE.

关键词： Defect Detection Edge-light Highly Reflective Materials Image Enhancement Image Synthesis Optical system

来源：评论

学校读者我要写书评

暂无评论

Carbon dioxide storage and cumulative oil production predictions in unconventional reservoirs applying optimized machine-learning models

引用

Petroleum Science 2025年第1期22卷 296-323页

作者： Shadfar Davoodi Hung Vo Thanh David A.Wood Mohammad Mehrad Sergey V.Muravyov Valeriy S.Rukavishnikov School of Earth Sciences&Engineering Tomsk Polytechnic UniversityLenin AvenueTomskRussia Laboratory for Computational Mechanics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh CityViet Nam Applied Science Research Center Applied Science Private UniversityAmmanJordan DWA Energy Limited LincolnUK Division for Automation&Robotics Tomsk Polytechnic UniversityLenin AvenueTomskRussia

To achieve carbon dioxide(CO_(2))storage through enhanced oil recovery,accurate forecasting of CO_(2) subsurface storage and cumulative oil production is *** study develops hybrid predictive models for the determination of CO_(2) storage mass and cumulative oil production in unconventional *** does so with two multi-layer perceptron neural networks(MLPNN)and a least-squares support vector machine(LSSVM),hybridized with grey wolf optimization(GWO)and/or particle swarm optimization(PSO).Large,simulated datasets were divided into training(70%)and testing(30%)groups,with normalization applied to both *** distance identifies/eliminates outliers in the training subset only.A non-dominated sorting genetic algorithm(NSGA-II)combined with LSSVM selected seven influential features from the nine available input parameters:reservoir depth,porosity,permeability,thickness,bottom-hole pressure,area,CO_(2) injection rate,residual oil saturation to gas flooding,and residual oil saturation to water *** models were developed and tested,with performance evaluated with an overfitting index(OFI),scoring analysis,and partial dependence plots(PDP),during training and independent testing to enhance model focus and *** LSSVM-GWO model generated the lowest root mean square error(RMSE)values(0.4052 MMT for CO_(2) storage and 9.7392 MMbbl for cumulative oil production)in the training *** trained model also exhibited excellent generalization and minimal overfitting when applied to the testing group(RMSE of 0.6224 MMT for CO_(2) storage and 12.5143 MMbbl for cumulative oil production).PDP analysis revealed that the input features“area”and“porosity”had the most influence on the LSSVM-GWO model's pre-diction *** paper presents a new hybrid modeling approach that achieves accurate forecasting of CO_(2) subsurface storage and cumulative oil *** also establishes a new standard for such forecasting,which can

关键词： Hybrid machine learning Least-squares support vector machine Grey wolf optimization Feature selection Carbon dioxide storage Enhanced oil recovery

来源：评论

学校读者我要写书评

暂无评论

Online Robot Motion Planning Methodology Guided by Group Social Proxemics Feature

arXiv

引用

arXiv 2025年

作者： Mu, Xuan Liu, Xiaorui Guo, Shuai Chi, Wenzheng Wang, Wei Ge, Shuzhi Sam School of Automation Qingdao University Qingdao266000 China School of Automation Qingdao University Qingdao University Qingdao266000 China Robotics and Microsystems Center School of Mechanical and Electric Engineering Soochow University Suzhou215021 China School of Mechanical Engineering & Automation the Robotics Institute Beihang University Beijing100000 China Department of Electrical and Computer Engineering National University of Singapore Singapore117576 Singapore

Nowadays robot is supposed to demonstrate human-like perception, reasoning and behavior pattern in social or service application. However, most of the existing motion planning methods are incompatible with above requirement. A potential reason is that the existing navigation algorithms usually intend to treat people as another kind of obstacle, and hardly take the social principle or awareness into consideration. In this paper, we attempt to model the proxemics of group and blend it into the scenario perception and navigation of robot. For this purpose, a group clustering method considering both social relevance and spatial confidence is introduced. It can enable robot to identify individuals and divide them into groups. Next, we propose defining the individual proxemics within magnetic dipole model, and further established the group proxemics and scenario map through vector-field superposition. On the basis of the group clustering and proxemics modeling, we present the method to obtain the optimal observation positions (OOPs) of group. Once the OOPs grid and scenario map are established, a heuristic path is employed to generate path that guide robot cruising among the groups for interactive purpose. A series of experiments are conducted to validate the proposed methodology on the practical robot, the results have demonstrated that our methodology has achieved promising performance on group recognition accuracy and path-generation efficiency. This concludes that the group awareness evolved as an important module to make robot socially behave in the practical scenario. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulation

arXiv

引用

arXiv 2025年

作者： Fan, Shichao Yang, Quantao Liu, Yajie Wu, Kun Che, Zhengping Liu, Qingjie Wan, Min School of Mechanical Engineering and Automation BeiHang University China School of Computer Science and Engineering BeiHang University China Beijing Innovation Center of Humanoid Robotics China KTH Royal Institute of Technology Sweden

Recently, Vision-Language-Action models (VLA) have advanced robot imitation learning, but high data collection costs and limited demonstrations hinder generalization and current imitation learning methods struggle in out-of-distribution scenarios, especially for long-horizon tasks. A key challenge is how to mitigate compounding errors in imitation learning, which lead to cascading failures over extended trajectories. To address these challenges, we propose the Diffusion Trajectory-guided Policy (DTP) framework, which generates 2D trajectories through a diffusion model to guide policy learning for long-horizon tasks. By leveraging task-relevant trajectories, DTP provides trajectory-level guidance to reduce error accumulation. Our two-stage approach first trains a generative vision-language model to create diffusion-based trajectories, then refines the imitation policy using them. Experiments on the CALVIN benchmark show that DTP outperforms state-of-the-art baselines by 25% in success rate, starting from scratch without external pretraining. Moreover, DTP significantly improves real-world robot performance. All source code and experiment videos will be released upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Switching-Like Event-Based Formation Control for Multi-Agent Systems Against Denial of Service Attacks

引用

IEEE Transactions on Control of Network Systems 2025年

作者： Ru, Tingting Cai, Chenxiao Lin, Hong Rudas, Imre Shi, Peng Nanjing University of Science and Technology School of Automation Nanjing210094 China Shenzhen Polytechnic University Institute of Intelligence Science and Engineering Shenzhen518055 China University Research Innovation and Service Center Óbuda University Antal Bejczy Center for Intelligent Robotics Budapest1034 Hungary University of Adelaide School of Electrical and Mechanical Engineering AdelaideSA5005 Australia

This paper studies formation control for multi-agent systems in the presence of denial-of-service (DoS) attacks. The challenge is to address secure formation tracking and communication bandwidth-saving issues simultaneously. To tackle this, we propose a switching- like event-triggered mechanism that reduces excessive bandwidth consumption during interactions among multiple followers under DoS attacks. The triggering condition is allowed to be switched during the intervals when attacks are activated, ensuring that triggering can normally occur throughout the overall time interval by introducing an auxiliary variable depending on the success of the latest trigger moment. Based on this approach, we construct an event-based time-varying formation control scheme. Additionally, we establish sufficient conditions that reveal the relationship between exponential stability and the frequency/duration of the DoS attacks. Unlike other single-leader methods, a significant feature of the formation control scheme is its ability to achieve the desired formation tracking for multi-agent systems with multiple leaders. Finally, the validity of the proposed method is demonstrated through simulation and experimental results. © 2014 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Minimizing Long-Term Energy Consumption in RIS-Assisted UAV-Enabled MEC Network

引用

IEEE Internet of Things Journal 2025年

作者： Yao, Zheng Zhu, Qiwu Zhang, Yanhui Huang, Haibo Luo, Min Hubei University of Automotive Technology School of Robotics and Automation Shiyan442002 China Hong Kong Polytechnic University National Rail Transit Electrification and Automation Engineering Technology Research Center Hong Kong Branch Hongkong999077 Hong Kong Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen517085 China

In recent years, Unmanned Aerial Vehicles (UAVs) are increasingly becoming flight-based communicative and computing platforms, but the scarcity of communication resources can significantly hinder their performance and scalability. Therefore, this paper proposes a Reconfigurable Intelligent Surface (RIS)-assisted UAV-enabled Mobile Edge Computing (MEC) network, aiming to reduce long-term energy consumption while maintaining system stability by jointly optimizing computing resources, time slot allocation, transmit power, RIS phase angles, and UAV trajectory. By applying the Lyapunov method, we transform the long-term stochastic optimization problem into manageable deterministic online subproblems, and obtain approximate optimal solutions using successive convex approximation, penalty functions, and convex optimization techniques. Simulation results show that compared to the baseline scheme, the proposed scheme approximately reduces energy consumption by 10%, improves system stability by approximately 16%, and maintains computational efficiency. © 2014 IEEE.

关键词： Aircraft communication

来源：评论

学校读者我要写书评

暂无评论

Value Stream Mapping for Smart Pharmaceutical Management in a Thai Hospital 6

Value Stream Mapping for Smart Pharmaceutical Management in ...

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Boonsothonsatit, Ganda Silapunt, Rardchawadee Vongbunyong, Supachai Kaemarungsi, Kamol Chanpuypetch, Wirachchaya Chonsawat, Nilubon Graduate School of Management and Innovation King Mongkut's University of Technology Thonburi Thailand Electronic and Telecommunication Engineering King Mongkut's University of Technology Thonburi Thailand Hospital Automation Research Center Institute of Field Robotics King Mongkut's University of Technology Thonburi Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Thailand Faculty of Agro-Industry Chiang Mai University Thailand Department of Agricultural Economy and Developement Faculty of Agriculture Chiang Mai University Thailand

The evolution of healthcare systems worldwide necessitates continual improvement in hospital management practices, particularly pharmaceutical management. This paper explores transforming traditional pharmaceutical management systems in large and medium-sized hospitals in Thailand into smart systems using Value Stream Mapping (VSM) as a guiding tool. Traditional systems often face challenges such as inefficiencies and medication errors. VSM, rooted in lean management principles, offers a structured approach to visualize and optimize processes. Additionally, smart technologies like automated inventory systems and electronic health records enhance pharmaceutical management effectiveness. Through a comprehensive research methodology encompassing case studies, data collection, and VSM analysis, this study identifies inefficiencies and proposes evidence-based strategies for improvement. Results from a case study highlight the benefits of VSM implementation in enhancing pharmacy operations, emphasizing improved patient care and operational efficiency. The implementation of a smart medication dispensing system shows promising results in reducing workload and accommodating increased patient arrivals. Continued evaluation and refinement are crucial for maximizing benefits and addressing emerging challenges effectively. © 2025 Elsevier B.V.. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Optimization of Crop Yields in Sustainable Agriculture: Application of Big Data Analytics and Artificial Intelligence

引用

Remote Sensing in Earth Systems Sciences 2025年第2期8卷 375-386页

作者： Nimma, Divya Dhanke, Jyoti A. Murthy, G.S.N. Khandekar, Sachin Dadu Hymavathi, J. Jangir, Pradeep Singh, Mahesh Department of Computational Science University of Southern Mississippi Hattiesburg 39406 MS United States Department of Engineering Science (Mathematics) Bharati Vidyapeeth’s College of Engineering Lavale Maharashtra Pune India Department of CSE Aditya University Surampalem India Department of Civil Engineering Sinhgad College of Engineering Maharashtra Pune India Department of CSE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan Department of Robotics and Automation Symbiosis Institute of Technology Pune Campus Symbiosis International (Deemed University) Pune India

Making informed economic decisions based on agricultural data is challenging without proper crop management. Data has become the single most important part of modern farming, and its rapid evolution is a major contributor to the rise of “smart farming.” Using sensors to gather objective data with the end aim of increasing productivity and sustainability has several advantages. Information that might boost productivity while decreasing resource waste and pollution levels is essential for managed farms. The cornerstone of future sustainable farming will be data-driven agriculture using robotic solutions based on AI-based techniques. This paper examines the current state of advanced farm management systems, discussing topics like data acquisition in crop fields and variable rate applications, to assist farmers in saving money, protecting the environment, and transforming food production so that it can sustainably keep up with the expected increase in population. The advent of machine learning, big data technologies, and high-performance computers has opened up new avenues for data-intensive research in the interdisciplinary subject of agro technology. These avenues of exploration have been aided by the development of more capable computers. A comprehensive literature review on the issue of the applications of machine learning in agricultural manufacturing is provided in this research. Machine learning has shown its utility in agriculture via two applications: filtering and categorizing products. The use of machine learning on sensor data is transforming conventional farm management systems into AI-enabled programs. These services provide farmers instantaneous, complete access to ideas and insights that may guide their decisions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Artificial intelligence Big data analytics Optimize crop yields Sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Riemannian Online Optimistic Algorithms with Dynamic Regret

引用

IEEE Transactions on Automatic Control 2025年

作者： Wang, Xi Yuan, Deming Hong, Yiguang Hu, Zihao Wang, Lei Shi, Guodong University of New South Wales School of Electrical Engineering & Telecommunications SydneyNSW2052 Australia Nanjing University of Science and Technology School of Automation Nanjing210094 China Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Hong Kong University of Science and Technology Department of Mathematics Hong Kong Zhejiang University College of Control Science and Engineering Zhejiang 310058 China The University of Sydney Australian Center for Robotics School of Aerospace Mechanical and Mechatronic Engineering NSW2006 Australia

In this paper, we consider Riemannian online convex optimization with dynamic regret, which involves minimizing the cumulative loss difference between a learner's decisions and a sequence of adaptive decisions across dynamic environments over time on Riemannian manifolds. First, we propose Riemannian Online Optimistic Gradient Descent (R-OOGD), which extends the classical optimistic algorithms to Riemannian manifolds, requiring one gradient inquiry per round. We then propose Riemannian Adaptive Online Optimistic Gradient Descent (R-AOOGD) by incorporating the meta-expert framework into R-OOGD. We analyze the dynamic regret of R-OOGD and R-AOOGD in terms of the regularity of the sequence of cost functions and comparators. The dynamic regret bound matches the results in Euclidean space and with a scale adjustment of O(1+κ D2/√1-KD2) related to the sectional curvature lower bound κ, sectional curvature upper bound and feasible set diameter. Finally, we provide numerical experiments to illustrate the performance of the proposed algorithms. © 1963-2012 IEEE.

关键词： Optimization algorithms

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：