检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Li, Chenming Wang, Jiankun Meng, Max Q.-H. The Chinese University of Hong Kong Department of Electronic Engineering Hong Kong Hong Kong Southern University of Science and Technology Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Shenzhen China Southern University of Science and Technology Jiaxing Research Institute Jiaxing China University of Alberta Department of Electrical and Computer Engineering Canada

ISBN: (纸本)9798350327182

Robot path planning in high-dimensional continuous space is of great significance in robotics. The conventional bidirectional fast marching method utilizes brute-force search to explore the space, which is computationally expensive. Though improving the planning efficiency, heuristic-based bidirectional fast marching search results in a suboptimal path under a predetermined number of random samples. To address these issues, we propose Focused Bidirectional Fast Marching Trees (FBFMT*), developing a novel vertex exploring sequence to constrain the forward and backward searches within the brute-force searched regions. It enables the search trees to meet in the middle of the solution path, which guarantees the optimality under the current set of samples and searches faster than the bidirectional brute-force strategy. Extensive simulations in different scenarios validate the superiority of the proposed method, showing that FBFMT∗ can speed up the planning process and find a better solution. We also extend the proposed method to general conditions so that the forward and backward searches of FBFMT∗ can meet at any portion of the path. FBFMT∗ reveals that the heuristic-based bidirectional fast marching search strategy can be a general and efficient technique for robot path planning in high-dimensional continuous spaces. © 2023 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Progressive Motion Boosting for Video Frame Interpolation

引用

IEEE Transactions on Multimedia 2023年 25卷 8076-8090页

作者： Xiao, Jing Xu, Kangmin Hu, Mengshun Liao, Liang Wang, Zheng Lin, Chia-Wen Wang, Mi Satoh, Shin'Ichi The School of Computer Science Wuhan University Wuhan430072 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The Department of Electrical Engineering the Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430072 China The Digital Content and Media Sciences Research Division National Institute of Informatics Tokyo101-8430 Japan

Video frame interpolation has made great progress in estimating advanced optical flow and synthesizing in-between frames sequentially. However, frame interpolation involving various resolutions and motions remains challenging due to limited or fixed pre-trained networks. Inspired by the success of the coarse-to-fine scheme for video frame interpolation, i.e., gradually interpolating frames of different resolutions, we propose a progressive boosting network (ProBoost-Net) based on a multi-scale framework to achieve flexible recurrent scales and then gradually optimize optical flow estimation and frame interpolation. Specifically, we designed a dense motion boosting (DMB) module to transfer features close to real motion to the decoded features from the later scales, which provides complementary information to refine the motion further. Furthermore, to ensure the accuracy of the estimated motion features at each scale, we propose a motion adaptive fusion (MAF) module that adaptively deals with motions with different receptive fields according to the motion conditions. Thanks to the framework’s flexible recurrent scales, we can customize the number of scales and make trade-offs between computation and quality depending on the application scenario. Extensive experiments with various datasets demonstrated the superiority of our proposed method over state-of-the-art approaches in various scenarios. © 2023 Institute of electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

An overview of recent progress in the development of flexible electrochromic devices

引用

Nano Materials Science 2023年第4期5卷 369-391页

作者： Bin Wang Wu Zhang Feifei Zhao William W.Yu Abdulhakem Y.Elezzabi Linhua Liu Haizeng Li Optics and Thermal Radiation Research Center Institute of Frontier&Interdisciplinary ScienceShandong UniversityQingdao266237China School of Chemistry&Chemical Engineering Shandong UniversityJinan250100China Ultrafast Optics and Nanophotonics Laboratory Department of Electrical and Computer EngineeringUniversity of AlbertaEdmontonAlbertaT6G 2V4Canada

Electrochromic materials are capable of reversibly switching their colors or optical properties through redox reactions under applied voltages,which have shown great potential applications including smart windows,nonemissive displays,optical filters,among *** the current rigid electrochromic devices have shown emerging interest and developed rapidly,many applications(e.g.,wearable/deformable optoelectronics)are blocked due to their inflexible ***,the adaption of rigid electrochromic devices to flexible ones is of particular interest for the new era of smart *** this review,the current state-of-the-art achievements of flexible electrochromic devices(FECDs)are highlighted,along with their design strategies and the choice of electrochromic *** recent research progress of FECDs is reviewed in detail,and the challenges and corresponding solutions for real-world applications of FECDs are ***,we summarize the basic fabrication strategies of FECDs and their potential *** addition,the development trend,the perspectives,and the outlook of FECDs are discussed at the end of this Review,which may provide recommendations and potential directions to advance the practical applications of FECDs.

关键词： Electrochromism Flexible electrochromic devices Optoelectronics Optical materials

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Device Scheduling for Over-the-Air Federated Learning 23

Probabilistic Device Scheduling for Over-the-Air Federated L...

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Sun, Yuchang Lin, Zehong Mao, Yuyi Jin, Shi Zhang, Jun The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Hong Kong Southeast University National Mobile Communications Research Laboratory Nanjing210096 China

ISBN: (纸本)9798350325959

Federated learning (FL) is an emerging distributed training scheme where edge devices collaboratively train a model by uploading model updates instead of private data. To address the communication bottleneck, over-the-air (OTA) computation has been introduced to FL, which allows multiple edge devices to upload their gradient updates concurrently for aggregation. However, OTA computation is plagued by the communication error, which is critically affected by the device selection policy and impacts the performance of the output model. In this paper, we propose a probabilistic device selection scheme PO-FL, which effectively enhances the convergence performance of over-the-air FL. Specifically, each device is selected for OTA computation according to the predetermined probability, and its local update is scaled by this probability. By analyzing the convergence of PO-FL, we show that its convergence is determined by the device selection via the communication error and the variance of global update. Then, we propose a device selection algorithm that jointly considers the channel condition and gradient update importance of edge devices to optimize their selection probabilities. The experimental results on the MNIST dataset demonstrate that the proposed algorithm converges faster and learns better models than the baselines. © 2023 IEEE.

关键词： channel awareness device scheduling Federated learning (FL) gradient importance over-the-air computation (AirComp)

来源：评论

学校读者我要写书评

暂无评论

High-Value Target Escort and Defense Scenario with Differential Subgame Cost 63

High-Value Target Escort and Defense Scenario with Different...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Judy, Rachael L. Fuchs, Zachariah E. Casbeer, David W. University of Cincinnati Department of Electrical Engineering and Computer Science CincinnatiOH United States Control Science Center of Excellence Air Force Research Laboratory 2210 8th St. WPAFBOH45433 United States

ISBN: (纸本)9798350316339

An Escort and Defense Scenario is presented in which a high-value Target maneuvers through a high-risk region while being escorted by a mobile, defensive agent. Along this trajectory, an Attacker may be launched from one of several possible launch locations. If a launch occurs, the three agents play out a Target-Attacker-Defender (TAD) differential game in which the Defender attempts to intercept the Attacker at maximal distance from the Target while the Attacker strives to maneuver as close as possible to the Target. Prior to launch, the Target and Defender strive to preposition themselves in advantageous positions to effectively respond to a potential threat while simultaneously moving towards a safety region. An augmented collocation-based direct optimal control method is developed to solve the escort problem by solving and utilizing the value of the TAD differential subgame at each collocation point while simultaneously optimizing the primary optimal control problem. © 2024 IEEE.

关键词： Optimal control systems

来源：评论

学校读者我要写书评

暂无评论

Potential detection of Flavescence dorée in the vineyard using close-range hyperspectral imaging

Potential detection of Flavescence dorée in the vineyard us...

引用

2023 International Conference on electrical, computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Barjaktarovic, Marko Santoni, Massimo Faralli, Michele Bertamini, Massimo Bruzzone, Lorenzo School of Electrical Engineering University of Belgrade Serbia Remote Sensing Laboratory University of Trento Italy Remote Sensing Laboratory Department of Information Engineering and Computer Science University of Trento Italy University of Trento Italy Research and Innovation Centre Fondazione Edmund Mach Italy

ISBN: (纸本)9798350322972

Grapevine is one of the most important crops cultivated across Europe. Climate factors and diseases constantly threaten its production. Recently, Flavescence dorée (FD), an incurable grapevine disease with the obligation to uproot each infected plant, has been widely spread in Europe. The symptoms of FD are visually expressed in the late summer. Currently, the adopted procedure consists in scouting for infected plants by trained experts, which is time-consuming and not frequent enough. As stress development causes subtle spectral changes before any visible symptoms appear, during the summer of 2022, hyperspectral and multispectral images were acquired in the two vineyards near Riva del Garda, Trentino, Italy. A classification accuracy between 90.2 % and 96.9 % in distinguishing between infected and healthy plants was obtained from the hyperspectral data. These findings justify further efforts to use an in-house developed, affordable multispectral camera, significantly reducing equipment cost and procedure complexity while mapping the relevant spectral channels. © 2023 IEEE.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

BalanceDN: Load-Balancing Allocation of Interest for Fast Discovery in Content Centric Networks

BalanceDN: Load-Balancing Allocation of Interest for Fast Di...

引用

IEEE World Forum on Internet of Things (WF-IoT)

作者： Murali Gunti Roberto Rojas-Cessa Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ Department of Electrical and Computer Engineering Networking Research Laboratory Newark NJ

ISBN: (数字)9798350311617

ISBN: (纸本)9798350311624

In Named Data Networking (NDN), data is identified by unique names instead of IP addresses, and routers use the names of the content to forward Interest packets towards the producers of the requested content. However, the current content search mechanism in NDN is complex and slow. This mechanism not only creates congestion but also hinders practical deployment due to its slowness and cumbersome nature. To address this issue, we propose a methodology, called BalanceDN, that distributes content through the network such that sought content can be found quickly. BalanceDN uses a distributed allocation of resolvers as those used by the domain name system but differs in how content is distributed. Our approach avoids flooding the network with pending interest requests and also eliminates the need for blind search when the location of content is unknown. We tested our approach on a simulation platform for NDN called ndnSIM. The results show that the proposed routing scheme utilizes far fewer network resources compared to the NDN network when retrieving content. The proposed scheme accomplishes this performance gain by leveraging a load-balanced hashing mechanism to distribute and locate the name of the content on the distributed nameserver lookup service nodes.

关键词： Search methods Performance gain Routing Resource management Reliability Internet of Things IP networks

来源：评论

学校读者我要写书评

暂无评论

Comparison of Event-Based Processing Algorithms for Experimental 2D2C Velocimetry

Comparison of Event-Based Processing Algorithms for Experime...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Gunasekaran, Sidaard Mongin, Michael Alsattam, Osama A. Hirakawa, Keigo Mechanical and Aerospace Engineering Department University of Dayton DaytonOH45469 United States U.S. Air Force Research Laboratory AFRL AIAA Wright–Patterson Air Force Base OH45433 United States Department of Electrical and Computer Engineering University of Dayton DaytonOH45469 United States

ISBN: (纸本)9781624107238

Event-based cameras, which operate without traditional frames and instead capturea synchronous changes in intensity, offer a transformative approach to flow diagnostics. This study investigates the application of event-based methods for velocimetry around an SD7003wing and compares their performance to traditional Particle Image Velocimetry (PIV). Four event-based algorithms—Weighted Tracking (Linear and Non-Linear fits), Kalman Filter, and Motion Compensation—are evaluated using a combination of free stream, near-surface, and wake flow scenarios. Results demonstrate that event-based methods successfully replicate global flow trends observed in PIV, including mean and median velocity estimates, while also capturing subtle flow features such as near-surface pressure gradients and wake asymmetry with higher resolution. Unlike PIV, which is constrained by frame rate and windowed processing, event-based methods track individual tracer particles, resolving flow features even in regions with steep gradients. The weighted tracking methods exhibited the closest agreement with PIV, while Kalman Filter and Motion Compensation methods showed slight biases in Uvelocity, hypothesized to result from input parameter tuning. The findings highlight the potential of event-based methods as a viable candidate for flow diagnostics. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Wakes

来源：评论

学校读者我要写书评

暂无评论

A Wearable Paper-Based Hybrid Energy Harvester from Human Sweat and Ambient Moisture 38

A Wearable Paper-Based Hybrid Energy Harvester from Human Sw...

引用

38th IEEE International Conference on Micro Electro Mechanical Systems, MEMS 2025

作者： Gao, Yang Choi, Seokheun State University of New York at Binghamton Bioelectronics & Microsystems Laboratory Department of Electrical & Computer Engineering BinghamtonNY United States State University of New York at Binghamton Center for Research in Advanced Sensing Technologies and Environmental Sustainability BinghamtonNY United States

ISBN: (纸本)9798331508890

We present a wearable, paper-based energy harvester that combines a sweat-driven microbial fuel cell (MFC) with an ambient moisture-enabled electric generator (MEG), capable of simultaneously or independently harnessing energy from both human sweat and the environment. Paper stands out as an ideal substrate for wearable applications, offering flexibility and easy integration through straightforward printing methods. Due to the simple design of the MFC and MEG, both devices can be seamlessly integrated into a single sheet of paper. The biocatalyst-embedded anode of the MFC is positioned directly against the skin for optimal sweat absorption, while the hygroscopic region of the MEG faces outward to efficiently capture ambient moisture. At low humidity levels, the energy harvesting is primarily driven by the MFC, while in the absence of sweat, the MEG takes over as the main power source. This dual functionality ensures continuous and sustainable power generation, making the system highly efficient and reliable for long-term wearable applications. © 2025 IEEE.

关键词： Microbial fuel cells

来源：评论

学校读者我要写书评

暂无评论

When Does Sora Show:The Beginning of TAO to Imaginative Intelligence and Scenarios engineering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 809-815页

作者： Fei-Yue Wang Qinghai Miao Lingxi Li Qinghua Ni Xuan Li Juanjuan Li Lili Fan Yonglin Tian Qing-Long Han School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Department of Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIndianapolisIN 46202USA Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng LaboratoryShenzhen 518000China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia

DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.

关键词： something Intelligence replace

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：