检索结果-内蒙古大学图书馆

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Qingbo Wu Guanxing Wu Shengyong Chen Key Laboratory of Computer Vision and Systems (Ministry of Education) Tianjin University of Technology Tianjin China Engineering Research Center of Learning-Based Intelligent System (Ministry of Education) Tianjin University of Technology Tianjin China School of Computer Science and Engineering Tianjin University of Technology Tianjin China

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

This paper proposes a novel encoder-decoder architecture for camouflaged object fixation prediction (COFP), which builds on a large-kernel decomposition technique and depth-wise separable convolution embedded attention. Specifically, the encoder with the large-kernel decomposition adopts a Visual Attention Network (VAN) as the backbone to extract more accurate features, and the decoder predicts fixation maps from concealed objects using the attention module incorporating depth-wise separable convolution. Both designs aim to reduce the number of learnable parameters, making the model lighter and simultaneously maintaining the performance of COFP. In addition, we propose using the reverse Kullback-Leibler Divergence (KLDiv) as the loss function. Extensive experiments demonstrate that the proposed method performs well against SOTA approaches in quality and quantity.

关键词： Industrial electronics Visualization Accuracy Convolution Feature extraction Decoding

来源：评论

学校读者我要写书评

暂无评论

Temporal Triplane Transformers as Occupancy World Models

arXiv

引用

arXiv 2025年

作者： Xu, Haoran Peng, Peixi Tan, Guang Chang, Yiqian Zhao, Yisen Tian, Yonghong School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen Campus Shenzhen518107 China Peng Cheng Laboratory Shenzhen518108 China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University 518066 China School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China School of Computer Science Peking University Beijing100871 China

Recent years have seen significant advances in world models, which primarily focus on learning fine-grained correlations between an agent’s motion trajectory and the resulting changes in its surrounding environment. However, existing methods often struggle to capture such fine-grained correlations and achieve real-time predictions. To address this, we propose a new 4D occupancy world model for autonomous driving, termed T3Former. T3Former begins by pre-training a compact triplane representation that efficiently compresses the 3D semantically occupied environment. Next, T3Former extracts multi-scale temporal motion features from the historical triplane and employs an autoregressive approach to iteratively predict the next triplane changes. Finally, T3Former combines the triplane changes with the previous ones to decode them into future occupancy results and ego-motion trajectories. Experimental results demonstrate the superiority of T3Former, achieving 1.44× faster inference speed (26 FPS), while improving the mean IoU to 36.09 and reducing the mean absolute planning error to 1.0 meters. Copyright © 2025, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

An Adaptive RPC Mechanism for Performance and Node Fault Tolerance Optimization in HDFS

An Adaptive RPC Mechanism for Performance and Node Fault Tol...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Jingyu Zhang Zhengwen Shu Lailong Luo School of Computer & Communication Engineering Changsha University of Science & Technology Changsha China Science and Technology on Information Systems Engineering Laboratory School of Systems Engineering National University of Defense Technology Changsha China

With the rapid development and evolution of information technologies, the big data industry has been experiencing exponential explosive data growth. Since the huge business and research value behind the large-scale data, big data technology has become one of the hotest research fields in academia and industry. To the big data, storing and processing the data is core function of the file systems. Hadoop Distributed File System (HDFS) is the most typical distributed big data architecture, which has the characteristics of high reliability, high fault tolerance, and low hardware cost. HDFS provides the efficient task implementation and fault tolerance among nodes by Remote Procedure Call (RPC) mechanism. However, the traditional RPC mechanism has remarkable defects with the fixed timing method, and cannot quickly establish the relationship between node downtime and network congestion. In this paper, we propose an improved adaptive RPC mechanism for node fault tolerance and performance. The proposed method classifies nodes by the data block access statistic, and dynamically adjusts the RPC interval time. This method can be used to reduce the networking traffic and processing pressure of NameNode nodes, and improve the I/O and task performance. Through the node classification, an inrack method is used to achieve better performance on fault tolerance. Eventually, we design the extensive experiments to evaluate the proposed method, and experimental results show it improves the performance compared with state-of-the-art method.

关键词： Industries Fault tolerance Adaptive systems Heart beat File systems System performance Fault tolerant systems

来源：评论

学校读者我要写书评

暂无评论

A SINS Error Correction Approach Based on Dual-Threshold ZV Detection and Cubature Kalman Filter

A SINS Error Correction Approach Based on Dual-Threshold ZV ...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Xu, Ruijie Chen, Shichao Sun, Wenqiao Lv, Yisheng Luo, Jialiang Tang, Ying Institute of Automation Chinese Academy of Sciences College of Information Science & Technology Beijing University of Chemical Technology The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Institute of Automation Chinese Academy of Sciences The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Transportation and Economics Research Institute The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Institute of Automation Chinese Academy of Sciences China University of Geosciences Beijing School of Information Engineering The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Rowan University Department of Electrical and Computer Engineering Glassboro United States

ISBN: (纸本)9798350337020

Global Navigation Satellite systems (GNSS) can provide real-time positioning information for outdoor users, but cannot for indoor scenarios or heavily occluded outdoor scenarios. Strap-down Inertial Navigation System (SINS) are widely used to locate people in complex interior or heavily occluded outdoor scenarios due to its light weight and low power consumption. However, IMU of SINS are noisy, and the sampling data error is large, which is a divergence of the error with time. Therefore, it will generate a positioning accumulation error, which affects the final positioning accuracy. The problem of cumulative IMU errors is usually dealt with by Zero-Velocity Update (ZUPT). The zero-velocity detection part of basic ZUPT method usually uses a single threshold to determine the gait of pedestrian, which often has the problem of gait misjudgment and omission. To address these problems, this paper proposes a composite conditional detection method to solve the problem of misjudgment in the zero-velocity interval. In addition, we redesign the zero-velocity update algorithm and uses the Cubature Kalman filter (CKF) for pedestrian positioning error correction. The experimental results demonstrate that the proposed ZUPT method based on dual-threshold detection can better detect the interval between pedestrian motion and stationery than ones with single threshold. The zero-velocity update algorithm based on CKF has higher performance than conventional EKF and UKF methods, which constrains the cumulative error of SINS to about 0.2% of the whole walking distance. © 2023 IEEE.

关键词： Cubature Kalman Filter Inertial Pedestrian Navigation Zero-Velocity Update

来源：评论

学校读者我要写书评

暂无评论

Modelling and Control of a Trailer Sprayer for Precision Spraying

Modelling and Control of a Trailer Sprayer for Precision Spr...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： André Baltazar Filipe N. Santos Antόnio Paulo Moreira Salviano Pinto Soares M. J. C. S. Reis José Boaventura Cunha CRIIS-Centre for Robotics in Industry and Intelligent Systems INESC TEC—Institute for Systems and Computer Engineering Technology and Science Porto Portugal ECT—School of Science and Technology UTAD—University of Trás-os-Montes and Alto Douro Vila Real Portugal FEUP—Faculty of Engineering University of Porto Porto Portugal Institute of Electronics and Informatics Engineering of Aveiro (IEETA) Portugal Intelligent Systems Associate Laboratory (LASI) Portugal

ISBN: (数字)9798350352344

ISBN: (纸本)9798350352351

Precision spraying in agriculture is crucial for optimizing the application of pesticides while minimizing environmental impact. Despite significant advancements in control models for spraying systems, predictive control algorithms were not used. This paper addresses this gap by proposing a real-time control framework that integrates predictive control strategies to ensure consistent pressure output in a trailer sprayer. Based on information from various sensors, the framework anticipates and adapts to dynamic environmental conditions, enhancing accuracy and sustainability in spraying practices. A methodology is developed to define a proportional valve model. Based on this valve model, the predictive control model optimizes valve movements to minimize errors between predicted and reference pressures, thereby improving spraying efficiency. This study demonstrates the viability of predictive control in improving precision spraying systems applicable to autonomous robots, encouraging future advances in agricultural spraying technologies.

关键词： Adaptation models Spraying Predictive models Valves Real-time systems Agriculture Sensors

来源：评论

学校读者我要写书评

暂无评论

Near-Far Field Three-Stage Beam Training for RIS-Assisted Wideband OFDM Communications

Near-Far Field Three-Stage Beam Training for RIS-Assisted Wi...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Cheng, Zhichao Zhang, Shupei Fu, Shu Di, Boya School of Electronics Engineering and Computer Science Peking University Beijing China School of Electronics Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks Beijing China Chongqing University Department of Microelectronics and Communication Engineering Chongqing China

ISBN: (纸本)9798350368369

Large-scale reconfigurable intelligent surfaces (RISs) have emerged as a promising technology for signal strength enhancement and coverage extension in 6G networks. However, as the antenna scale and the bandwidth increase, large-scale RIS-assisted wideband orthogonal frequency division multiplexing (OFDM) communication systems face new challenges due to the near-field range expansion and the beam split effect, complicating the acquisition of channel state information (CSI). To tackle these challenges, in this paper, we present a wideband beam training scheme by utilizing the beam split effect to bypass the CSI acquisition. Specifically, by analyzing the beam split effect in RIS-assisted OFDM communication systems, we propose a beam-split-aware codebook capable of covering both the near and far fields. The coverage of codewords in the proposed codebook is expanded benefiting from the beam split effect, leading to fewer codewords compared to conventional narrow-band codebooks. Utilizing such a codebook, a three-stage beam training mechanism is performed to obtain the optimal codeword with low time overhead, thereby facilitating the beamforming. Simulation results demonstrate that the proposed scheme outperforms existing codebook-based beam training schemes in terms of training overhead and sum rate in the hybrid near-far field. © 2025 IEEE.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Variational Bayesian Learning based Joint Localization and Path Loss Exponent with Distance-dependent Noise in Wireless Sensor Network

arXiv

引用

arXiv 2024年

作者： Li, Yunfei Luo, Yiting Tan, Weiqiang Li, Chunguo Ma, Shaodan Yang, Guanghua The Department of Electrical Engineering Anhui Polytechnic University Wuhu China The School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China The School of Information Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories Nanjing China The State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau Taipa China The School of Intelligent Systems Science and Engineering Jinan University Zhuhai519070 China

This paper focuses on the challenge of jointly optimizing location and path loss exponent (PLE) in distance-dependent noise. Departing from the conventional independent noise model used in localization and path loss exponent estimation problems, we consider a more realistic model incorporating distance-dependent noise variance, as revealed in recent theoretical analyses and experimental results. The distance-dependent noise introduces a complex noise model with unknown noise power and PLE, resulting in an exceptionally challenging non-convex and nonlinear optimization problem. In this study, we address a joint localization and path loss exponent estimation problem encompassing distance-dependent noise, unknown parameters, and uncertainties in sensor node locations. To surmount the intractable nonlinear and non-convex objective function inherent in the problem, we introduce a variational Bayesian learning-based framework that enables the joint optimization of localization, path loss exponent, and reference noise parameters by leveraging an effective approximation to the true posterior distribution. Furthermore, the proposed joint learning algorithm provides an iterative closed-form solution and exhibits superior performance in terms of computational complexity compared to existing algorithms. computer simulation results demonstrate that the proposed algorithm approaches the performance of the Bayesian Cramer-Rao bound (BCRB), achieves localization performance comparable to the (maximum likelihood-Gaussian message passing) ML-GMP algorithm in some cases, and outperforms the other comparison algorithm in all cases. Copyright © 2024, The Authors. All rights reserved.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Scavenger: Better Space-Time Trade-Offs for Key-Value Separated LSM-trees

Scavenger: Better Space-Time Trade-Offs for Key-Value Separa...

引用

International Conference on Data engineering

作者： Jianshun Zhang Fang Wang Sheng Qiu Yi Wang Jiaxin Ou Junxun Huang Baoquan Li Peng Fang Dan Feng Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology China Shenzhen Huazhong University of Science and Technology Research Institute Bytefrance Inc.

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Key- Value Stores (KVS) implemented with log- structured merge-tree (LSM-tree) have gained widespread ac-ceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction process. While KV-separated LSM-trees successfully tackle this issue, they also bring about substantial space am-plification problems, a concern that cannot be overlooked in cost-sensitive scenarios. Garbage collection (GC) holds significant promise for space amplification reduction, yet existing GC strategies often fall short in optimization performance, lacking thorough consideration of workload characteristics. Additionally, current KV-separated LSM-trees also ignore the adverse effect of the space amplification in the index LSM-tree. In this paper, we systematically analyze the sources of space amplification of KV- separated LSM-trees and introduce Scavenger, which achieves a better trade-off between performance and space amplification. Scavenger initially proposes an I/O-efficient garbage collection scheme to reduce I/O overhead and incorporates a space-aware compaction strategy based on compensated size to minimize the space amplification of index LSM-trees. Extensive experiments show that Scavenger significantly improves write performance and achieves lower space amplification than other KV-separated LSM-trees (including BlobDB, Titan, and TerarkDB).

关键词： Data engineering Compaction Indexes Optimization

来源：评论

学校读者我要写书评

暂无评论

On the Convergence of Gossip Learning in the Presence of Node Inaccessibility

On the Convergence of Gossip Learning in the Presence of Nod...

引用

IEEE International Conference on Communications (ICC)

作者： Tian Liu Yue Cui Xueyang Hu Yecheng Xu Bo Liu Zhejiang Laboratory Hangzhou China Department of Computer Science and Computer Information Systems Auburn University at Montgomery Montgomery USA Department of Computer Science and Software Engineering Auburn University Auburn USA Institute of Rural Development Zhejiang Academy of Agricultural Sciences Hangzhou China DBAPPSecurity Co. Ltd. Hangzhou China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Gossip learning (GL), as a decentralized alternative to federated learning (FL), is more suitable for resourceconstrained wireless networks, such as Flying Ad-Hoc Networks (FANETs) that are formed by unmanned aerial vehicles (UAVs). GL can significantly enhance the efficiency and extend the battery life of UAV networks. Despite the advantages, the performance of GL is strongly affected by data distribution, communication speed, and network connectivity. However, how these factors influence the GL convergence is still unclear. Existing work studied the convergence of GL based on a virtual quantity for the sake of convenience, which failed to reflect the real state of the network when some nodes are inaccessible. In this paper, we formulate and investigate the impact of inaccessible nodes to GL under a dynamic network topology. We first decompose the weight divergence by whether the node is accessible or not. Then, we investigate the GL convergence under the dynamic of node accessibility and theoretically provide how the number of inaccessible nodes, data non-i.i.d.-ness, and duration of inaccessibility affect the convergence. Extensive experiments are carried out in practical settings to comprehensively verify the correctness of our theoretical findings.

关键词： Training Accuracy Network topology Federated learning Wireless networks Autonomous aerial vehicles Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Co-Design Optimisation of Morphing Topology and Control of Winged Drones

Co-Design Optimisation of Morphing Topology and Control of W...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Fabio Bergonti Gabriele Nava Valentin Wüest Antonello Paolino Giuseppe L’Erario Daniele Pucci Dario Floreano Artificial and Mechanical Intelligence Laboratory Istituto Italiano di Tecnologia (IIT) School of Computer Science University of Manchester Laboratory of Intelligent Systems Ecole Polytechnique Federale de Lausanne (EPFL) Department of Industrial Engineering University of Naples Federico II

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

The design and control of winged aircraft and drones is an iterative process aimed at identifying a compromise of mission-specific costs and constraints. When agility is required, shape-shifting (morphing) drones represent an efficient solution. However, morphing drones require the addition of actuated joints that increase the topology and control coupling, making the design process more complex. We propose a co-design optimisation method that assists the engineers by proposing a morphing drone’s conceptual design that includes topology, actuation, morphing strategy, and controller parameters. The method consists of applying multi-objective constraint-based optimisation to a multi-body winged drone with trajectory optimisation to solve the motion intelligence problem under diverse flight mission requirements, such as energy consumption and mission completion time. We show that co-designed morphing drones outperform fixed-winged drones in terms of energy efficiency and mission time, suggesting that the proposed co-design method could be a useful addition to the aircraft engineering toolbox.

关键词： Energy consumption Costs Computational modeling Process control Energy efficiency Topology Trajectory

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：