检索结果-内蒙古大学图书馆

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Andrea Berra Viswa Narayanan Sankaranarayanan Achilleas Santi Seisa Julien Mellet Udayanga G.W.K.N. Gamage Sumeet Gajanan Satpute Fabio Ruggiero Vincenzo Lippiello Silvia Tolu Matteo Fumagalli George Nikolakopoulos Miguel Ángel Trujillo Soto Guillermo Heredia CATEC Advanced Center for Aerospace Technologies Seville Spain Department of Computer Electrical and Space Engineering Robotics and AI Team Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Information Technology PRISMA Lab University of Naples Federico II Naples Italy Department of Electrical Engineering and Photonics Automation and Control Group Technical University of Denmark Denmark Robotics Vision and Control Group School of Engineering University of Seville Seville Spain

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

The paper introduces a novel framework for safe and autonomous aerial physical interaction in industrial settings. It comprises two main components: a neural network-based target detection system enhanced with edge computing for reduced onboard computational load, and a control barrier function (CBF)-based controller for safe and precise maneuvering. The target detection system is trained on a dataset under challenging visual conditions and evaluated for accuracy across various unseen data with changing lighting conditions. Depth features are utilized for target pose estimation, with the entire detection framework offloaded into low-latency edge computing. The CBF-based controller enables the UAV to converge safely to the target for precise contact. Simulated evaluations of both the controller and target detection are presented, alongside an analysis of real-world detection performance.

关键词： Visualization Pose estimation Neural networks Lighting Object detection Autonomous aerial vehicles Aircraft navigation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Attention for Efficient LLM Inference: A Review

Optimizing Attention for Efficient LLM Inference: A Review

引用

World Congress on Computing and Communication Technologies (WCCCT)

作者： Siyuan Sun Jinling Yu Hanshuo Liu Hanyun Guo Yang Cao Shouhua Zhang Jiehan Zhou School of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Faculty of Computer Science Western University London Canada Research&Development Department Mox Automation Shanghai Company Shanghai China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland

ISBN: (数字)9798331512620

ISBN: (纸本)9798331512637

The rapid advancement of deep learning has led to significant progress in large language models (LLMs), with the Attention mechanism serving as a core component of their success. However, the computational and memory demands of Attention mechanisms pose bottlenecks for efficient inference, especially in long-sequence and real-time tasks. This paper systematically reviews optimization strategies for Attention mechanisms, including sparse attention, low-rank decomposition, quantization techniques, block-based parallel computation, and memory management. These approaches have demonstrated notable improvements in reducing computational complexity, optimizing memory usage, and enhancing inference performance. This review highlights the key challenges of computational efficiency, long-sequence modeling, and cross-task generalization through an in-depth analysis of existing methods, their advantages, and limitations. Future research directions, including dynamic precision, hardware-aware optimization, and lightweight architectures offer insights for advancing LLM inference theory and practice.

关键词： Attention mechanisms Quantization (signal) Reviews Computational modeling Large language models Memory management Optimization methods Real-time systems Computational efficiency Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A GM-TCN based Hybrid Prediction Method for Ash Fouling Prediction in Coal-fired Power Plant Boiler

A GM-TCN based Hybrid Prediction Method for Ash Fouling Pred...

引用

2022 Chinese automation Congress, CAC 2022

作者： Shi, Yuanhao Han, Tianxiang Cui, Fangshu Wen, Jie Qiao, Gangzhu North University of China School of Electrical and Control Engineering Taiyuan China Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China North University of China School of Data Science and Technology Taiyuan China

ISBN: (纸本)9781665465335

In response to the problem that ash deposition in boilers has a great impact on production efficiency as well as production safety, a grey level theory prediction model based on time convolution networks (GM-TCN) is proposed to predict the degree of ash in boiler heated areas by using a cleaning factor to assess the ash deposition condition on the heated surfaces. The accuracy of the prediction model is improved by utilizing the features of grey level theory that can predict the developmental changes in system behavior, combined with the high-precision approximation capability of the time-convolutional network. The modelling prediction of the ash level in the heated area of boilers during the production of coal-fired power stations is investigated. Experiments demonstrate that the model can predict the cleanliness factor with high accuracy, and the predicted values are closest to the true values compared to the other two models, verifying the accuracy and reliability of the model. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Exchange Strategies for Multi-Colony Ant Algorithms in Dynamic Environments

Exchange Strategies for Multi-Colony Ant Algorithms in Dynam...

引用

Congress on Evolutionary Computation

作者： Michalis Mavrovouniotis Changhe Li Danial Yazdani Diofantos Handjimitsis ERATOSTHENES Centre of Excellence Limassol Cyprus Department of Civil Engineering and Geomatics Cyprus University of Technology Limassol Cyprus Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Wuhan China Faculty of Engineering & Information Technology University of Technology Sydney Sydney Australia

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

In dynamic optimization problems where optimal solutions change over time, traditional ant colony optimization (ACO) algorithms face limitations. This study explores the adaptation of multi-colony ACO algorithms, known for their enhanced search capabilities in stationary problems, to tackle optimization problems in dynamic environments. Various strategies for exchanging information between colonies, which is a critical factor influencing algorithm performance, are investigated. Using the dynamic traveling salesman problem as a foundation, we generate test cases to reflect real-world complexities. Our results on a set of problem instances reveal that the choice of communication strategy between colonies significantly impacts the adaptability and efficiency of multi-colony ACO algorithms in tracking moving optimum.

关键词： Schedules Satellites Processor scheduling Heuristic algorithms Evolutionary computation Traveling salesman problems Search problems

来源：评论

学校读者我要写书评

暂无评论

Disturbance Observer Based on Terminal Sliding-Mode control for a Secure Communication of Fractional-Order Takagi-Sugeno Fuzzy Chaotic Systems

Disturbance Observer Based on Terminal Sliding-Mode Control ...

引用

International Conference on Advanced Mechanical engineering, automation and Sustainable Development, AMAS 2021

作者： Giap, Van Nam Nguyen, Quang Dich Trung, Nguyen Kien Huang, Shyh-Chour Trinh, Xuan Thang Institute for Control Engineering and Automation Hanoi University of Science and Technology Hanoi100000 Viet Nam School of Electrical Engineering Hanoi University of Science and Technology Hanoi100000 Viet Nam Department of Mechanical Engineering National Kaohsiung University of Science and Technology Kaohsiung80778 Taiwan Faculty of Mechanical Engineering Hung Yen University of Technology and Education Hung Yen160000 Viet Nam

ISBN: (纸本)9783030996659

In this study, the disturbance observer (DOB) for a secure communication system (SCS) of the fractional-order (FO) Takagi-Sugeno (T-S) fuzzy systems was newly proposed. The synchronization of the master and slave systems (MSS) was guaranteed by a terminal sliding mode control (TSMC) method. The experimental study of computer communication-based MATLAB software with support of FOMCON toolbox was used to confirm the correction of the proposed theories. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Disturbance observer Fractional order Secure communication T-S fuzzy chaotic system Terminal sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Accurate RGB-D SLAM in dynamic environments based on dynamic visual feature removal

引用

Science China(information Sciences) 2022年第10期65卷 256-269页

作者： Chenxin LIU Jiahu QIN Shuai WANG Lei YU Yaonan WANG Department of Automation University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center College of Electrical and Information Engineering Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University

Visual localization is considered an essential capability in robotics and has attracted increasing interest for the past few years. However, most proposed visual localization systems assume that the surrounding environment is static, which is difficult to maintain in real-world scenarios due to the presence of moving objects. In this paper, we present DFR-SLAM, a real-time and accurate RGB-D SLAM based on ORB-SLAM2 that achieves satisfactory performance in a variety of challenging dynamic scenarios. At the core of our system lies a motion consensus filtering algorithm estimating the initial camera pose and a graph-cut optimization framework combining long-term observations, prior information, and spatial coherence to jointly distinguish dynamic and static visual features. Other systems for dynamic environments detect dynamic components by using the information from short time-span frames, whereas our system uses observations from a long period of keyframes. We evaluate our system using dynamic sequences from the public TUM dataset, and the evaluation demonstrates that the proposed system outperforms the original ORB-SLAM2 system significantly. In addition, our system provides competitive localization accuracy with satisfactory real-time performance compared to closely related SLAM systems designed to adapt to dynamic environments.

关键词： SLAM dynamic environments indoor localization graph-cut robot navigation

来源：评论

学校读者我要写书评

暂无评论

Space Target Surveillance Based on Non-linear Model Predictive control

Space Target Surveillance Based on Non-linear Model Predicti...

引用

2021 China automation Congress, CAC 2021

作者： Zhang, Jiancheng Chen, Yutao Huang, Jie College of Electrical Engineering and Automation Fuzhou University Fuzhou350108 China Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350108 China

ISBN: (纸本)9781665426473

Space target surveillance plays an important role in maintaining space advantages. Trajectory planning and attitude control are the key technologies of space target surveillance. We propose a nonlinear model predictive control framework to plan the trajectory of the surveillance satellite, track the surveillance target and keep a certain distance. In particular, the orbit dynamics and environmental disturbance of surveillance satellite are taken into account. A MatLab based real-time nonlinear model predictive control toolbox is used to solve these problems. The toolbox uses an efficient numerical method to calculate the maneuvering solution of MPC, which means that it allows the prediction horizon length to be greatly extended and save calculation time. The developed controller is simulated in a simulation scene, including the interference of near ground environment. We show that the proposed MPC method can be successfully applied to the satellite orbit planning and attitude control and the MATMPC toolbox can greatly speed up the solution of MPC optimization functions. © 2021 IEEE

关键词： Attitude control

来源：评论

学校读者我要写书评

暂无评论

A Transfer Gated Recurrent Unit Model for Battery Health Monitoring Under Cross-Domain Conditions

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Tian, Jilun Xie, Jiale Zhang, Jiusi Huang, Congsheng Jiang, Yuchen Luo, Hao Chow, Mo-Yuen Yin, Shen Harbin Institute of Technology School of Astronautics Department of Control Science and Engineering Harbin150001 China North China Electric Power University Department of Automation Baoding071003 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China National Taipei University of Technology Department of Electrical Engineering Taipei10608 Taiwan University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China Norwegian University of Science and Technology Faculty of Engineering Department of Mechanical and Industrial Engineering Trondheim7034 Norway

Battery health monitoring is crucial for ensuring maintenance reliability and safety, with broad applications in various industrial systems. Data-driven state-of-health (SOH) estimation methods can perform excellently using massive historical data without prior physical knowledge. In the battery aging process, this article extracts the essential health indicators to construct the model and adopts a suitable data preprocessing method to reduce the influence of noise. There is still a limitation for data-driven methods regarding data quality, and the domain shift caused by different operating conditions will damage estimation performance. To tackle the issue, this article proposes a transfer feature transformation (TFT) based on mean maximum discrepancy (MMD) to get a new feature space to get domain-invariant features with sufficient information. We propose a multilayer gated recurrent unit (GRU) neural network with fully connection (FC) layers to uncover hidden relationships in degraded data. Fusing TFT and GRU-FCs methods can realize an end-to-end SOH estimation under cross-domain conditions. We apply real-world public Center of Advanced Life Cycle engineering (CALCE) and NASA battery datasets and lab testing-based accelerated aging data to validate the performance of algorithms. By comparison, our proposed TFT-GRU-FCs method can get the best performance of all algorithms, and we have also given sufficient results as support. © 1963-2012 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Optimized Formation control for a Class of Second-order Multi-agent Systems based on Single Critic Reinforcement Learning Method 18

Optimized Formation Control for a Class of Second-order Mult...

引用

18th IEEE International Conference on Networking, Sensing and control, ICNSC 2021

作者： Shao, Wentai Chen, Yutao Huang, Jie Fuzhou University College of Electrical Engineering and Automation Fuzhou350108 China Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350108 China

ISBN: (纸本)9781665440486

In this paper, an optimized formation control based on single critic reinforcement learning is developed for a class of second-order multi-agent systems. Unlike first-order systems, both position and velocity variables need to be considered in second-order system control. Therefore, the control of second-order systems is more challenging. In the control design, single critic reinforcement learning method combined with fuzzy logic systems is used. Fuzzy logic systems approximator is used to compensate the nonlinearity of the systems. Compared with the actor-critic reinforcement learning method, single critic reinforcement learning requires only one network iterative training such that the training errors are smaller, and the calculation time caused by the iterative loop between actor and critic can be reduced. According to the analysis of Lyapunov stability theory, the proposed control design can achieve the control objective. Finally, the effectiveness of the proposed method is verified by simulation. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

2D multiple waves scattering for active detection of a dummy human body in a low frequency range and for various boundary conditions 12

2D multiple waves scattering for active detection of a dummy...

引用

12th International Conference on Mathematical Modeling in Physical Sciences, IC-MSQUARE 2023

作者： Bibcu, Dorin Florescu Culea, Anisia Moldovanu, Simona Moraru, Luminita The Modelling & Simulation Laboratory University "Dunǎrea de Jos" of Galati 47 Domneasca Street Galati800008 Romania University "Dunǎrea de Jos" of Galati Business Administration Department 59-61 N. Balcescu St. Galati800001 Romania Department of Electronics and Telecommunications Faculty of Automation Computers Electrical Engineering and Electronics Galati University "Dunǎrea de Jos" of Galati 47 Domneasca Str. Galati800008 Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics University 'Dunǎrea de Jos' of Galati 47 Domneasca Street Galati800008 Romania Department of Chemistry Physics & Environment Faculty of Sciences and Environment University "Dunǎrea de Jos" of Galati 47 Domneasca Street Galati800008 Romania

This paper investigates the results of simulations devoted to the acoustic field variation caused by different boundary conditions applied to the backscattering of the acoustic wave in both low and moderately low frequency ranges. The goal is to analyse the object behaviour and the detection ability of the 2D acoustic field approximations when the simulation data of the scattered sound field is available. The plane waves are backscattered by a dummy human body, positioned in a cabin which has a defined size. The dummy human body is created by using clusters of finite and disjointed but tangent circular cylinders. Each cylinder is a scatterer that emulates various boundary conditions i.e., the scatterers can be sound-soft (Dirichlet boundary condition) and sound-hard scatterers (Neumann boundary condition). The cylinders are filled with biological tissue (i.e., fat). The exterior scattering problem is solved using the preconditioned Krylov subspace iterative solvers (GMRES), as a computationally cheaper alternative. We use the hypothesis that the mass density of the obstacle and wave speed in the obstacle are both constant. During the simulation experiments, we neglected the interactions among scatterers. A frequency range from 100 Hz to 1000 Hz is analysed. Both the Sound Pressure Level (SPL) and Radar Cross Section (RCS) are used to analyse the numerical simulation of the sound field. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Acoustic fields

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：