检索结果-内蒙古大学图书馆

SHAA: Spatial Hybrid Attention Network with Adaptive Cross-Entropy Loss Function for UAV-view Geo-localization

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Nanhua Zhang, Dongshuo Jiang, Kai Yu, Meng Zhu, Yeqing Lou, Tai-Shan Zhao, Liangyu Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China Zhengzhou University of Light Industry School of Electrical and Information Engineering Zhengzhou450002 China Beijing Institute of Technology School of Aerospace Engineering Beijing100081 China Beijing Institute of Technology Zhengzhou Research Institute Zhengzhou450000 China Beijing Institute of Technology National Key Laboratory of Land and Air Based Information Perception and Control Beijing100081 China

Cross-view geo-localization provides an offline visual positioning strategy for unmanned aerial vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments. However, it still faces the following challenges, leading to suboptimal localization performance: 1) Existing methods primarily focus on extracting global features or local features by partitioning feature maps, neglecting the exploration of spatial information, which is essential for extracting consistent feature representations and aligning images of identical targets across different views. 2) Cross-view geo-localization encounters the challenge of data imbalance between UAV and satellite images. To address these challenges, the Spatial Hybrid Attention Network with Adaptive Cross-Entropy Loss Function (SHAA) is proposed. To tackle the first issue, the Spatial Hybrid Attention (SHA) method employs a Spatial Shift-MLP (SSM) to focus on the spatial geometric correspondences in feature maps across different views, extracting both global features and fine-grained features. Additionally, the SHA method utilizes a Hybrid Attention (HA) mechanism to enhance feature extraction diversity and robustness by capturing interactions between spatial and channel dimensions, thereby extracting consistent cross-view features and aligning images. For the second challenge, the Adaptive Cross-Entropy (ACE) loss function incorporates adaptive weights to emphasize hard samples, alleviating data imbalance issues and improving training effectiveness. Extensive experiments on widely recognized benchmarks, including University-1652, SUES-200, and DenseUAV, demonstrate that SHAA achieves state-of-the-art performance, outperforming existing methods by over 3.92%. Code will be released at: https://***/chennanhua001/SHAA. © 1991-2012 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

Taking Myopic Best Response Against The Hedge Algorithm

Taking Myopic Best Response Against The Hedge Algorithm

引用

Chinese control Conference (CCC)

作者： Xinxiang Guo Yifen Mu School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China The Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

With the rapid development of artificial intelligence (AI), the game between the human and machine/AI becomes more and more common. The related theoretical analysis becomes significant and necessary, which however is still rare. This problem involves evolution analysis and optimal control of dynamic game systems driven by learning algorithms. In this paper, we consider a finitely repeated two-player zero-sum game. We study the dynamic evolution process of the game system, in which one player employs the Hedge algorithm and the other player takes the myopic best response. By the updating formula of the Hedge algorithm, we define a quantity called the state and construct the State Transition Triangle Graph (STTG). Then, we prove that the game system is periodic after o(T) stages.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Optimization Through Deep Learning Classification of COVID-19 in Chest X-Ray Images

引用

Computers, Materials & Continua 2022年第11期73卷 4193-4210页

作者： Nagwan Abdel Samee El-Sayed M.El-Kenawy Ghada Atteia Mona M.Jamjoom Abdelhameed Ibrahim Abdelaziz A.Abdelhamid Noha E.El-Attar Tarek Gaber Adam Slowik Mahmoud Y.Shams Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh 11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura 35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura 35712Egypt Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh 11671Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura University35516MansouraEgypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams University11566CairoEgypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Faculty of Computers and Artificial Intelligence Benha UniversityEgypt School of Science Engineeringand EnvironmentUniversity of SalfordUK Faculty of Computers and Informatics Suez Canal UniversityIsmailia41522Egypt Koszalin University of Technology Poland Faculty of Artificial Intelligence Kafrelsheikh UniversityKafrelsheikh33511Egypt

As corona virus disease(COVID-19)is still an ongoing global outbreak,countries around the world continue to take precautions and measures to control the spread of the *** of the excessive number of infected patients and the resulting deficiency of testing kits in hospitals,a rapid,reliable,and automatic detection of COVID-19 is in extreme need to curb the number of *** analyzing the COVID-19 chest X-ray images,a novel metaheuristic approach is proposed based on hybrid dipper throated and particle swarm *** lung region was segmented from the original chest X-ray images and augmented using various transformation ***,the augmented images were fed into the VGG19 deep network for feature *** the other hand,a feature selection method is proposed to select the most significant features that can boost the classification ***,the selected features were input into an optimized neural network for *** neural network is optimized using the proposed hybrid *** experimental results showed that the proposed method achieved 99.88%accuracy,outperforming the existing COVID-19 detection *** addition,a deep statistical analysis is performed to study the performance and stability of the proposed *** results confirm the effectiveness and superiority of the proposed approach.

关键词： Covid-19 feature selection dipper throated optimization particle swarm optimization deep learning

来源：评论

学校读者我要写书评

暂无评论

A domain decomposition strategy for natural imposition of mixed boundary conditions in port-Hamiltonian systems

arXiv

引用

arXiv 2025年

作者： de Jong, Sjoerd D.M. Brugnoli, Andrea Rashad, Ramy Zhang, Yi Stramigioli, Stefano Department of Microelectronics Delft University of Technology Delft Netherlands ICA Université de Toulouse ISAE–SUPAERO INSA CNRS MINES ALBI UPS Toulouse France Control and Instrumentation Engineering Department King Fahd University of Petroleum and Minerals Saudi Arabia School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China Robotics and Mechatronics Department University of Twente Netherlands

[Abstract] In this contribution, a finite element scheme to impose mixed boundary conditions without introducing Lagrange multipliers is presented for wave propagation phenomena described as port-Hamiltonian systems. The strategy relies on finite element exterior calculus and a domain decomposition to interconnect two systems with different causalities. The spatial domain is split into two parts by introducing an arbitrary interface. Each subdomain is discretized with a mixed finite element formulation that introduces a uniform boundary condition in a natural way as the input. In each subdomain the spaces are selected from a finite element subcomplex to obtain a stable discretization. The two systems are then interconnected together by making use of a feedback interconnection. This is achieved by discretizing the boundary inputs using appropriate spaces that couple the two formulations. The final systems includes all boundary conditions explicitly and does not contain any Lagrange multiplier. Each subdomain is integrated using an implicit midpoint scheme in an uncoupled way from the other by means of a leapfrog scheme. The proposed strategy is tested on three different examples: the Euler-Bernoulli beam, the wave equation and the Maxwell equations. Numerical tests assess the conservation properties of the scheme and the effectiveness of the methodology. © 2025, CC BY.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Tracking control for Nonlinear Servo System with Unknown Time-Varying Parameters and Uncertainties

Adaptive Neural Tracking Control for Nonlinear Servo System ...

引用

Chinese control Conference (CCC)

作者： Faxiang Zhang Guanbin Gao Jing Na Jiande Wu Faculty of Mechanical and Electrical Engineering and Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment Kunming University of Science and Technology Kunming P. R. China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming P. R. China

This paper solves the neural network (NN) tracking control problem for uncertain nonlinear servo system with time-varying parameters and uncertainties. To address the uncertain nonlinear function with unknown time-varying parameters (i.e., unknown nonlinear spatiotemporal function), the time-varying parameter extraction method is used to separate the time-varying parameters from uncertain nonlinear spatiotemporal function, which yields an unknown state-based boundary function. By the tools of NN and adaptive technology, an adaptive neural tracking controller is designed, which guarantees the uniformly ultimately bounded (UUB) performance of the resulting closed-loop system. The effectiveness of the designed method is verified by simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-Aware Joint DNN Model Deployment and Partition Optimization for Delay-Efficient Collaborative Edge Inference

arXiv

引用

arXiv 2025年

作者： Cheng, Zhipeng Xia, Xiaoyu Wang, Hong Liwang, Minghui Chen, Ning Fan, Xuwei Wang, Xianbin School of Future Science and Engineering Soochow University Suzhou215006 China School of Computing Technologies RMIT University MelbourneVIC Australia Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Tongji University Shanghai201804 China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai201804 China Qingdao China College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou350002 China Department of Electrical and Computer Engineering Western University ON Canada

Edge inference (EI) is a key solution to address the growing challenges of delayed response times, limited scalability, and privacy concerns in cloud-based Deep Neural Network (DNN) inference. However, deploying DNN models on resource-constrained edge devices faces more severe challenges, such as model storage limitations, dynamic service requests, and privacy risks. This paper proposes a novel framework for privacy-aware joint DNN model deployment and partition optimization to minimize long-term average inference delay under resource and privacy constraints. Specifically, the problem is formulated as a complex optimization problem considering model deployment, user-server association, and model partition strategies. To handle the NP-hardness and future uncertainties, a Lyapunov-based approach is introduced to transform the long-term optimization into a single-time-slot problem, ensuring system performance. Additionally, a coalition formation game model is proposed for edge server association, and a greedy-based algorithm is developed for model deployment within each coalition to efficiently solve the problem. Extensive simulations show that the proposed algorithms effectively reduce inference delay while satisfying privacy constraints, outperforming baseline approaches in various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Cooperative guidance strategy for multiple hypersonic gliding vehicles system

引用

Chinese Journal of Aeronautics 2020年第3期33卷 990-1005页

作者： Jianglong YU Xiwang DONG Qingdong LI Zhang REN Jinhu LV School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control LaboratoryBeihang UniversityBeijing 100083China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100083China Shananxi Key Laboratory of Integrated and Intelligent Navigation Xi’an 710068China

Cooperative guidance strategy for multiple hypersonic gliding vehicles system with flight constraints and cooperative constraints is *** paper mainly cares about the coordination of the entry glide flight phase and driving-down *** from the existing results,both the attack time and the attack angle constraints are considered ***, for the entry glide flight phase, a two-stage method is proposed to achieve the rapid cooperative trajectories planning, where the control signal corridors are designed based on the quasi-equilibrium gliding *** the first stage, the bank angle curve is optimized to achieve the attack angle *** the second stage, the angle of attack curve is optimized to achieve the attack time *** optimized parameters can be obtained by the secant ***, for the driving-down phase, the cooperative terminal guidance law is designed where the terminal attack time and attack angle are *** guidance law is then transformed into the bank angle and angle of attack *** cooperative guidance strategy is summarized as an ***, a numerical simulation example with three hypersonic gliding vehicles is provided for revealing the effectiveness of the acquired strategy and algorithm.

关键词： Attack angle constraints Attack time constraints Cooperative guidance Cooperative path planning Entry guidance Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

A Shadowcasting-Based Next-Best-View Planner for Autonomous 3D Exploration

arXiv

引用

arXiv 2021年

作者： Batinovic, Ana Ivanovic, Antun Petrovic, Tamara Bogdan, Stjepan University of Zagreb Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems Unska 3 Zagreb10000 Croatia

—In this paper, we address the problem of autonomous exploration of unknown environments with an aerial robot equipped with a sensory set that produces large point clouds, such as LiDARs. The main goal is to gradually explore an area while planning paths and calculating information gain in short computation time, suitable for implementation on an on-board computer. To this end, we present a planner that randomly samples viewpoints in the environment map. It relies on a novel and efficient gain calculation based on the Recursive Shadowcasting algorithm. To determine the Next-Best-View (NBV), our planner uses a cuboid-based evaluation method that results in an enviably short computation time. To reduce the overall exploration time, we also use a dead end resolving strategy that allows us to quickly recover from dead ends in a challenging environment. Comparative experiments in simulation have shown that our approach outperforms the current state-of-the-art in terms of computational efficiency and total exploration time. The video of our approach can be found at https://***/playlist?list=PLC0C6uwoEQ8ZDhny1V dmFXLeTQOSBibQl. © 2021, CC BY-SA.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

The SRIVC algorithm for continuous-time system identification with arbitrary input excitation in open and closed loop

The SRIVC algorithm for continuous-time system identificatio...

引用

IEEE Conference on Decision and control

作者： Rodrigo A. González Cristian R. Rojas Siqi Pan James S. Welsh Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden School of Electrical Engineering and Computing University of Newcastle Australia

ISBN: (纸本)9781665436601

Continuous-time system identification has primarily dealt with sampled input and output data for constructing continuous-time models. However, sampled signals can lead to inaccurate models if their intersample behavior is not addressed appropriately. In this paper, this effect is explored in detail with respect to the SRIVC and CLSRIVC estimators, which are some of the most popular methods for open and closed-loop continuous-time system identification respectively. Based on our consistency analysis, we propose an algorithm that alleviates the asymptotic bias of these methods for arbitrary input excitations and provide an alternative procedure to achieve consistent estimates for band-limited signals. Simulation examples show the effectiveness of our approach.

关键词： Filtering Conferences control systems Data models System identification

来源：评论

学校读者我要写书评

暂无评论

Sim2Air - Synthetic Aerial Dataset for UAV Monitoring

arXiv

引用

arXiv 2021年

作者： Barisic, Antonella Petric, Frano Bogdan, Stjepan The University of Zagreb Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems Unska 3 Zagreb10000 Croatia

In this paper we propose a novel approach to generate a synthetic aerial dataset for application in UAV monitoring. We propose to accentuate shape-based object representation by applying texture randomization. A diverse dataset with photo-realism in all parameters such as shape, pose, lighting, scale, viewpoint, etc. except for atypical textures is created in a 3D modelling software Blender. Our approach specifically targets two conditions in aerial images where texture of objects is difficult to detect, namely challenging illumination and objects occupying only a small portion of the image. Experimental evaluation of YOLO and Faster R-CNN detectors trained on synthetic data with randomized textures confirmed our approach by increasing the mAP value (17 and 3.7 percentage points for YOLO;20 and 1.1 percentage points for Faster R-CNN) on two test datasets of real images, both containing UAV-to-UAV images with motion blur. Testing on different domains, we conclude that the more the generalisation ability is put to the test, the more apparent are the advantages of the shape-based representation. © 2021, CC BY-NC-SA.

关键词： Robotics

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：