检索结果-内蒙古大学图书馆

An Uncertainty Quantization-Based Method for Anti-UAV Detection in Infrared Images

Computers, Materials & Continua 2025年第4期83卷 1439-1458页

作者： Can Wu Wenyi Tang Yunbo Rao Yinjie Chen Hui Ding Shuzhen Zhu Yuanyuan Wang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China State Key Laboratory of Air Traffic Management System Nanjing210000China National Airspace Management Center Beijing100094China

Infrared unmanned aerial vehicle(UAV)target detection presents significant challenges due to the inter-play between small targets and complex *** methods,while effective in controlled environments,often fail in scenarios involving long-range targets,high noise levels,or intricate backgrounds,highlighting the need for more robust *** address these challenges,we propose a novel three-stage UAV segmentation framework that leverages uncertainty quantification to enhance target *** framework incorporates a Bayesian convolutional neural network capable of generating both segmentation maps and probabilistic uncertainty *** utilizing uncer-tainty predictions,our method refines segmentation outcomes,achieving superior detection ***,this marks the first application of uncertainty modeling within the context of infrared UAV target *** evaluations on three publicly available infrared UAV datasets demonstrate the effectiveness of the proposed *** results reveal significant improvements in both detection precision and robustness when compared to state-of-the-art deep learning *** approach also extends the capabilities of encoder-decoder convolutional neural networks by introducing uncertainty modeling,enabling the network to better handle the challenges posed by small targets and complex environmental *** bridging the gap between theoretical uncertainty modeling and practical detection tasks,our work offers a new perspective on enhancing model interpretability and *** codes of this work are available openly at https://***/general-learner/UQ_Anti_UAV(acceessed on 11 November 2024).

关键词： Object segmentation uncertainty quantification bayesian convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Plasticity and rejuvenation of aged metallic glasses by ultrasonic vibrations

引用

Journal of Materials Science & Technology 2024年第14期181卷 231-239页

作者： Zhe Chen Shuai Ren Rui Zhao Jian Zhu Xin Li Heting Zhang Hongji Lin Jiahua Zhu Sajad Sohrabi Wenqing Ruan Jiang Ma Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen UniversityShenzhen 518060China Shenzhen Key Laboratory of High Performance Nontraditional Manufacturing College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen 518060China Institute of Physics Chinese Academy of SciencesBeijing 100190China School of Mechanical Electrical and Information EngineeringShandong UniversityWeihai 264209China

Metallic glasses(MGs)possess exceptional properties,but their properties consistently deteriorate over time,thereby resulting in increased complexity in *** thus poses a formidable challenge to the forming of long-term aged ***,we report ultrasonic vibration(UV)loading can lead to large plas-ticity and strong rejuvenation in significantly aged MGs within 1 s.A large UV-induced plasticity(UVIP)of 80%height reduction can be achieved in LaNiAl MG samples aged at 85%of its glass transition tem-perature(0.85 T_(g))for a duration of up to 1 *** energy threshold required for UVIP monotonously increases with aging *** the UV loading process,the aged samples show strong rejuvenation,with the relaxation enthalpy even surpassing that of as-cast *** findings suggest that UV loading is an effective technique for forming and rejuvenating aged MGs simultaneously,providing an alterna-tive avenue to explore the interplay between the property and microstructures as well as expanding the application prospects of MGs.

关键词： Metallic glass Ultrasonic vibration induced plasticity Aging Rejuvenation

来源：评论

学校读者我要写书评

暂无评论

Adjustable patch and feature prior token-based transformer for weakly supervised semantic segmentation

引用

International Journal of Computers and Applications 2024年第7期46卷 445-454页

作者： Li, Linjuan Zhang, Haoxue Xie, Gang Bai, Yanhong School of Electronic and Information Engineering Taiyuan University of Science and Technology Taiyuan China Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan China

Weakly supervised semantic segmentation is a challenging task, utilizing only low-cost weak supervision to produce pixel-level predictions. Existing transformer-based methods for weakly supervised semantic segmentation have some limitations: (1) Fixing patch size might destroy the structured semantics, which is unfriendly to objects of different scales, and (2) Ignoring the prior features when using multi-head attention mechanisms might lead to inaccurate segmentation localization. To tackle these issues, we proposed an effective transformer framework coupled with the adjustable patch and prior feature tokens, termed as APFPformer, in which an adjustable patch module is developed to split the image according to the area of the salient object for preserving the structured semantics in patches. A prior feature token module is devised to exploit the edge and texture information as prior tokens, ensuring the gain of discriminative representation. Additionally, a single-stage scheme is applied to reduce the computation and rapid segmentation process. Our experiments demonstrate the superiority of our approach over early methods, gaining competitive mean Intersection-over-Union scores of 67.9% on the PASCAL VOC2012 dataset and 40.2% on the MS COCO dataset. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Joint Task Offloading and Resource Allocation Strategy for Space-Air-Ground Integrated Vehicular Networks

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1027-1043页

作者： Yuanshuo Gang Yuexia Zhang Zhihai Zhuo School of Information and Communication Engineering Beijing Information Science and Technology UniversityBeijing 100101China Key Laboratory of Modern Measurement and Control Technology Ministry of EducationBeijing Information Science and Technology UniversityBeijing 100101China

Space-Air-Ground integrated Vehicular Network(SAGVN)aims to achieve ubiquitous connectivity and provide abundant computational resources to enhance the performance and efficiency of the vehicular ***,there are still challenges to overcome,including the scheduling of multilayered computational resources and the scarcity of spectrum *** address these problems,we propose a joint Task Offloading(TO)and Resource Allocation(RA)strategy in SAGVN(namely JTRSS).This strategy establishes an SAGVN model that incorporates air and space networks to expand the options for vehicular TO,and enhances the edge-computing resources of the system by deploying edge *** minimize the system average cost,we use the JTRSS algorithm to decompose the original problem into a number of subproblems.A maximum rate matching algorithm is used to address the channel allocation and the Lagrangian multiplier method is employed for computational *** acquire the optimal TO decision,a differential fusion cuckoo search algorithm is *** simulation results demonstrate the significant superiority of the JTRSS algorithm in optimizing the system average cost.

关键词： edge computing Resource Allocation(RA) Space-Air-Ground integrated Vehicular Network(SAGVN) Task Offloading(TO)

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Planning Method Based on Trust Region Policy Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Ye, Bao-Lin Zhang, Jiajie Li, Lingxi Wu, Weimin Jiaxing Key Laboratory of Smart Transportations the School of Information Science and Engineering Jiaxing University China Elmore Family School of Electrical and Computer Engineering Purdue University Indianapolis USA State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight parameter updates during the training process. Therefore, this paper proposes a novel trajectory planning method based on deep reinforcement learning trust region policy optimization (TRPO). Firstly, in order to enhance the robustness of the trajectory planning method based on deep reinforcement learning TRPO, a TRPO-LSTM based decision model was proposed. More specifically, a long short term memory (LSTM) based state feature extraction network was designed and embeded into a TRPO-based decision model to enhance the ability of TRPO to extract information from the environmental state space. Secondly, in order to make the planned trajectory adaptive to the dynamic changes of traffic environment, we presented a novel TRPO-LSTM trajectory fitting algorithm. To the best of our knowledge, this is the first work aiming at applying the TRPO-LSTM based decision model in the trajectory fitting process to search the optimal longitudinal trajectory speed. Finally, the proposed trajectory planning method was implemented and simulated on the CARLA simulator. The experimental results show that, compared with existing trajectory planning methods based on deep reinforcement learning algorithms, our proposed method achieves a cumulative reward improvement of over 28.9% in the scenario of four lane highway, and has better robustness. Meanwhile, the proposed method can achieve a lower collision rate of 0.93% while improving the average speed and comfort of vehicle driving. IEEE

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Advanced modeling of the absorption enhancement of black carbon particles in chamber experiments by considering the morphology and coating thickness

引用

Frontiers of Environmental Science & engineering 2024年第9期18卷 129-142页

作者： Xiaodong Wei Jianlin Hu Chao Liu Xiaodong Xie Junjie Yin Song Guo Min Hu Jianfei Peng Huijun Wang Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Collaborative Innovation Center of Atmospheric Environment and Equipment TechnologySchool of Environmental Science and EngineeringNanjing University of Information Science&TechnologyNanjing 210044China Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters Key Laboratory of Meteorological Disaster(Ministry of Education)Nanjing University of Information Science and TechnologyNanjing 210044China Nansen−Zhu International Research Centre Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China East China Air Traffic Management Bureau CAAC Shanghai 200335China State Key Joint Laboratory of Environmental Simulation and Pollution Control International Joint Laboratory for Regional Pollution Control(IJRC)(Ministry of Education)College of Environmental Sciences and EngineeringPeking UniversityBeijing 100871China Tianjin Key Laboratory of Urban Transport Emission Research&State Environmental Protection Key Laboratory of Urban Ambient Air Particulate Matter Pollution Prevention and Control College of Environmental Science and EngineeringNankai UniversityTianjin 300071China

Measurements studies have shown that the absorption of radiation by black carbon(BC)increases as the particles ***,there are significant discrepancies between the measured and modeled absorption enhancement(E_(abs)),largely due to the simplifications used in modeling the mixing states and shape *** took advantage of chamber experiments on BC aging and developed an efficient method to resolve the particle shape based on the relationship between the coating fraction(ΔD_(ve)/D_(ve),0)and fractal dimension(D_(f)),which can also reflect the variations of D_(f)during the whole BC aging *** with externally and partly mixed states(0≤ΔD_(ve)/D_(ve),0≤0.5)can be considered to be uniformly distributed with the D_(f)values of 1.8–2.1,whereas the Df values are constrained in the range 2.2–2.8 for fully mixed states(ΔD_(ve)/D_(ve),0>0.5).The morphological parameters(i.e.,the effective density and the dynamic shape factor)were compared with the measured values to verify the simulated *** simulated mean deviations of morphological parameters were smaller than 8%for the method resolving the particle *** applying a realistic shape and refractive index,the mass absorption cross for fully mixed states can be improved by 11%compared with a simplified core–shell *** on our understanding of the influence of D_(f)andΔD_(ve)/D_(ve),0 on E_(abs),we propose a two-stage calibration equation to correct the E_(abs)values estimated by the core–shell model,which reduces the simulation error in the Mie calculation by 6%–14%.

关键词： Black carbon Mixing states Fractal dimension Dynamic shape factor Absorption enhancement

来源：评论

学校读者我要写书评

暂无评论

Design and Performance Analysis of HMDV Dynamic Inertial Suspension Based on Active Disturbance Rejection control

引用

Computer Modeling in engineering & Sciences 2024年第8期140卷 1485-1506页

作者： Xiaofeng Yang Wei Wang Yujie Shen Changning Liu Tianyi Zhang School of Automotive and Traffic Engineering Jiangsu UniversityZhenjiang212013China Automotive Engineering Research Institute Jiangsu UniversityZhenjiang212013China Chongqing Key Laboratory of Urban Rail Transit System Integration and Control Chongqing400074China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan universityChangsha410082China

This paper addresses the impact of vertical vibration negative effects,unbalanced radial forces generated by the static eccentricity of the hub motor,and road excitation on the suspension performance of Hub Motor Driven Vehicle(HMDV).A dynamic inertial suspension based on Active Disturbance Rejection control(ADRC)is proposed,combining the vertical dynamic characteristics of dynamic inertial suspension with the features of ADRC,which distinguishes between internal and external disturbances and arranges the transition ***,a simulation model of the static eccentricity of the hub motor is established to simulate the unbalanced radial electromagnetic force generated under static eccentricity.A quarter-vehicle model of an HMDV with a controllable dynamic inertial suspension is then ***,the passive suspension model is studied under different grades of road excitation,and the impact mechanism of suspension performance at speeds of 0–20 m/s is ***,the three main components within the ADRC controller are designed for the second-order controlled system,and optimization algorithms are used to optimize its internal ***,the performance of the traditional passive suspension,the PID-based controllable dynamic inertial suspension,and the ADRC-based controllable dynamic inertial suspension are analyzed under different road *** results show that,under sinusoidal road input,the ADRC-based controllable dynamic inertial suspension exhibits a 52.3%reduction in the low-frequency resonance peak in the vehicle body acceleration gain diagram compared to the traditional passive suspension,with significant performance optimization in the high-frequency *** random road input,the ADRC-based controllable dynamic inertial suspension achieves a 29.53%reduction in the root mean square value of vehicle body acceleration and a 14.87%reduction in dynamic tire *** indicates that the designed controllable dynamic inertia

关键词： HMDV static eccentricity ADRC dynamic inertial suspension road excitation

来源：评论

学校读者我要写书评

暂无评论

Evolution hydrothermal aging resistance mechanism study of zirconium and manganese doped CeO_(2)catalysts in soot catalytic combustion based on low Miller indices crystal surface effect

引用

Journal of Rare Earths 2024年第7期42卷 1272-1281,I0003页

作者： Zonglin Li Pan Wang Hong Ni Chengcheng Ao Lidong Zhang Hefeng Zhang Kai Li School of Automotive and Traffic Engineering Jiangsu UniversityZhenjiang212013China State Environmental Protection Key Laboratory of Vehicle Emission Control and Simulation Chinese Research Academy of Environmental ScienceBeijing100012China National Synchrotron Radiation Laboratory University of Science and Technology of ChinaHefei230026China

The thermogravimetric analysis(TGA)experiments were carried out to reveal the mechanism of Zr and Mn doping on catalytic activity of CeO_(2)catalyst both fresh and after hydrothermal aging,and the lattice morphology and valence changes were characterized by means of Brunauer-Emmett-Teller(BET)method,X-ray diffraction(XRD),X-ray photoelectron spectroscopy(XPS),and H_(2)-temperature programmed reduction(H_(2)-TPR).Density functional theory(DFT)and molecular thermodynamics calculations were applied to investigate the change in catalytic activity,crystal surface energy and crystal morphology caused by hydrothermal *** maximum reaction rate temperature of fresh Mn/CeO_(2)(389℃)is similar to that of CeO_(2)(371℃)and lower than that of Zr/CeO_(2)(447℃),but the catalytic performance of CeO_(2)decreases more severely after hydrothermal *** catalyst crystals show different degrees of crystal surface migration after hydrothermal aging,which leads to the reduction of Ce^(3+)/Ce^(4+) ratio and the active sites *** calculations indicate that the doping of Zr and Mn reduces the surface energy of the low Miller indices surface and increases the oxygen vacancy formation energy,leading to better thermal stability and lower catalytic *** Zr and Mn doping also changes the adsorption energy and Gibbs free energy of H_(2)O,which dominates the migration of(111)to(110)and(100)in the vapor *** crystal surface migration mechanism of CeO_(2)catalysts doped with Zr and Mn induced by H_(2)O molecules at high temperature obtained in this study can provide a valuable addition to the regeneration of CeO_(2)catalysts in the after-treatment systems of diesel engines.

关键词： Soot CeO_(2)-based catalyst CDPF Rare earth metal oxides DFT calculations

来源：评论

学校读者我要写书评

暂无评论

Highly constrained cooperative guidance for flexible landing on asteroids

引用

Chinese Journal of Aeronautics 2025年第4期38卷 349-360页

作者： Chang LYU Zixuan LIANG Shengying ZHU School of Aerospace Engineering Beijing Institute of TechnologyBeijing 100081China Key Laboratory of Autonomous Navigation and Control for Deep Space Exploration(Beijing Institute of Technology) Ministry of Industry and Information TechnologyBeijing 100081China

Flexible lander,composed of multiple nodes connected by flexible material,can reducethe bouncing and overturning during the asteroid *** satisfy the complex constraints inthe node cooperation of the flexible landing,an intelligent cooperative guidance method is *** method consists of a double-layer cooperative guidance structure,a guidance parameterdetermination approach,and an action priority *** double-layer contains a basic guid-ance used to satisfy the terminal state constraints,and a compensatory guidance used to satisfythe lander's attitude *** the compensatory guidance,the parameters are determinedby multi-agent system,which are trained according to the performance index of flexible landing *** action priority strategy is used to reduce the detrimental effect of parameter inconsis-tency on the node *** simulation of flexible landing shows that the cooperativeguidance method is effective in improving the landing accuracy while satisfying the ***,the method is robust to the disturbance in the navigation and control.

关键词： Asteroid Flexible lander Multi-constraint Cooperative guidance Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-party semi-quantum private comparison protocol of size relation based on two-dimensional Bell states

引用

Chinese Physics B 2024年第11期33卷 184-192页

作者： Bing Wang Li-Hua Gong San-Qiu Liu Jiangxi Province Key Laboratory of Fusion and Information Control Department of PhysicsNanchang UniversityNanchang 330031China School of Physics and Materials Nanchang UniversityNanchang 330031China Department of Electronic Information Engineering Nanchang UniversityNanchang 330031China

Currently,all quantum private comparison protocols based on two-dimensional quantum states can only compare equality,via using high-dimensional quantum states that it is possible to compare the size relation in existing *** addition,it is difficult to manipulate high-dimensional quantum states under the existing conditions of quantum information processing,leading to low practicality and engineering feasibility of protocols for comparing size *** this situation,we propose an innovative *** proposed protocol can make size comparison by exploiting more manageable two-dimensional Bell states,which significantly enhances its feasibility with current quantum ***,the proposed protocol enables multiple participants to compare their privacies with the semi-quantum *** communication process of the protocol is simulated on the IBM Quantum Experience platform to verify its *** analysis shows that the proposed protocol can withstand common attacks while preserving the privacies of all ***,the devised protocol may provide an important reference for implementation of quantum private size comparison protocols.

关键词： two-dimensional Bell state size relation multi-party semi-quantum private comparison

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：