检索结果-内蒙古大学图书馆

PSMFNet:Lightweight Partial Separation and Multiscale Fusion Network for Image Super-Resolution

Computers, Materials & Continua 2024年第10期81卷 1491-1509页

作者： Shuai Cao Jianan Liang Yongjun Cao Jinglun Huang Zhishu Yang Institute of Intelligent Manufacturing GDASGuangdong Key Laboratory of Modern Control TechnologyGuangzhou510030China School of Mechanical&Automotive Engineering South China University of TechnologyGuangzhou511442China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China School of Faculty of Intelligent Manufacturing Wuyi UniversityJiangmen529020China

The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)***,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction *** methods commonly use standard convolutions,which increase the convolutional operation cost of the *** this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this ***,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image ***,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature *** by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an *** can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature *** the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.

关键词： Deep learning single image super-resolution lightweight network multiscale fusion

来源：评论

学校读者我要写书评

暂无评论

Rydberg-Induced Topological Solitons in Three-Dimensional Rotation Spin–Orbit-Coupled Bose–Einstein Condensates

引用

Chinese Physics Letters 2024年第9期41卷 9-14页

作者： Yang Wang Jinlong Cui Hongkai Zhang Yuan Zhao Siliu Xu Qin Zhou Key Laboratory of Optoelectronic Sensing and Intelligent Control Hubei University of Science and TechnologyXianning 437100China School of Electronic and Information Engineering Hubei University of Science and TechnologyXianning 437100China School of Biomedical Engineering and Imaging Xianning Medical CollegeHubei University of Science and TechnologyXianning 437100China Research Center of Nonlinear Science School of Mathematics and Physical SciencesWuhan Textile UniversityWuhan 430200China

We present a novel approach for generating stable three-dimensional(3D)spatiotemporal solitons(SSs)within a rotating Bose–Einstein condensate,incorporating spin–orbit coupling(SOC),a weakly anharmonic potential and cold Rydberg *** intricate system facilitates the emergence of quasi-stable 3D SSs with topological charges|m|≤3 in two spinor components,potentially exhibiting diverse spatial *** findings reveal that the Rydberg long-range interaction,spin–orbit coupling,and rotational angular frequency exert significant influence on the domains of existence and stability of these ***,the Rydberg interaction contributes to a reduction in the norm of topological solitons,while the SOC plays a key role in stabilizing the SSs with finite topological *** research of SSs exhibits potential applications in precision measurement,quantum information processing,and other advanced technologies.

关键词： Rydberg topological Einstein

来源：评论

学校读者我要写书评

暂无评论

Ground fissure development regularity and formation mechanism of shallow buried coal seam mining with Karst landform in Jiaozi coal mine: a case study

引用

Journal of Mountain science 2023年第10期20卷 3101-3120页

作者： ZHU Heng-zhong School of Energy and Mining Engineering Shandong University of Science and TechnologyQingdao 26659oChina State Key Laboratory of Strata Intelligent Control and Green Mining Co-Founded by Shandong Province and the Ministry of Science and Technology Shandong University of Science and TechnologyQingdao 266590China State Key Laboratory of Water Resource Protection and Utilization in Coal Mining Beijing 102209China

A comprehensive study was undertaken at Jiaozi coal mine to investigate the development regularity of ground fissures in shallow buried coal seam mining with Karst landform,shedding light on the development type,geographical distribution,dynamic development process,and failure mechanism of these ground fissures by employing field monitoring,numerical simulation,and theoretical *** findings demonstrate that ground fissure development has an obvious feature of subregion,and its geographical distribution is significantly affected by *** type,open type,and stepped type are three different categories of ground *** fissures emerge dynamically as the panel advances,and they typically develop with a distance of less than periodic weighting step distance in advance of panel advancing *** fissures present the dynamic development feature,temporary fissure has the ability of *** dynamic development process of ground fissure with closed-distance coal seam repeated mining is expounded,and the development scale is a dynamic development stage of“closure→expansion→stabilized”on the basis of the original development *** the perspective of topsoil deformation,the computation model considering two points movement vectors towards two directions of the gob and the ground surface is established,the development criterion considering the critical deformation value of topsoil is *** mechanical model of hinged structure of inclined body is proposed to clarify the ground fissure development,and the interaction between slope activity and ground fissure development is *** research results fulfill the gap of ground fissures about development regularity and formation mechanism,and can contribute to ground fissure prevention and treatment with Karst landform.

关键词： Karst landform Shallow buried coal seam Development regularity Formation mechanism Ground fissure Repeated mining

来源：评论

学校读者我要写书评

暂无评论

A 2-18 GHz 8-W Distributed GaN Power Amplifier Based on Input and Output Matching Network 15

A 2-18 GHz 8-W Distributed GaN Power Amplifier Based on Inpu...

引用

15th International Conference on Microwave and Millimeter Wave technology, ICMMT 2023

作者： Pu, Ziqi Zhu, Xu Qi, Liang Wang, Yong Chi, Pei-Ling Yang, Tao University of Electronic Science and Technology of China Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100191 China

ISBN: (纸本)9798350338874

A high efficiency non-uniform distributed power amplifier (NDPA) based on a 0.15 μm Gallium Nitride (GaN) HEMT process is proposed. The amplifier contains eight amplification cells and uses artificial transmission line theory to design the drain transmission line with decreasing characteristic impedance. To improve the efficiency of the amplifier, the amplifier is class AB biased and designed for optimum impedance matching using the matching networks. The electromagnetic simulation results of the designed amplifier show that the small signal gain of the amplifier is more than 12.6 dB and the saturated output power (Psat) is more than 39.1 dBm with power-added efficiency (PAE) of larger than 28.5% in the frequency range of 2-18 GHz. The core area of the chip is 3.0×1.8 mm2 © 2023 IEEE.

关键词： Power amplifiers

来源：评论

学校读者我要写书评

暂无评论

HWD-YOLO:A New Vision-Based Helmet Wearing Detection Method

引用

Computers, Materials & Continua 2024年第9期80卷 4543-4560页

作者： Licheng Sun Heping Li Liang Wang College of Information Science and Technology Beijing University of TechnologyBeijing100124China Chinese Institute of Coal Science Beijing100013China State Key Laboratory for Intelligent Coal Mining and Strata Control Beijing100013China Engineering Research Center of Digital Community of Ministry of Education Beijing100124China

It is crucial to ensure workers wear safety helmets when working at a workplace with a high risk of safety accidents,such as construction sites and mine *** existing methods can achieve helmet detection in images,their accuracy and speed still need improvements since complex,cluttered,and large-scale scenes of real workplaces cause server occlusion,illumination change,scale variation,and perspective ***,a new safety helmet-wearing detection method based on deep learning is ***,a new multi-scale contextual aggregation module is proposed to aggregate multi-scale feature information globally and highlight the details of concerned objects in the backbone part of the deep neural ***,a new detection block combining the dilate convolution and attention mechanism is proposed and introduced into the prediction *** block can effectively extract deep featureswhile retaining information on fine-grained details,such as edges and small ***,some newly emerged modules are incorporated into the proposed network to improve safety helmetwearing detection performance *** experiments on open dataset validate the proposed *** reaches better performance on helmet-wearing detection and even outperforms the state-of-the-art *** be more specific,the mAP increases by 3.4%,and the speed increases from17 to 33 fps in comparison with the baseline,You Only Look Once(YOLO)version 5X,and themean average precision increases by 1.0%and the speed increases by 7 fps in comparison with the YOLO version *** generalization ability and portability experiment results show that the proposed improvements could serve as a springboard for deep neural network design to improve object detection performance in complex scenarios.

关键词： Object detection deep learning safety helmet wearing detection feature extraction attention mechanism

来源：评论

学校读者我要写书评

暂无评论

GooDFlight: Goal-Oriented Diffusion Model for Flight Trajectory Prediction

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 7447-7465页

作者： Yang, Songru Liu, Liqin Chen, Bowen Cheng, Shaoyuan Shi, Zhenwei Zou, Zhengxia Beihang University Department of Aerospace Intelligent Science and Technology School of Astronautics China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Beijing Institute of Space Mechanics and Electricity Beijing100076 China

Flight trajectory prediction is an essential task in the air traffic control field. Previous approaches to this problem usually follow a single-stage or short-term intention-guided prediction paradigm, which suffers from problems such as insufficient trajectory prediction diversity, limited accuracy and interpretability. Different from existing paradigms, in this paper, we present GooDFlight - A Goal-oriented Diffusion Model for Flight trajectory prediction. GooDFlight is a long-term intention-guided, diversity-emphasizing framework that decouples the flight trajectory prediction process into two stages: goal estimation and trajectory prediction. In the first stage, we propose a One-then-all goal estimation method to sufficiently cover the macro-uncertainty in flight patterns and then tailor the interaction-aware joint goal distribution, which extends the flight intention from a single, deterministic ground truth to the empirical intention distribution from the similar experience. In the second stage, we employ a transformer-based diffusion model to generate stochastic flight trajectories conditioned on the intention estimations, modeling the micro-uncertainty in flight operations under each pattern estimated in stage one. In terms of evaluation metrics, existing metrics have difficulties in accurately reflecting the model's ability to handle the natural uncertainty of trajectories. We further propose a simple yet effective Global-local endpoints Variance (GLeV) metric for evaluating the diversity of predicted trajectories under social acceptance. Our proposed method is validated in-depth on TrajAir, a large-scale dataset collected from the real-world air traffic control environment at the Pittsburgh-Butler Regional Airport, a non-towered general aviation airport. The experimental results demonstrate that the proposed method significantly outperforms other methods in terms of both accuracy and diversity with superior interpretability. © 1965-2011 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A FAS approach for stabilization of generalized chained forms: part 2. Continuous control laws

引用

science China(Information sciences) 2024年第3期67卷 114-135页

作者： Guang-Ren DUAN Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology Center for Control Theory and Guidance Technology Harbin Institute of Technology

In this paper, continuous time-varying stabilizing controllers for the type of general nonholonomic systems proposed and treated in part 1 are designed using the fully actuated system(FAS) approach. The key step is to differentiate the first scalar equation, and by control of the obtained second-order scalar system, a proportional plus integral feedback form for the first control variable is obtained. With the solution to this designed second-order scalar system, the rest equations in the nonholonomic system form an independent time-varying subsystem which is then handled by the FAS approach. The overall designed controller contains an almost arbitrarily chosen design parameter, and is proven to guarantee the uniformly and globally exponential stability of the closed-loop system. The proposed approach is simple and effective,and is demonstrated with a practical example of ship control.

关键词： nonholonomic systems feedback stabilization fully actuated systems Lyapunov stability continuous controllers

来源：评论

学校读者我要写书评

暂无评论

Tracking control in Presence of Obstacles and Uncertainties for Bioinspired Spherical Underwater Robots

引用

Journal of Bionic Engineering 2023年第1期20卷 323-337页

作者： Chunying Li Shuxiang Guo Jian Guo Graduate School of Engineering Kagawa UniversityTakamatsuKagawa761-0396Japan Key Laboratory of Convergence Medical Engineering System and Healthcare Technology the Ministry of Industry and Information TechnologySchool of Life Science and TechnologyBeijing Institute of TechnologyBeijing100081China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of TechnologyBinshui Xidao Extension 391Tianjin300384China

During marine missions,AUVs are susceptible to external disturbances,such as obstacles,ocean currents,etc.,which can easily cause mission failure or *** this paper,considering the strong nonlinearities,external disturbances and obstacles,the kinematic and dynamic model of bioinspired Spherical Underwater Robot(SUR)was ***,the waypoints-based trajectory tracking with obstacles and uncertainties was proposed for SUR to guarantee its safety and ***,the Lyapunov theory was adopted to verify the stability and the Slide Mode control(SMC)method is used to verify the robustness of the control *** addition,a series of simulations were conducted to evaluate the effectiveness of proposed control *** tests,including path-following,static and moving obstacle avoidance were performed which verified the feasibility,robustness and effectiveness of the designed control ***,a series of experiments in real environment were performed to verify the performance of the control *** simulation and experimental results of the study supplied clues to the improvement of the path following capability and multi-obstacle avoidance of AUVs.

关键词： Path following Obstacle avoidance Bioinspired.Spherical underwater robot(SUR) Lyapunov theory

来源：评论

学校读者我要写书评

暂无评论

Robust Bounded-H8 control for High-Order Fully Actuated Systems Based on FAS Approaches 3

Robust Bounded-H8 Control for High-Order Fully Actuated Syst...

引用

3rd Conference on Fully Actuated System Theory and Applications, FASTA 2024

作者： Hu, Liyao Duan, Guangren Harbin Institute of Technology Center for Control Theory and Guidance Technology Harbin150001 China Southern University of Science and Technology Shenzhen Key Laboratory of Control Theory and Intelligent Systems Shenzhen518055 China

ISBN: (纸本)9798350373691

This paper investigates the robust bounded-H8 stabilization for a class of high-order fully actuated systems (FASs) with time-varying uncertainty and disturbance. Based on the FAS approaches and the H8 control, a robust bounded-H8 controller is designed, which guarantees that the system state and its derivatives of each order are globally bounded. Furthermore, a combined disturbance, composed of part time-varying uncertainty and disturbance, is given. With the help of the combined disturbance, the impact of the uncertainty and the disturbance on system output can be attenuated simultaneously, because the closed-loop high-order FAS has the bounded-H8 performance. A simulation example is provided to demonstrate the effectiveness of the proposed control method. © 2024 IEEE.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Data secure transmission intelligent prediction algorithm for mobile industrial IoT networks

引用

Digital Communications and Networks 2023年第2期9卷 400-410页

作者： Lingwei Xu Hao Yin Hong Jia Wenzhong Lin Xinpeng Zhou Yong Fu Xu Yu Department of Information Science and Technology Qingdao University of Science and TechnologyQingdao266061China Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen UniversityXiamen361005China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control(Minjiang University) Fuzhou350121China Faculty of Information Science and Engineering Ocean University of ChinaQingdao266100China Shandong Provincial Key Laboratory of Computer Networks Shandong Computer Science Center(National Supercomputer Center in Jinan)JinanChina

Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent *** mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interconnection of all *** variety of application scenarios has brought serious challenges to mobile IIoT networks,which face complex and changeable communication *** data secure transmission is critical for mobile IIoT *** paper investigates the data secure transmission performance prediction of mobile IIoT *** cut down computational complexity,we propose a data secure transmission scheme employing Transmit Antenna Selection(TAS).The novel secrecy performance expressions are first ***,to realize real-time secrecy analysis,we design an improved Convolutional Neural Network(CNN)model,and propose an intelligent data secure transmission performance prediction *** mobile signals,the important features may be removed by the pooling *** will lead to negative effects on the secrecy performance prediction.A novel nine-layer improved CNN model is *** of the input and output layers,it removes the pooling layer and contains six convolution ***,Back-Propagation(BP)and LeNet methods are employed to compare with the proposed *** simulation analysis,good prediction accuracy is achieved by the CNN *** prediction accuracy obtains a 59%increase.

关键词： Mobile IIoT networks Data secure transmission Performance analysis intelligent prediction Improved CNN

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：