检索结果-内蒙古大学图书馆

9th International Conference on Image, Vision and Computing, ICIVC 2024

作者： Zeng, Shuqi Liu, Jun Xu, Ji Luo, Yuan School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Key Laboratory of Biomarkers and In Vitro Diagnosis Translation Zhejiang province Hangzhou China Hubei Engineering Research Center for Intelligent Digital Technology in New Power System Hubei Central China Technology Development of Electric Power Co. Ltd Wuhan China

ISBN: (纸本)9798350385991

The diffusion probability model has recently garnered remarkable achievements in image generation, emerging as a prominent research focus within computer vision. It has been observed through numerous studies that the diffusion probability model holds potential for application across various domains within computer vision. Drawing inspiration from these models, we present a novel approach to extend their utility to the realm of brain tumor medical image segmentation. Our method entails training the model utilizing a diffusion framework, followed by iterative refinement of segmentation outcomes by incorporating additional encoding layers and decoders. This method employs an end-to-end training approach without relying on pre-trained backbone networks. Given the probabilistic nature of the results generated by the diffusion model and to simulate the actual decision-making process of doctors, we will generate multiple segmentation results and apply denoising techniques to obtain a stable output. These results will then be integrated into the final segmentation map to achieve more precise segmentation. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Design of Hardware Accelerator Architecture for Target Detection Based on ZYNQ 3

Design of Hardware Accelerator Architecture for Target Detec...

引用

3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023

作者： Zhang, Xianbin Zhang, Xiaoqiang Zheng, Xinxing Zhang, Xing Anhui Polytechnic University Institute of Integrated Circuit Wuhu China Anhui Automotive Display Integrated System Engineering Research Center Wuhu China Wuhu Institute of Technology School of Information and Artificial Intelligence Wuhu China Wuhu Automot. Intelligent Product Development and Application Engineering Technology Research Center Wuhu China

ISBN: (纸本)9798350316674

To implement target detection algorithms such as YOLO on FPGA and meet the strict requirement of real-time target detection with low latency, a variety of optimization methods from model quantization to hardware optimization are needed. Firstly, the layer fusion and the bit width quantization strategy are used to reduce computational complexity. Then, the column-based fine-grained pipeline architecture with padding skip technology is used to reduce start time. Next, the double symbol multiplication correction circuit is introduced to shorten the calculation time of CNN. Finally, the design space exploration algorithm is used to solve the problem of resource allocation in the FPGA-based convolutional neural network hardware accelerator and improve the efficiency of DSP. To verify the neural network accelerator architecture, we implement YOLOv2-tiny network on Xilinx ZCU104. Compared with the previous accelerators, the latency is reduced by 1.88 to 2.07 times, and the DSP efficiency reaches 90.9%. © 2023 IEEE.

关键词： convolutional neural network hardware accelerator low latency the column-based fine-grained pipeline the design space exploration

来源：评论

学校读者我要写书评

暂无评论

Influence of different turbulence models on tip vortex prediction 4

Influence of different turbulence models on tip vortex predi...

引用

4th IAHR Asian Working Group Symposium on Hydraulic Machinery and systems

作者： Fang, Mingkun Li, Na Tao, Ran Xiao, Ruofu College of Water Resources and Civil Engineering China Agricultural University Beijing100083 China Beijing Engineering Research Center of Safety and Energy Saving Technology for Water Supply Network System China Agricultural University Beijing100083 China China Irrigation and Drainage Development Center Beijing100000 China

Tip vortex cavitation usually occurs in marine propellers and axial-flow turbines, the cavitation in the tip vortex could potentially result in blade erosion, at the same time, it will cause the pump vibration and noise emission. The tip vortex mainly occurs in rotating machinery with complex three-dimensional flow, but the prediction of the hydrofoil tip vortex can provide a basis for the study of the blade tip vortex in rotating machinery by simplifying the blade model. Hence, in this paper, we use the commercial software CFX to investigate the impact of distinct turbulence models on the configuration of tip vortex distribution in the NACA 16-020 hydrofoil, including SST (Shear Stress Transport), DES (Detached Eddy simulation), LES (Large Eddy simulation) turbulence models which are widely used in the field of rotating machinery. At the same time, the axial and radial velocity distributions at different locations downstream of the tip of the hydrofoil are compared to analyse the effects on the velocity distribution near the vortex core line stemming from various turbulence models. By comparing with the experimental data, the most accurate turbulence model for tip vortex prediction is obtained, which will provide guidance for the next step tip vortex prediction and the control of tip vortex flow. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Turbulence models

来源：评论

学校读者我要写书评

暂无评论

Pressure Fluctuation analysis of pump-turbine in turbine mode under the same head condition 4

Pressure Fluctuation analysis of pump-turbine in turbine mod...

引用

4th IAHR Asian Working Group Symposium on Hydraulic Machinery and systems

作者： Zhang, Fangfang Li, Na Xiao, Ruofu Tao, Ran College of Water Resources and Civil Engineering China Agricultural University Beijing100083 China Beijing Engineering Research Center of Safety and Energy Saving Technology for Water Supply Network System China Agricultural University Beijing100083 China China Irrigation and Drainage Development Center Beijing100000 China

As the key technical part of pumped-storage power station, the efficient and stable development of pump-turbine units is of great significance for renewable energy power generation. However, pump-turbine units have the characteristics of complex and variable operation conditions. In addition, under different guide vane openings, operation conditions of pump-turbine units also show different flow patterns and pressure fluctuation characteristics. For the sack of studying the pressure fluctuation characteristics of pump-turbine units in turbine mode, a dynamic model of a pump-turbine unit is established in this research. Based on SST k-ω turbulence model, combined numerical simulation and experimental test, pressure fluctuation laws in vaneless region and draft tube under three typical guide vane openings are carried out. The results indicate that, by increasing the guide vane opening, the pressure fluctuation intensity of each monitor point is decreased. Furthermore, the pressure fluctuation at the monitor points in vaneless region between guide vane and the runner presents a periodic change rule, which is mainly due to the two-stage rotor and stator interference between guide vane and runner, and between runner and draft tube. The research further clarifies the pressure fluctuation law in turbine mode, and provides theoretical reference for long-term sustainable development of pump-turbine units. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Turbulence models

来源：评论

学校读者我要写书评

暂无评论

Machine learning for membrane bioreactor research:principles,methods,applications,and a tutorial

引用

Frontiers of Environmental Science & Engineering 2025年第3期19卷 119-144页

作者： Yizhe Lai Kang Xiao Yifan He Xian Liu Jihua Tan Wenchao Xue Aiqian Zhang Xia Huang Beijing Yanshan Earth Critical Zone National Research Station College of Resources and EnvironmentUniversity of Chinese Academy of SciencesBeijing 101408China Key Laboratory of Earth System Numerical Modeling and Application University of Chinese Academy of SciencesBeijing 101408China Environmental Chemistry Faculty College of Resources and EnvironmentUniversity of Chinese Academy of SciencesBeijing 101408China State Key Laboratory of Environmental Chemistry and Ecotoxicology Research Center for Eco-Environmental SciencesChinese Academy of SciencesBeijing 100085China Department of Energy Environmentand Climate ChangeSchool of EnvironmentResourcesand DevelopmentAsian Institute of TechnologyP.O.Box 4Klong LuangPathumthani 12120Thailand State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China

Membrane fouling poses a significant challenge to the sustainable development of membrane bioreactor(MBR)technologies for wastewater *** accurate prediction of the membrane filtration process is of great importance for identifying and controlling *** learning methods address the limitations of traditional statistical approaches,such as low accuracy,poor generalization ability,and slow convergence,particularly in predicting complex filtration and fouling processes within the realm of big *** article provides an in-depth exposition of machine learning *** study then reviews advances in MBRs that utilize machine learning methods,including artificial neural networks(ANN),support vector machines(SVM),decision trees,and ensemble *** on current literature,this study summarizes and compares the model input and output characteristics(including foulant characteristics,solution environments,filtration conditions,operating conditions,and time factors),as well as the selection of models and optimization *** modeling procedures of SVM,random forest(RF),back propagation neural network(BPNN),long short-term memory(LSTM),and genetic algorithm-back propagation(GA-BP)methods are elucidated through a tutorial *** simulation results demonstrated that all five methods yielded accurate predictions with R2>***,the existing challenges in the implementation of machine learning models in MBRs were *** is notable that integration of deep learning,automated machine learning(AutoML)and explainable artificial intelligence(XAI)may facilitate the deployment of models in practical engineering *** insights presented here are expected to facilitate the establishment of an intelligent control framework for MBR processes in future endeavors.

关键词： Membrane bioreactor Machine learning Pollutant removal Membrane fouling Model prediction

来源：评论

学校读者我要写书评

暂无评论

research on HRI Evaluation system and Diver Safety Equipment

Research on HRI Evaluation System and Diver Safety Equipment

引用

OCEANS 2024 - Halifax, OCEANS 2024

作者： Lee, Ye Jun Kim, Min-Gyu Shin, Myung-Jun Park, Tae Sung Kim, Jinhyung Kim, Sunghun Lee, Kichoon Lee, Jihun Min, Jeongtack Research Center Pohang Korea Republic of Pusan National University Hospital Pusan National University School of Medicine Department of Rehabilitation Medicine Busan Korea Republic of Institute of Technology Pusan National University Hospital Department of Convergence Medical Busan Korea Republic of Technical Research Center RNWare Co. Ltd Daegu Korea Republic of Gleam-Systems System Development Division Daejeon Korea Republic of Gleam-Systems Modeling and Simulation Division Daejeon Korea Republic of Marine Leisure Equipment R&d Center Pohang Korea Republic of

ISBN: (纸本)9798331540081

Scuba diving is a common aquatic leisure sport that many individuals enjoy in the sea. With the increasing number of people participating, there is a corresponding rise in related incidents and accidents. Typically, such events are caused by inadequate user proficiency with equipment, sudden onset of physical symptoms, failure to respond to external obstacles, and equipment malfunctions. As interest in scuba diving grows, the development of diver safety equipment that enhances convenience and usability through the interaction between divers and equipment is crucial, not only to assist underwater activities but also to preemptively prevent accidents. This paper explores the analysis of divers' physiological conditions and diver equipment evaluation criteria. Building upon this, it proposes a HRI(Human-Robot Interaction) evaluation system to facilitate the research and development of safety equipment for secure scuba diving operations. © 2024 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Finite element analysis and experimental verification of the mechanical performance of a novel easy-to-splice mechanical coupler

引用

Computers and Concrete 2025年第2期35卷 127-136页

作者： Chung, Sukhwan Jang, Seongmin Seo, Ildong Lee, Nakyoung Chung, Wanjin Joun, Mansoo MFRC Research and Development Center 1209-A 12 Dongbu-ro 169beng-gil Gyeongsangnam-do Jinju-si52818 Korea Republic of Dae Jung Metal Co. Ltd Research and Development Center 26-62 Sangdong-ro 375ben-gil Sngdong-myeon Gyeongsangnam-do Gimhae-si50805 Korea Republic of Department of Mechanical System Design Engineering Seoul National University of Science and Technology 232 Gongneung-ro Nowon-gu Seoul01811 Korea Republic of Engineering Research Institute School of Mechanical Engineering Gyeongsang National University 103-403 501 Jinju-daero Gyeongsangnam-do Jinju-si52828 Korea Republic of

A novel easy-to-splice mechanical coupler (EtSMC) involving a sleeve, two caps, two racks, two rack guides, and two springs is introduced;this coupler easily and tightly connects two rebars through a simple manual operation (without any tool) on a construction site. The mechanical performance (including the pull force/stroke curve of the EtSMC assembly) is experimentally examined via tensile testing in air. A finite element analysis (FEA) model that minimizes simplification of the conceptual design is presented;the spring reaction is assumed to be mechanically symmetrical. The experimental tensile test is numerically analyzed using a fully implicit elastoplastic FEA function and a multi-body treatment scheme based on the tetrahedral MINI-element technique. The predictions are in qualitatively good agreement with the experimental data in terms of both the pull force/stroke curve and the damaged regions of the racks and rack guides. Small differences between the curves can be attributed to some experimental slip between parts. Copyright © 2025 Techno-Press, Ltd.

关键词： Tensile testing

来源：评论

学校读者我要写书评

暂无评论

CW-YOLO: joint learning for mask wearing detection in low-light conditions

引用

Frontiers of Computer Science 2023年第6期17卷 191-193页

作者： Mingqiang GUO Hongting SHENG Zhizheng ZHANG Ying HUANG Xueye CHEN Cunjin WANG Jiaming ZHANG School of Computer Science China University of GeosciencesWuhan 430074China National Engineering Research Center of Geographic Information System Wuhan 430074China Wuhan Zondy Cyber Technology Co.Ltd. Wuhan 430074China Shenzhen Data Management Center of Planning and Natural Resources Shenzhen 518000China Key Laboratory of Urban Land Resources Monitoring and Simulation(Ministry of Natural Resources) Shenzhen 518000China College of Engineering Boston UniversityBoston 02215USA

1 Introduction With the rapid progress of Artificial Intelligence(AI)technology in object detection and face recognition,deep learning methods for face mask wearing detection have become increasingly mature and continuously take into account the needs of efficiency and ***,these conventional detection methods mostly ignore the complexity of real-world application scenarios,such as extremely darkness and gloomy *** unfavorable conditions lead to a series of image degradations that seriously hamper machine vision *** camera parameter adjustment,auxiliary lighting,or pre-processing enhancement[1]can weaken these negative effects to some extent to promote the detection,they will also result in increased hardware and time costs.

关键词： hardware lighting weather

来源：评论

学校读者我要写书评

暂无评论

Variable stiffness design optimization of fiber-reinforced composite laminates with regular and irregular holes considering fiber continuity for additive manufacturing

引用

Chinese Journal of Aeronautics 2025年第3期38卷 334-354页

作者： Yi LIU Zunyi DUAN Chunping ZHOU Yuan SI Chenxi GUAN Yi XIONG Bin XU Jun YAN Jihong ZHU School of Mechanics Civil Engineering&ArchitectureNorthwestern Polytechnical UniversityXi’an 710072China Research&Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen 518063China Key Lab for Airborne Hi-performance Electro-magnetic Window RISACJinan 130012China School of System Design and Intelligent Manufacturing Southern University of Science and TechnologyShenzhen 518055China State Key Laboratory of Structural Analysis for Industrial Equipment Department of Engineering MechanicsInternational Research Center for Computational MechanicsDalian University of TechnologyDalian 116024China State IJR Center of Aerospace Design and Additive Manufacturing MIIT Lab of Metal Additive Manufacturing and Innovative DesignNorthwestern Polytechnical UniversityXi’an 710072China

Fiber-reinforced composites are an ideal material for the lightweight design of aerospace structures. Especially in recent years, with the rapid development of composite additive manufacturing technology, the design optimization of variable stiffness of fiber-reinforced composite laminates has attracted widespread attention from scholars and industry. In these aerospace composite structures, numerous cutout panels and shells serve as access points for maintaining electrical, fuel, and hydraulic systems. The traditional fiber-reinforced composite laminate subtractive drilling manufacturing inevitably faces the problems of interlayer delamination, fiber fracture, and burr of the laminate. Continuous fiber additive manufacturing technology offers the potential for integrated design optimization and manufacturing with high structural performance. Considering the integration of design and manufacturability in continuous fiber additive manufacturing, the paper proposes linear and nonlinear filtering strategies based on the Normal Distribution Fiber Optimization (NDFO) material interpolation scheme to overcome the challenge of discrete fiber optimization results, which are difficult to apply directly to continuous fiber additive manufacturing. With minimizing structural compliance as the objective function, the proposed approach provides a strategy to achieve continuity of discrete fiber paths in the variable stiffness design optimization of composite laminates with regular and irregular holes. In the variable stiffness design optimization model, the number of candidate fiber laying angles in the NDFO material interpolation scheme is considered as design variable. The sensitivity information of structural compliance with respect to the number of candidate fiber laying angles is obtained using the analytical sensitivity analysis method. Based on the proposed variable stiffness design optimization method for complex perforated composite laminates, the numerical examples cons

关键词： Variable stiffness composite laminates Discrete material interpolation scheme Normal distribution fiber optimization Discrete fiber continuous filtering strategy Additive manufacturing of composite laminates

来源：评论

学校读者我要写书评

暂无评论

A Grad-CAM and capsule network hybrid method for remote sensing image scene classification

引用

Frontiers of Earth Science 2024年第3期18卷 538-553页

作者： Zhan HE Chunju ZHANG Shu WANG Jianwei HUANG Xiaoyun ZHENG Weijie JIANG Jiachen BO Yucheng YANG Shenzhen Data Management Center of Planning and Natural Resources Key Laboratory of Urban Land Resources Monitoring and Simulation(Ministry of Natural Resources)Shenzhen 518000China Key Laboratory of Jianghuai Arable Land Resources Protection and Eco-restoration(Ministry of Natural Resources) Hefei 230088China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China School of Civil Engineering Hefei University of TechnologyHefei 230009China

Remote sensing image scene classification and remote sensing technology applications are hot research *** CNN-based models have reached high average accuracy,some classes are still misclassified,such as“freeway,”“spare residential,”and“commercial_area.”These classes contain typical decisive features,spatial-relation features,and mixed decisive and spatial-relation features,which limit high-quality image scene *** address this issue,this paper proposes a Grad-CAM and capsule network hybrid method for image scene *** Grad-CAM and capsule network structures have the potential to recognize decisive features and spatial-relation features,*** using a pre-trained model,hybrid structure,and structure adjustment,the proposed model can recognize both decisive and spatial-relation features.A group of experiments is designed on three popular data sets with increasing classification *** the most advanced experiment,92.67%average accuracy is ***,83%,75%,and 86%accuracies are obtained in the classes of“church,”“palace,”and“commercial_area,”*** research demonstrates that the hybrid structure can effectively improve performance by considering both decisive and spatial-relation ***,Grad-CAM-CapsNet is a promising and powerful structure for image scene classification.

关键词： image scene classification CNN Grad-CAM CapsNet DenseNet

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：