检索结果-内蒙古大学图书馆

Convolution-Transformer for Image Feature Extraction

computer Modeling in engineering & Sciences 2024年第10期141卷 87-106页

作者： Lirong Yin Lei Wang Siyu Lu Ruiyang Wang Youshuai Yang Bo Yang Shan Liu Ahmed AlSanad Salman A.AlQahtani Zhengtong Yin Xiaolu Li Xiaobing Chen Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia College of Resources and Environmental Engineering Key Laboratory of Karst Georesources and Environment(Guizhou University)Ministry of EducationGuiyang550025China School of Geographical Sciences Southwest UniversityChongqing400715China School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA70803USA

This study addresses the limitations of Transformer models in image feature extraction,particularly their lack of inductive bias for visual *** to Convolutional Neural Networks(CNNs),the Transformers are more sensitive to different hyperparameters of optimizers,which leads to a lack of stability and slow *** tackle these challenges,we propose the Convolution-based Efficient Transformer Image Feature Extraction Network(CEFormer)as an enhancement of the Transformer *** model incorporates E-Attention,depthwise separable convolution,and dilated convolution to introduce crucial inductive biases,such as translation invariance,locality,and scale invariance,into the Transformer ***,we implement a lightweight convolution module to process the input images,resulting in faster convergence and improved *** results in an efficient convolution combined Transformer image feature extraction *** results on the ImageNet1k Top-1 dataset demonstrate that the proposed network achieves better accuracy while maintaining high computational *** achieves up to 85.0%accuracy across various model sizes on image classification,outperforming various baseline *** integrated into the Mask Region-ConvolutionalNeuralNetwork(R-CNN)framework as a backbone network,CEFormer outperforms other models and achieves the highest mean Average Precision(mAP)*** research presents a significant advancement in Transformer-based image feature extraction,balancing performance and computational efficiency.

关键词： Transformer E-Attention depth convolution dilated convolution CEFormer

来源：评论

学校读者我要写书评

暂无评论

Dual Mode pMUT for Structural Health Monitoring of Piping Systems in Advanced Reactors

Dual Mode pMUT for Structural Health Monitoring of Piping Sy...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Khan, Talha Masood Sabino, John Xu, Chenxi Obregon, Javier Adkins, Joshua Wilis Daly, Matthew Heifetz, Alexander Kultgen, Derek Wiliam Ozevin, Didem University of Illinois Chicago Department of Civil Materials and Environmental Engineering ChicagoIL United States University of Illinois Chicago Department of Electrical and Computer Engineering ChicagoIL United States Argonne National Laboratory Nuclear Science and Engineering Division LemontIL United States

ISBN: (纸本)9798350346459

The objective of this work is to develop a durable MEMS sensor for in situ monitoring of advanced reactor piping. Existing sensors for structural health monitoring (SHM) in nuclear reactor environments have limited temperature ranges and service lifetimes, owing to material constraints. Micromachined transducers using aluminum nitride (AlN) as a sensing element, and silicon carbide (SiC) as a substrate, have the potential to address this challenge. In this work, piezoelectric Micromachined Ultrasonic Transducers (pMUT) capable of delivering passive (acoustic emission) and active (guided wave) ultrasonic sensing for SHM in a high-temperature environment are studied. These sensors will be able to couple directly to the structures for real-time SHM of advanced reactor piping systems. A customized microfabrication process is used to produce dual-mode sensing operation at a small footprint of 5×5 mm2. This process involves sputtering a 1 μm thick AlN sandwiched between metal and handle layer. The frequency modes of the pMUT device are tuned to 140 kHz by varying the lateral dimensions of the sensor. Sensor locations on piping are determined by generating plane waves using finite element simulations and studying the wave dispersion. With higher sensitivity, our pMUT sensors are capable of detecting the smallest defect energy at high temperatures, while decreasing the number of sensors on piping. © 2023 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Quantitative Estimation of Pipeline Slope Disaster Risk in China

引用

International Journal of Disaster Risk Science 2023年第2期14卷 298-312页

作者： Yan Yan Jiaojiao Zhou Cheng Xie Shuyao Yin Sheng Hu Renchao Wang Key Laboratory of High-Speed Railway Engineering Ministry of Education/School of Civil EngineeringSouthwest Jiaotong UniversityChengdu610031China Institute of Geographic Sciences and Natural Resources Research Chinese Academy of SciencesBeijing100101China Pipe China South Branch Guangzhou510623China Shaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity Northwest UniversityXi’an 710127China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China

China’s economic development is closely related to oil and gas resources,and the country is investing heavily in pipeline *** geological hazards seriously affect the long-term safe operation of buried pipelines,usually causing pipeline leakage,property and environmental losses,and adverse social *** ensure the safety of pipelines and reduce the probability of pipeline disasters,it is necessary to predict and quantitatively evaluate slope *** there has been much research focus in recent years on the evaluation of pipeline slope disasters and the stress calculation of pipelines under hazards,existing methods only provide information on the occurrence probability of slope events,not whether a slope disaster will lead to pipeline *** the 2015 Xinzhan landslide in Guizhou Province,China,as an example,this study used discrete elements to simulate landslide events and determine the risk level and scope for pipeline damage,and then established a pipe-soil coupling model to quantitatively evaluate the impact of landslide hazards for pipelines in medium-and high-risk *** results provide a reference for future pipeline disaster prevention and control.

关键词： China Coupled pipe-soil model Landslides Pipeline slope disasters Pipe stress Risk classification

来源：评论

学校读者我要写书评

暂无评论

Virtual MOLLI Target: Generative Adversarial Networks Toward Improved Motion Correction in MRI Myocardial T1 Mapping

引用

Journal of Magnetic Resonance Imaging 2025年第1期61卷 209-219页

作者： Pan, Nai-Yu Huang, Teng-Yi Yu, Jui-Jung Peng, Hsu-Hsia Chuang, Tzu-Chao Lin, Yi-Ru Chung, Hsiao-Wen Wu, Ming-Ting Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Biomedical Engineering and Environmental Sciences National Tsing Hua University Hsinchu Taiwan Department of Electrical Engineering National Sun Yat-Sen University Kaohsiung Taiwan Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan Department of Radiology Kaohsiung Veterans General Hospital Kaohsiung Taiwan School of Medicine College of Medicine National Yang Ming Chiao Tung University Taipei Taiwan

Background: The modified Look-Locker inversion recovery (MOLLI) sequence is commonly used for myocardial T1 mapping. However, it acquires images with different inversion times, which causes difficulty in motion correction for respiratory-induced misregistration to a given target image. Hypothesis: Using a generative adversarial network (GAN) to produce virtual MOLLI images with consistent heart positions can reduce respiratory-induced misregistration of MOLLI datasets. Study Type: Retrospective. Population: 1071 MOLLI datasets from 392 human participants. Field Strength/Sequence: Modified Look-Locker inversion recovery sequence at 3 T. Assessment: A GAN model with a single inversion time image as input was trained to generate virtual MOLLI target (VMT) images at different inversion times which were subsequently used in an image registration algorithm. Four VMT models were investigated and the best performing model compared with the standard vendor-provided motion correction (MOCO) technique. Statistical Tests: The effectiveness of the motion correction technique was assessed using the fitting quality index (FQI), mutual information (MI), and Dice coefficients of motion-corrected images, plus subjective quality evaluation of T1 maps by three independent readers using Likert score. Wilcoxon signed-rank test with Bonferroni correction for multiple comparison. Significance levels were defined as P < 0.01 for highly significant differences and P < 0.05 for significant differences. Results: The best performing VMT model with iterative registration demonstrated significantly better performance (FQI 0.88 ± 0.03, MI 1.78 ± 0.20, Dice 0.84 ± 0.23, quality score 2.26 ± 0.95) compared to other approaches, including the vendor-provided MOCO method (FQI 0.86 ± 0.04, MI 1.69 ± 0.25, Dice 0.80 ± 0.27, quality score 2.16 ± 1.01). Data Conclusion: Our GAN model generating VMT images improved motion correction, which may assist reliable T1 mapping in the presence of respiratory motion

关键词： generative adversarial networks MOLLI registration

来源：评论

学校读者我要写书评

暂无评论

Computational Fluid Dynamic Analysis at Dam Spillway Due to Different Upstream Water Levels

Computational Fluid Dynamic Analysis at Dam Spillway Due to ...

引用

AWAM International Conference on Civil engineering, AICCE 2022

作者： Hassan, N.H. Kamarulbahrin, S.Z.A.S. Zawawi, M.H. Mazlan, A.Z.A. Abas, M.A. Zainol, M.R.R.M.A. Kamaruddin, M.A. Department of Civil Engineering College of Engineering Universiti Tenaga Nasional Selangor Kajang43000 Malaysia Department of Electrical and Electronic Engineering College of Engineering Universiti Tenaga Nasional Selangor Kajang43000 Malaysia School of Mechanical Engineering Universiti Sains Malaysia Penang Nibong Tebal14300 Malaysia School of Civil Engineering Universiti Sains Malaysia Penang Nibong Tebal14300 Malaysia Environmental Technology Division School of Industrial Technology Universiti Sains Malaysia Penang George Town11800 Malaysia

ISBN: (纸本)9789819960255

This paper analyses the fluid dynamic on the dam spillway structure when the water spilling event occurred. The parameters determined in this study are velocity and pressure. A 3D Computational Fluid Dynamics (CFD) model of the dam spillway structure and the fluid boundary condition was developed using FLUENT. The result of the CFD model shows that hydrostatic pressure for all water levels was observed at the upstream section. The highest velocity and pressure occur at the highest water level which are 3.2 m/s and 1.526 MPa, respectively, at the spillway wall. High water velocity may contribute to critical stress due to the high pressure. All of the cases from 146 to 153 m water level show the fluid flows which are at reasonable velocity and pressure at the spillway. However, the continuous interaction with water towards the granite may affect the scouring effect of the granite in the long-term run. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Optimal Pricing Model for Electric Vehicle Charging Stations Considering Competition

Optimal Pricing Model for Electric Vehicle Charging Stations...

引用

International Conference on Renewable Energy and Power engineering (REPE)

作者： A K M Yousuf Zhanle Wang Raman Paranjape Yili Tang Electronic Systems Engineering University of Regina Regina SK Canada Civil and Environmental Engineering & Electrical and Computer Engineering University of Western Ontario London Ontario Canada

ISBN: (数字)9798350375558

ISBN: (纸本)9798350375565

In today's world, technology is booming, and people are more aware of how their actions affect the environment. One big change we are seeing is the rise of electric vehicles (EVs). The surge in EV adoption necessitates efficient and fast EV charging stations, but challenges such as extended charging times, limited facilities, and their impact on power systems must be addressed. This paper proposes an optimized pricing model, considering the integrated operation of the transportation network and the power distribution system. This model accounts for both competitive and non-competitive charging demand. The proposed model can effectively reduce peak demand, ensure power system stability, increase EV charging station profit and decrease EV users' waiting time for charging.

关键词： Space vehicles Renewable energy sources Transportation Pricing Power system stability Electric vehicle charging Stability analysis Surges Space stations Load modeling

来源：评论

学校读者我要写书评

暂无评论

Graphene Bridge Heterostructure Devices for Negative Differential Transconductance Circuit Applications

引用

Nano-Micro Letters 2023年第2期15卷 161-171页

作者： Minjong Lee Tae Wook Kim Chang Yong Park Kimoon Lee Takashi Taniguchi Kenji Watanabe Min‑gu Kim Do Kyung Hwang Young Tack Lee Department of Electrical and Computer Engineering Inha UniversityIncheon 22212Republic of Korea Department of Materials Science and Engineering The University of Texas at DallasRichardsonTX 75080USA Center for Opto‑Electronic Materials and Devices Post‑Silicon Semiconductor InstituteKorea Institute of Science and Technology(KIST)Seoul 02792Republic of Korea Department of Physics Kunsan National UniversityGunsan 54150Republic of Korea Advanced Materials Laboratory National Institute for Materials ScienceTsukuba 305‑0044Japan Department of Information and Communication Engineering Inha UniversityIncheon 22212Republic of Korea Division of Nanoscience and Technology KIST SchoolUniversity of Science and Technology(UST)Seoul 02792Republic of Korea Department of Electronic Engineering Inha UniversityIncheon 22212Republic of Korea

Two-dimensional van der Waals(2D vdW)material-based heterostructure devices have been widely studied for high-end electronic applications owing to their heterojunction *** this study,we demonstrate graphene(Gr)-bridge heterostructure devices consisting of laterally series-connected ambipolar semiconductor/Gr-bridge/n-type molybdenum disulfide as a channel material for field-effect transistors(FET).Unlike conventional FET operation,our Gr-bridge devices exhibit nonclassical transfer characteristics(humped transfer curve),thus possessing a negative differential *** phenomena are interpreted as the operating behavior in two series-connected FETs,and they result from the gate-tunable contact capacity of the Gr-bridge ***-value logic inverters and frequency tripler circuits are successfully demonstrated using ambipolar semiconductors with narrow-and wide-bandgap materials as more advanced circuit applications based on non-classical transfer ***,we believe that our innovative and straightforward device structure engineering will be a promising technique for future multi-functional circuit applications of 2D nanoelectronics.

关键词： Graphene bridge Heterostructure device Non-classical transfer characteristics Multi-value logic inverter Frequency tripler

来源：评论

学校读者我要写书评

暂无评论

Model-Plant Mismatch Detection Using the Plant-Model Ratio: The Influence of Multivariable Systems Containing Both Fast and Slow Dynamics.

引用

IFAC-PapersOnLine 2024年第25期58卷 55-60页

作者： Heinz K. Mittermaier Johan D. le Roux Ian K. Craig Measurement and Control Division Mintek Randburg South Africa Department of Electrical Electronic and Computer Engineering University of Pretoria Pretoria South Africa

The plant-model ratio, developed to diagnose model-plant mismatch present in model-based controllers, inherits the same limitations from the frequency-based analysis that the method is based on. Nonetheless, the plant-model ratio shows the capacity to counteract the effect of non-linear dynamics within processes due to the ability to diagnose parametric model-plant mismatches for first-order plus time delay models. The plant-model ratio is developed before being validated on the Wood-Berry distillation column. One of the prominent limitations of frequency analysis, the filtering effects of time constant differences, is investigated and quantified for the Wood-Berry distillation column, showing the effect of time constant differences on each parametric model-plant mismatch diagnosis.

关键词： controller performance monitoring grinding mill circuit model predictive control model-plant mismatch process performance monitoring

来源：评论

学校读者我要写书评

暂无评论

An Energy Harvester Using Rolling Magnets with Integrated Rotor and Stator for Wireless Sensor System on a Marine Shaft

An Energy Harvester Using Rolling Magnets with Integrated Ro...

引用

2023 IEEE International Symposium on Antennas and Propagation, ISAP 2023

作者： Hoang, Van Ai Kim, Yang Gon Lee, Young Chul Department of Marine Electronic Communication and Computer Engineering Mokpo National Maritime University Mokpo Korea Republic of Division of Marine Mechatroincs Mokpo National Maritime University Mokpo Korea Republic of

ISBN: (纸本)9798350341140

In this paper, we introduce a novel energy harvester (EH) using rolling magnets, which can supply power to a wireless sensor system (WSS) for monitoring the status of rotating ship shafts. The EH consists of twelve coils and seven magnets, which generate energy from the shaft's motion and supply it to the WSS for monitoring the shaft system's status. We installed the EH on a 20 cm diameter shaft and obtained a transferred voltage of 0.84 V and an output power of 47.2 mW with 2000 turns of each coil, despite a rotation speed of 25 rpm and a 3 mm air gap. The proposed EH shows great potential for monitoring rotating shaft on ships. © 2023 IEEE.

关键词： battery-free energy harvester marine propulsion shaft rolling magnets wireless sensor system

来源：评论

学校读者我要写书评

暂无评论

980 nm micro-cavity lasers with sub-milliampere threshold

980 nm micro-cavity lasers with sub-milliampere threshold

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Lin, Qi Xue, Ying Huang, Jie Gu, Wen Lau, Kei May Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong Division of Emerging Interdisciplinary Area Hong Kong University of Science and Technology Clear Water Bay Hong Kong

We report electrically-pumped InGaAs/GaAs/GaAsP quantum well micro-cavity lasers on GaAs with low thresholds down to the sub-milliamp level and a maximum operating temperature of 95°C. Micro-lasers with various c... 详细信息

ISBN: (纸本)9781957171395

关键词： Semiconductor quantum wells

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：