检索结果-内蒙古大学图书馆

DPT‐tracker:Dual pooling transformer for efficient visual tracking

CAAI Transactions on Intelligence Technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

Creating semi-Quanta multi-layer synthetic CNT images using CycleGAN

Creating semi-Quanta multi-layer synthetic CNT images using ...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Safavigerdini, Kaveh Surya, Ramakrishna Reinhard, Andrew Quinlan, Zach Bunyak, Filiz Maschmann, Matthew R. Palaniappan, Kannappan University of Missouri Department of Electrical Engineering and Computer Science ColumbiaMo United States University of Missouri Department of Mechanical and Aerospace Engineering ColumbiaMo United States University of Missouri MU Materials Science and Engineering Institute ColumbiaMo United States

ISBN: (纸本)9798350359527

We address the challenge of creating semi-Quanta images of vertically-oriented carbon nanotubes (CNT). Our previous method, CNTNeXt, successfully predicted the mechanical properties for semi-Scanning Electron Microscopy (SEM) images of CNT forests. However, for Quanta images, a more sophisticated approach is required. We propose a novel pipeline that modifies multi-layer synthetic (MLS) CNT images, which are synthetic representations of CNT structures, to resemble Quanta images. This is achieved using CycleGAN, a deep learning model designed for image-To-image translation tasks, which can learn mappings between two different domains without paired training data. By training the CycleGAN on both Quanta and MLS images, we are able to transfer the texture of Quanta images to the MLS images. The resulting 'semi-Quanta' images are ready to train CNTNeXt, which effectively predicts the mechanical properties, including buckling load and stiffness of synthetic MLS images. Our method represents an advancement towards our ultimate goal of creating an automated CNT growth process, and opens up possibilities for further improvements and applications. © 2023 IEEE.

关键词： Carbon nanotubes

来源：评论

学校读者我要写书评

暂无评论

Two-Phase Immersion Cooler for Medium-Voltage Silicon Carbide MOSFETs 23

Two-Phase Immersion Cooler for Medium-Voltage Silicon Carbid...

引用

23rd IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2024

作者： Pandey, Hari Du, Xinyuan Weems, Ethan Pierson, Stephen Al-Hmoud, Ahmad Zhao, Yue Hu, Han University of Arkansas Department of Mechanical Engineering FayettevilleAR72701 United States University of Arkansas Department of Electrical Engineering and Computer Science FayettevilleAR72701 United States

ISBN: (纸本)9798350364330

Medium-voltage (MV) silicon carbide (SiC) MOSFETs play a pivotal role in various industrial applications, including electrical vehicles, DC fast charging stations, and renewable energy conversion systems, among others. Compared to their silicon counterparts, the MV SiC MOSFETs feature higher efficiency, faster switching speeds, lower heat generation, and higher power density. Despite their advantages, SiC MOSFETs also lead to higher cooling demands. To address this challenge, we have developed a two-phase immersion cooler, in which the base plate is immersed in the liquid pool, and vapor generated from coolant boiling on the base plate is condensed on the top surface of the immersion cooler under external air cooling. To further improve the cooling capacity, the base plates are textured with microchannels. Experimental tests have been performed to characterize the thermal performance of the two-phase immersion cooler with a state-of-the-art 6.5kV SiC device. The immersion cooler with microchannels exhibits decreasing thermal resistance with the power load and is shown to be superior to conventional air-cooled heat sinks when the power loads are beyond 70 W. Leveraging the feature of reduced thermal resistance with the power load, the fan power can be tuned based on the power load to increase the lifetime of the fans. © 2024 IEEE.

关键词： Fast charging (Batteries)

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Impacts of Reserve Requirements on Marginal Emission Rate

Analysis of the Impacts of Reserve Requirements on Marginal ...

引用

2024 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2024

作者： Arif, Md Arifin Wang, Fengyu Shi, Di Sun, Liang Wang, Zongjie New Mexico State University Department of Electrical and Computer Engineering Las CrucesNM88003 United States New Mexico State University Department of Mechanical and Aerospace Engineering Las CrucesNM88003 United States University of Connecticut Department of Electrical and Computer Engineering StorrsCT06269 United States

ISBN: (纸本)9798350313604

Modern Electric Power Sector is adopting policies for transitioning towards zero emission. The implementation of the policies for developing a smooth and efficient transition approach strongly relies on effective metrics to quantify emissions in a power system. Marginal Emission Rate (MER) is an important metric to encapsulate the change in emission in response to changes in demand. This paper proposes a computationally efficient MER calculation algorithm to analyze the impacts of reserve requirements on MER. The proposed algorithm uses a computationally efficient model to calculate the changes in the outputs of marginal generators in response to infinitesimal changes in demand. A systematic method is proposed to identify the marginal units with the presence of reserve requirements constraints. The MER can be calculated by multiplying the changes in outputs with corresponding emission rates. Numerical results on a small 3-Bus test system have been demonstrated to explain and validate the accuracy of the proposed method. © 2024 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Deep Style Transfer for Generation of Photo-realistic Synthetic Images of CNT Forests

Deep Style Transfer for Generation of Photo-realistic Synthe...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Kotha, Prashanth Reddy Attari, Minasadat Maschmann, Matthew Bunyak, Filiz University of Missouri Department of Electrical Engineering and Computer Science ColumbiaMO United States University of Missouri Department of Mechanical and Aerospace Engineering ColumbiaMO United States University of Missouri MU Materials Science and Engineering Institute ColumbiaMO United States

ISBN: (纸本)9798350359527

Carbon nanotubes (CNTs) are promising nano-materials with diverse applications in various fields, ranging from electronics and energy storage to biomedical applications. Characterization of CNT forest structures and prediction of material properties through image analytics are critical for new material design and discovery. Artificial intelligence and machine learning (AI/ML) driven approaches offer promising solutions towards these goals. These data-driven approaches rely on large amounts of annotated data for robust training. However, growing, imaging, and annotation of CNT forests are complex, time consuming, expensive processes limiting availability of such data. In this paper, we propose a novel neural style transfer pipeline to generate photo-realistic and structure-Aware synthetic images of CNT forests by imposing scanning electron microscopy (SEM) like appearance to physics-based simulation results. The proposed pipeline relies on a novel wavelet-based style transfer network and a selective decision fusion mechanism that allows better preservation of the thin curvilinear structures of CNTs, particularly their intricate details and connectivity, without introducing unwanted artifacts. Experimental results and quantitative analysis demonstrate refined style transfer that generates photo-realistic images that can be used to train AI/ML-driven CNT forest image analysis systems. © 2023 IEEE.

关键词： Carbon nanotubes

来源：评论

学校读者我要写书评

暂无评论

Validation of High Angular Resolution Diffusion-Weighted Imaging Protocols 15

Validation of High Angular Resolution Diffusion-Weighted Ima...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Seth, Jyoti Savitha, R. Kumar, Ashwini Vivekananda Global University Department of Computer Science & Engineering Jaipur India School of Engineering and Technology Department of Electrical and Electronics Engineering Karnataka Bangalore India Arka Jain University Department of Mechanical Engineering Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

High angular resolution diffusion-weighted imaging (HARDI) protocols are strategies used to growth the number of facts amassed about tissue microstructure in diffusion imaging. Current studies have sought to apprehend the validity of HARDI methods and their ability to reconstruct the underlying tissue systems accurately. The evaluation of HARDI reliability is accomplished thru 3 major classes: voxel-wise checks of methods, simulations to evaluate protocol efficiency, and human brain tract reconstruction. outcomes from these studies have tested that HARDI may additionally offer progressed visualization of mind microstructure and might higher differentiate between individual white count tracts and distinctive tissue kinds than conventional diffusion imaging. However, due to the complexity of HARDI protocols, further validation is essential to ensure accuracy and discover the strengths and weaknesses of the strategies. © 2024 IEEE.

关键词： Accomplished Accuracy Distinctive Essential Microstructure Protocols Strategies Validation

来源：评论

学校读者我要写书评

暂无评论

Nash Equilibrium Seeking for Noncooperative Duopoly Games via Event-Triggered Control 63

Nash Equilibrium Seeking for Noncooperative Duopoly Games vi...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Rodrigues, Victor Hugo Pereira Oliveira, Tiago Roux Krstic, Miroslav Basar, Tamer Dept of Eletronics and Telecommunication Engineering RJ Rio de Janeiro Brazil Dept of Mechanical and Aerospace Engineering La Jolla CA United States University of Illinois Urbana-Champaign Dept of Electrical and Computer Engineering UrbanaIL United States

ISBN: (纸本)9798350316339

This paper proposes a novel approach for locally stable convergence to Nash equilibrium in duopoly noncooperative games based on a distributed event-triggered control scheme. The proposed approach employs extremum seeking, with sinusoidal perturbation signals applied to estimate the gradient (first derivative) of unknown quadratic payoff functions. This is the first instance of noncooperative games being tackled in a model-free fashion integrated with the event-triggered methodology. Each player evaluates independently the deviation between the corresponding current state variable and its last broadcasted value to update the player action, while they preserve control performance under limited bandwidth of the actuation paths and still guarantee stability for the closed-loop dynamics. In particular, the stability analysis is carried out using time-scaling technique, Lyapunov's direct method and averaging theory for discontinuous systems. We quantify the size of the ultimate small residual sets around the Nash equilibrium and illustrate the theoretical results numerically on an example. © 2024 IEEE.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Investigation of Effective Electrode Structure for Metal Removal from Composite Materials Using Pulsed Discharge 10

Investigation of Effective Electrode Structure for Metal Rem...

引用

10th Euro-Asian Pulsed Power Conference, 25th International Conference on High-Power Particle Beams and 20th International Symposium on Electromagnetic Launch Technology, EAPPC-BEAMS-EML 2024

作者： Doi, Takuto Oishi, Shota Sakugawa, Takashi Nishimura, Kaisei Shobako, Shinichiro Shimasaki, Shinichi Yamashita, Tomohiko Kumamoto University Graduate School of Science and Technology Department of Computer Science and Electrical Engineering Kumamoto Japan Kagawa College National Institute of Technology Department of Electro-Mechanical Systems Engineering Takamatsu Japan

ISBN: (纸本)9789038661353

The authors investigate the potential of pulsed power technology in recycling of E-waste. Applying the pulsed discharge can separate composite materials into plastic and metal. In this study, pulsed discharge was applied to indium tin oxide (ITO) coated plastic films. We used two electrode types: rod-To-rod electrode and a pair of flat plate electrodes to investigate the effect of electrode structure on the metal removal area in detail. A series of single pulse discharges were applied at various electrode distances. As a result, it was revealed that metal can be removed over a wide range by the pulsed discharge using a pair of flat plate electrodes. When the gap between the electrodes was 30 mm, the removal area by the flat plate electrodes was approximately 3.4 times that by the rod electrodes. Analysis of the current density also revealed that the metal removal area was greatly affected by the current density. © 2024 Eindhoven University of Technology.

关键词： Tin oxides

来源：评论

学校读者我要写书评

暂无评论

A PV-Powered Microcontroller-Based Agricultural Robot Utilizing GSM Technology for Crop Harvesting and Plant Watering

A PV-Powered Microcontroller-Based Agricultural Robot Utiliz...

引用

2023 IEEE International Students' Conference on electrical, Electronics and computer science, SCEECS 2023

作者： Nuhel, Ahsan Kabir Sazid, Mir Mohibullah Paul, Dipta Hasan, Ekramul Roy, Priyadarshini Hriddhi Sinojiya, Fenish Prafulbhai Electrical and Electronics Engineering Bangladesh Vellore Institute of Technology Computer Science and Engineering Vellore India Vellore Institute of Technology Department of Mechanical Engineering Vellore India

ISBN: (纸本)9798350398748

A solar-powered, intelligent grass cutter and pesticide application system that uses microcontrollers, sonar sensors, solar panels, and GSM technology is being proposed as a solution to the issue of high labor costs in the agricultural sector of Bangladesh. This is done in order to achieve exquisite cost management. The initial objective is to design a system that, through utilizing a robot controlled by a micro controller, will make the laborious work of our farmers and entrepreneurs more feasible. This machine can trim the grass, apply pesticides, and simultaneously provide the plant with water. Solar panels are used to extract power from the sun to charge the device. At long last, GSM technology has been integrated, turning this device into one that can be remotely controlled using a straightforward SMS protocol. © 2023 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Fault Diagnosis Method Based on Transformer and CNN 7

A Hybrid Fault Diagnosis Method Based on Transformer and CNN

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Gao, Zhi He, Meixuan Zhang, Bangcheng Shao, Yubo Liu, Jingru Que, Shaohua Changchun University of Technology School of Mechatronic Engineering Changchun China Changchun University of Technology College of Computer Science and Engineering Changchun China Changchun University of Technology Faculty of Mechanical and Electrical Engineering Faculty of Mechanical and Electrical Engineering Changchun Institute of Technology Changchun China Faw Tooling Die Manufacturing Changchun China

ISBN: (纸本)9798350363173

The elevator data of the welding production line has significant timing characteristics. There are more normal data and less abnormal data. Therefore, it becomes more complicated to diagnose the abnormality of the welding production line hoisting system through data analysis. This paper proposes a hybrid fault diagnosis method that combines a Transformer with a convolutional neural network. Firstly, the Transformer is used to extract the long-range dependencies in the data and identify complex faults that may not be adjacent. Then, the convolutional neural network extracted local or spatial features from the data. Finally, the multilayer perceptron maps the extracted features to the output space. The model innovatively merges the Transformer's global context analysis with the convolutional neural network's local feature detection precision, boosting fault diagnosis accuracy and efficiency. The proposed hybrid model was applied to the actual vibration data set of the hoists condition monitoring system of the white welding production line, and the results were contrasted with those of the support vector machine method, the long short-term memory network method, and the back propagation neural network method. Experimental findings demonstrate that the hybrid model achieves an accuracy of 99.98%, which is suitable for the fault diagnosis of the driving end bearing of the body of the white welding production line. © 2024 IEEE.

关键词： Failure analysis

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：