检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yoo, Seungryong Kim, Eunji Jung, Dahuin Lee, Jungbeom Yoon, Sungroh Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as prompts, which steer the frozen pretrained ViTs. Although VPT has demonstrated its applicability with supervised vision transformers, it often underperforms with self-supervised ones. Through empirical observations, we deduce that the effectiveness of VPT hinges largely on the ViT blocks with which the prompt tokens interact. Specifically, VPT shows improved performance on image classification tasks for MAE and MoCo v3 when the prompt tokens are inserted into later blocks rather than the first block. These observations suggest that there exists an optimal location of blocks for the insertion of prompt tokens. Unfortunately, identifying the optimal blocks for prompts within each self-supervised ViT for diverse future scenarios is a costly process. To mitigate this problem, we propose a simple yet effective method that learns a gate for each ViT block to adjust its intervention into the prompt tokens. With our method, prompt tokens are selectively influenced by blocks that require steering for task adaptation. Our method outperforms VPT variants in FGVC and VTAB image classification and ADE20K semantic segmentation. The code is available at https://***/ryongithub/GatedPromptTuning. © 2023, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Periodic phase diagrams in micromagnetics with an eigenvalue solver

引用

IEEE Transactions on Magnetics 2025年

作者： Ai, Fangzhou Lin, Zhuonan Duan, Jiawei Lomakin, Vitaliy University of California Department of Electrical and Computer Engineering San DiegoCA92093 United States University of California Center for Memory and Recording Research San DiegoCA92093 United States University of California Program in Materials Science and Engineering San Diego92093 United States

This work introduces an approach to compute periodic phase diagram of micromagnetic systems by solving a periodic linearized Landau-Lifshitz-Gilbert (LLG) equation using an eigenvalue solver with the Finite Element Method formalism. The linear operator in the eigenvalue problem is defined as a function of the periodic phase-shift wave vector. The dispersion diagrams are obtained by solving the eigenvalue problem for complex eigenfrequencies and corresponding eigenstates for a range of prescribed wave vectors. The presented approach incorporates a calculation of the periodic effective field, including the exchange and magnetostatic field components. The approach is general in that it allows 3D problems to be handled with any 1D, 2D, and 3D periodicities. The ability to calculate periodic diagrams provides insights into the spin wave propagation and localized resonances in complex micromagnetic structures. © 1965-2012 IEEE.

关键词： Spin waves

来源：评论

学校读者我要写书评

暂无评论

Low Power Consumption of Non-Volatile Memory Device by Tunneling Process engineering

SSRN

引用

SSRN 2024年

作者： Wang, Fucheng Chu, Mengmeng Chen, Jingwen Pan, Zhong Kim, Yongsang Song, Jang Kun Yi, Junsin Khokhar, Muhammad Quddamah Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Interdisciplinary Program in Photovoltaic System Engineering Sungkyunkwan University Suwon16419 Korea Republic of College of Information and Communication Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Compared with Si3N4 and Al2O3, SiO2 grown using thermal oxidation process as tunneling layer has the advantages of high bandgap and well interface contact with the surface of silicon wafer, which can be a great solution to the leakage current problem of metal-insulator-semiconductor (MIS) devices. This study investigates the effect of improving the SiO2 tunnel layer on the operating voltage of MIS devices with a SiO2/HfAlOx/Al2O3 structure. The result shows the operating voltage changes as the tunneling layer thickness decreases, with a minimum of only 12 V for a 1.5 nm tunneling layer thickness. In addition, we found that pinholes are generated on the film surface when annealing a 1.5 nm SiO2 tunnel layer at 850 °C N2, in which case the operating voltage of the device is reduced to only 10 V, though it was also accompanied by the deterioration of the retention characteristics. © 2024, The Authors. All rights reserved.

关键词： Silicon wafers

来源：评论

学校读者我要写书评

暂无评论

An Open-Source GPU-Based Acoustic Simulator for Fast and Accurate Modeling of Acoustic Scattering

An Open-Source GPU-Based Acoustic Simulator for Fast and Acc...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Zixuan Tian Yun Jing Aiguo Han Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Urbana USA Graduate Program in Acoustics Pennsylvania State University USA Department of Biomedical Engineering and Mechanics Virginia Polytechnic Institute and State University Blacksburg USA

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Fast, accurate, and realistic simulations of ultrasonic scattering in biological tissues play an important role in biomedical ultrasound research. This study introduces UltraWave, a new open-source ultrasound simulation tool we developed for accurately modeling acoustic and elastic wave propagation in two- and three-dimensional heterogeneous media. UltraWave allows the utilization of multiple graphics processing units (GPUs) to deliver faster and more accurate full-wave simulations. The perfectly matched layer was integrated into the simulator. UltraWave was validated against well-established scattering theories in a variety of basic scattering scenarios, and achieved similar or higher accuracy than the widely used k-Wave toolbox. Additionally, UltraWave outperformed k-Wave in terms of computational efficiency with both central processing units (CPUs) and GPUs, particularly when using GPU acceleration for elastic wave simulations. These results demonstrated the potential of UltraWave as a promising tool for biomedical ultrasound simulations.

关键词： Solid modeling Accuracy Ultrasonic imaging Biological system modeling Computational modeling Graphics processing units Media Acoustics Computational efficiency Perfectly matched layers

来源：评论

学校读者我要写书评

暂无评论

Automated classification of renal tumors on ultrasound images using deep neural network

Automated classification of renal tumors on ultrasound image...

引用

International Symposium on Environmentally Conscious Design and Inverse Manufacturing (EcoDesign)

作者： Wei-Chieh Wu Te-Mei Chiang Zhi-Ren Tsai Program in Artificial Intelligence College of Information and Electrical Engineering Asia University Taichung City Taiwan Department of Radiation Oncology Asia University Hospital Taichung City Taiwan Department of Computer Science & Information Engineering Asia University

ISBN: (数字)9798350363043

ISBN: (纸本)9798350363050

Kidney cancer is one of the most common cancers worldwide. The major types of malignant renal tumors are renal cell carcinoma and urothelial carcinoma. Although the majority of renal tumors are malignant, up to $20\%$ are benign, most commonly renal cyst and angiomyolipomas. Ultrasound is the most accessible imaging tool in medical practice, but it highly depends on operator skill, which may lead to high false-negative rate in diagnosis. The purpose of this study was to develop a predictive model for the automated classification of renal tumors on ultrasound images using deep neural network. A total of 880 kidney ultrasound images were used for training and testing. Transfer learning was used to the ten Convolution neural network models. The kidney ultrasound images were classified as benign or malignant tumors. The classification performance of the model was evaluated by sensitivity and specificity. The research results show that VGG18 yielded the best performance, with a sensitivity of $79 \%$, and a specificity of $86 \%$.

关键词： Training Ultrasonic imaging Sensitivity Convolution Transfer learning Artificial neural networks Sensitivity and specificity Kidney Cancer Testing

来源：评论

学校读者我要写书评

暂无评论

Dynamic Interval-Valued PCA for Enhanced Fault Detection

Dynamic Interval-Valued PCA for Enhanced Fault Detection

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Lahcene Rouani Mohamed Faouzi Harkat Abdelmalek Kouadri Abderazak Bensmail Majdi Mansouri Mohamed Nounou Signals and Systems Laboratory Institute of Electrical and Electronics Engineering University M’Hamed Bougara of Boumerdes Boumerdes Algeria Systems and Advanced Material Laboratory Badji Mokhtar - Annaba University Annaba Algeria Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

This study introduces three novel dynamic interval-valued principal component analysis (DIPCA) methods: dynamic centers PCA (D-CPCA), dynamic vertices PCA (D-VPCA), and dynamic complete information PCA (D-CIPCA). These methods advance traditional interval-valued PCA (IPCA) by integrating dynamic aspects of industrial processes, thus addressing both data uncertainties and temporal correlations. The DIPCA methods were validated using real-world data from the Ain El Kebira cement plant. Results indicate significant improvements in fault detection accuracy, achieving lower false alarm rates and higher reliability compared to classical IPCA methods. Furthermore, an enhanced combined index for interval-valued data was developed, providing a single, comprehensive statistical measure for streamlined process monitoring.

关键词： Process monitoring Uncertainty Accuracy Fault detection Cement industry Aerodynamics Robustness Real-time systems Indexes Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Partial Discharge Investigation of Defective Cable Terminations using Different Voltage Sources

Partial Discharge Investigation of Defective Cable Terminati...

引用

2022 International Conference on Power, Energy and Innovations, ICPEI 2022

作者： Jamtsho, Karma Suwanasri, Thanapong Panmala, Nattapon Suwanasri, Cattareeya EPE Program The Sirindhorn International Thai-German Graduate School of Engineering KMUTNB 1518 Pracharat 1 Rd.Bangsue Bangkok Thailand Department of Teacher Training in Electrical Engineering Faculty of Technical Education KMUTNB 1518 Pracharat 1 Rd. Bangsue Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering KMUTNB 1518 Pracharat 1 Rd.Bangsue Bangkok Thailand

ISBN: (数字)9781665460194

ISBN: (纸本)9781665460194

This paper presents the Partial Discharge (PD) investigation of defective medium voltage (3.6/6(7.2) kV) cable terminations and the impact of using different voltage sources namely AC 50 Hz and Very Low Frequency (VLF) voltage source of 0.1 Hz as supply voltage. The PD is detected by High Frequency Current Transformer (HFCT). Electric field stress investigation is carried out by using Finite Element Method Magnetic (FEMM) simulation tool. The defective cable terminations used are no-stress control, needle tip on insulation screen and sandpaper scrubbed termination. PD investigation is carried out by applying 50 Hz and 0.1 Hz voltage sources and Partial Discharge Inception Voltage (PDIV), Partial Discharge Extinction Voltage (PDEV), PD magnitude and Pulse Repetition Rate are recorded. The comparison of PDIV values demonstrates the impact of different voltage sources. © 2022 IEEE.

关键词： Electric connectors

来源：评论

学校读者我要写书评

暂无评论

Fusion of Mixture of Experts and Generative Artificial Intelligence in Mobile Edge Metaverse

arXiv

引用

arXiv 2024年

作者： Liu, Guangyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Mao, Shiwen Kim, Dong In The College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Auburn University Auburn United States The School of Electrical and Computer Engineering University of Sydney Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is slowed down by the challenges of content creation, scalability, and dynamic user interaction. Our study investigates an integration of Mixture of Experts (MoE) models with Generative Artificial Intelligence (GAI) for mobile edge computing to revolutionize content creation and interaction in the Metaverse. Specifically, we harness an MoE model's ability to efficiently manage complex data and complex tasks by dynamically selecting the most relevant experts running various sub-models to enhance the capabilities of GAI. We then present a novel framework that improves video content generation quality and consistency, and demonstrate its application through case studies. Our findings underscore the efficacy of MoE and GAI integration to redefine virtual experiences by offering a scalable, efficient pathway to harvest the Metaverse's full potential. © 2024, CC BY.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Model for Pauses in the Synthesized Speech of Mathematical Expressions in MathML 22

A Dynamic Model for Pauses in the Synthesized Speech of Math...

引用

Proceedings of the 14th International Conference on Education Technology and computers

作者： Adriana Souza Diamantino Freitas Bahia Federal Institute of Education Science and Technology Brazil and Doctoral Program in Digital Media Faculty of Engineering Faculty of Engineering of University of Porto Portugal Department of Electrical and Computer Engineering Faculty of Engineering of University of Porto Portugal

ISBN: (纸本)9781450397766

Voice synthesizers still present several challenges in the speech of mathematical content, as spoken mathematics has quite peculiar rules. In the synthesized speech, pauses help blind and visually impaired students identify the limits of mathematical operators and subexpressions. However, most studies on pauses define them uniformly or use simple punctuation marks to force the synthesizer to introduce pauses in certain parts of the expression. Speech is a dynamic process and pauses in expressions also need to be dynamic to make the synthetic speech of expressions more natural, as this can help in memorizing this type of content. This work proposed a dynamic model of pauses for mathematical expressions. Collected math expressions spoken by teachers were used to create the model. These expressions were useful for identifying patterns and creating a linear regression model. Blind and visually impaired students evaluated the model. Some improvements were observed when we compared the synthesized mathematical expressions with the model and Audiomath, the parameter tool used in this study.

关键词： Accessibility Synthesized Speech Mathematics Visual Impairment

来源：评论

学校读者我要写书评

暂无评论

Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning 7

Impact of CLAHE-based image enhancement for diabetic retinop...

引用

7th International Conference on computer Science and Computational Intelligence, CSCI 2022

作者： Hayati, Mira Muchtar, Kahlil Roslidar Maulina, Novi Syamsuddin, Irfan Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Faculty of Medicine Universitas Syiah Kuala Banda Aceh23111 Indonesia Department of Computer and Networking Engineering Politeknik Negeri Ujung Pandang Makassar90245 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Diabetic retinopathy (DR) is a type of diabetes mellitus that attacks the retina of the eye. DR will cause patients to experience blindness slowly. Generally, DR can be detected by using a special instrument called an ophthalmoscope to view the inside of the eyeball. However, in conditions where there is a very small difference between the normal image and the DR image, computer-based assistance is needed for maximizing image reading value. In this research, a method of image quality improvement will be carried out which will then be integrated with a classification algorithm based on deep learning. The results of image improvement using Contrast Limited Adaptive Histogram Equalization (CLAHE) shows that the average accuracy of the method on several models is very competitive, 91% for the VGG16 model, 95% for InceptionV3, and 97% for EfficientNet compared to the results original image which only has an accuracy of 87% for VGG16 model, 90% for InceptionV3 model, and 95% for EfficientNet. However, in ResNet34 better accuracy is obtained in the original image with an accuracy of 95% while in the CLAHE image the accuracy value is only 84%. The results of this comprehensive evaluation and recommendation of famous backbone networks can be useful in the computer-Aided diagnosis of diabetic retinopathy. © 2022 Elsevier B.V.. All rights reserved.

关键词： Image enhancement

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：