检索结果-内蒙古大学图书馆

IEEE International Conference on Communications (ICC)

作者： Zehao Liu Fang Yang Jian Song Zhu Han Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing P. R. China Shenzhen International Graduate School Tsinghua University Shenzhen P. R. China Department of Electrical and Computer Engineering University of Houston Houston TX USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Optical intelligent reflecting surfaces (OIRS) can be deployed in visible light communication (VLC) systems to provide OIRS-reflected paths for multiple light-emitting diodes (LEDs) and users via adjustable reflective characteristics, thereby significantly mitigating the signal blockage challenges in VLC. To achieve this goal, the effectiveness of OIRS in the non-orthogonal multiple access (NOMA)-based multiple-input single-output (MISO) VLC system is explored, while the system model is established considering both the line-of-sight (LoS) and the OIRS-reflected paths. Subsequently, the problem is formulated with the objective of optimizing the OIRS configuration to maximize the achievable sum data rate with the diverse constraints. To address the highly intractable and non-convex problem, a relaxed iterative optimization algorithm based on the Taylor expansion is proposed in this paper. Moreover, numerical results are provided to show the improvement of the achievable sum data rate and the effects of the proposed relaxed iterative algorithm.

关键词： NOMA Simulation Line-of-sight propagation MISO communication Taylor series Light emitting diodes Optical reflection

来源：评论

学校读者我要写书评

暂无评论

Federated Reinforcement Learning with Constellation Collaboration for Dynamic Laser Inter-Satellite Link Scheduling

Federated Reinforcement Learning with Constellation Collabor...

引用

IEEE International Conference on Communications (ICC)

作者： Guanhua Wang Fang Yang Jian Song Zhu Han Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing P. R. China Shenzhen International Graduate School Tsinghua University Shenzhen P. R. China Department of Electrical and Computer Engineering University of Houston Houston TX USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The scheduling of the laser inter-satellite links (LISLs) can effectively improve the network performance but is challenging in mega-constellations due to the large amount of satellites. In this paper, inter-OP LISL scheduling is realized by federated reinforcement learning, which reduces complexity by decomposing global scheduling into independent decisions for each satellite and solved by multi-agent reinforcement learning. Based on the constellations collaboration, federated learning (FL) with partial and global aggregations is utilized to reduce the overhead for the model update, where the geostationary orbit (GEO)-GEO collaboration for global aggregation can be performed infrequently since the indirect associations among the GEO satellites according to the motion of low Earth orbit (LEO) satellite. Meanwhile, simulation results indicate that the proposed method reduces the average hop count by over two hops and decreases the number of LISLs by over 25% compared to the fixed LISLs, and the model update overhead is reduced to 46.6% of that in the centralized method.

关键词： Satellites Scheduling algorithms Simulation Collaboration Low earth orbit satellites Reinforcement learning Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

Characteristics Fluctuation of Sub-3-nm Bulk FinFET Devices Induced by Random Interface Traps

Characteristics Fluctuation of Sub-3-nm Bulk FinFET Devices ...

引用

IEEE Conference on Nanotechnology

作者： Sekhar Reddy Kola Min-Hui Chuang Yiming Li Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering Institute of Communications Engineering Institute of Biomedical Engineering Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Hsinchu Taiwan

Three-dimensional (3D) bulk fin-typed field effect transistors (FinFETs) have emerged as key devices that can scale down the technology node beyond 22-nm. However, the scaled devices have created new sources of fluctuation inherent in 3D geometry. The interface trap is one such fluctuation that is caused by the trapping and de-trapping of charge carriers and has an adverse effect on device characteristics and variability. In this work, we study impacts of random interface traps (RITs) on electrical characteristic of bulk FinFETs by using a 3D quantum-mechanically corrected device simulation. RIT position effects on short channel effects (SCEs) are examined with physical governed influence to show the major fluctuations. More than 50% reductions of the RITs-induced characteristic fluctuation of the germanium (Ge) devices are observed, compared with Si devices. The Ge ones can reduce SCE variations and exhibit high immunity to RITs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FincGAN: A Gan Framework of Imbalanced Node Classification on Heterogeneous Graph Neural Network

FincGAN: A Gan Framework of Imbalanced Node Classification o...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hung Chun Hsu Ting-Le Lin Bo-Jun Wu Ming-Yi Hong Che Lin Chih-Yu Wang Graduate Program of Data Science National Taiwan University and Academia Sinica Taiwan Department of Accounting and Statistics National ChengChi University Taiwan Department of Risk Management and Insurance National ChengChi University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan

Graph Neural Networks (GNNs) frequently face class imbalance issues, especially in heterogeneous graphs. Existing GNNs often assume balanced class sizes, which isn’t true in many cases. Applying them directly to imbalanced data can lead to sub-optimal performance. Traditional oversampling methods, while effective, risk overfitting and face difficulties in reintegrating synthetic samples into the original graph. In this study, we introduce Framework of Imbalanced Node Classification on heterogeneous graph neural network with GAN (FincGAN), a new framework that utilizes oversampling techniques to address class imbalance in heterogeneous graphs. Instead of duplicating existing samples, FincGAN employs a Generative Adversarial Network (GAN) to create synthetic samples and uses deep learning-based edge generators to connect them back to the original graph. Our evaluations on spam user detection in the Amazon and Yelp Review datasets show that FincGAN outperforms baseline models in all essential metrics, including F-score and AUC-PRC score, showing its effectiveness in addressing class imbalance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relationship Between Mechanical Deformation and Contact Force Applied by Catheter Tip on Cardiac Muscle: Experimentation and Computer Modeling

Relationship Between Mechanical Deformation and Contact Forc...

引用

IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability (ECBIOS)

作者： Yukako Ijima Kriengsak Masnok Juan J. Perez Ana González-Suárez Enrique Berjano Nobuo Watanabe Master's Program Global Course of Engineering and Science Graduate School of Engineering and Science Shibaura Institute of Technology Saitama Japan Biofluid Science and Engineering Laboratory Functional Control Systems Graduate School of Engineering and Science Shibaura Institute of Technology Saitama Japan Department of Electronic Engineering BioMIT Universitat Politecnica de Valencia Valencia Spain Translational Medical Device Lab School of Engineering University of Galway Galway Ireland Department of Bio-Science and Engineering Biofluid Science and Engineering Laboratory Functional Control Systems Graduate School of Engineering and Science College of Systems Engineering and Science Shibaura Institute of Technology Saitama Japan

The cardiac muscle is elastic and deformable. Pushing a catheter in contact with the cardiac muscle surface to conduct focal energy-based ablative therapies, such as RF ablation, requires an adequate electrode-tissue contact surface to transfer the energy to the target site. In this regard, the relationship between the contact force (CF) and the resulting mechanical response is still unclear, in particular, the insertion depth (ID) and the diameter of the surface deformation. The objective of this study was to quantify these relationships using an ex vivo model and a computational model. A rigid bar with a 2.3 mm diameter blunt tip (mimicking a 7Fr standard ablation catheter) was placed at a perpendicular orientation on a fragment of the porcine heart. CF values ranged from 10 to 80g. We used ANSYS to build a Mooney-Rivlig model of 3 parameters based on hyperelastic material and to simulate the same conditions as in the experiments. The experimental results showed a strong linear correlation between CF and insertion depth ID ( $\mathrm{R}^{2}=0.97, \mathrm{P} < 0.001$ ), from $0.7 \pm 0.3$ mm at 10 gto $6.9 \pm 0.1$ mm at 80 g. We also found a strong linear correlation between CF and minor and major diameters of the surface deformation assessed, from $4.0 \pm 0.4$ mm at 20 g to $10.3 \pm 0.0$ mm at 80 g ( $\mathrm{R}^{2}=0.96$ ), and from $6.4 \pm 0.7$ mm at 20 g to $16.7 \pm 0.1$ mm at 80 g ( $\mathrm{R}^{2}=0.95$ ), respectively. A descent gradient algorithm was used to minimize the mean square error (MSE) between the experimental and computational results of ID for the 10 values of CF. After trying different combinations for the3 parameters of the Mooney-Rivlig model, an optimal fit was achieved after 5 iterations, with an error of less than 0.55 mm for ID. This same mode was then used to predict the diameter of the surface deformation, obtaining an error of less than 0.65 mm. The results confirm that a Mooney-Rivlig model of three parameters based on

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Predictive Controller Applied in a Bidirectional DC-DC Converter 16

Generalized Predictive Controller Applied in a Bidirectional...

引用

16th Brazilian Power electronics Conference, COBEP 2021

作者： Da Silva, Daniel Abreu Macedo Do Nascimento, Andre Cavalcante De Barros Araujo, Rejane De Souza Melo, Rogerio Jose Federal University of Pará Electrical Engineering Graduate Program Belém Brazil Federal Institute of Pará Department of Education Control and Industrial Processes Information and Communication Belém Brazil Undergraduate Electrical Engineering Estácio College Belém Brazil

ISBN: (纸本)9781665421294

This work proposes the project of the Generalized Predictive Controller (GPC), this is applied to a bidirectional converter, whose topology is the non-isolated Buck and Boost derived bidirectional DC-DC, present on a DC Nanogrid. The system consists of a primary bus, represented by Vdc, with high voltage, which is feeded by a renewable energy source that generates 175 V and a secondary source, represented by VBatt, with low voltage from a 48 V battery. The objective is to develop robustness and performance analysis, and ensure reference tracking and rejection of disturbance of this predictive controller when used in a bidirectional converter present in the aforementioned situation. In addition to analyzing how the control weighting factor interferes in the robustness and performance of this controller in this situation. © 2021 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Knacks of marine predator heuristics for distributed energy source-based power systems harmonics estimation

引用

Heliyon 2024年第15期10卷 e35776页

作者： Cheema, Khalid Mehmood Mehmood, Khizer Chaudhary, Naveed Ishtiaq Khan, Zeshan Aslam Raja, Muhammad Asif Zahoor El-Sherbeeny, Ahmed M. Nadeem, Ahmed Ud din, Zaki Department of Electronic Engineering Fatima Jinnah Women University Department of Electrical and Computer Engineering International Islamic University Future Technology Research Center National Yunlin University of Science and Technology International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Industrial Engineering Department College of Engineering King Saud University Department of Pharmacology and Toxicology College of Pharmacy King Saud University Department of Engineering Lancaster University

The power system incorporates renewable energy resources into the main utility grid, which possesses low or no inertia, and these systems generate harmonics due to the utilization of power electronic equipment. The precise and effective assessment of harmonic characteristics is necessary for maintaining power quality in distributed power systems. In this paper, the Marine Predator Algorithm (MPA) that mimics the hunting behavior of predators is exploited for harmonics estimation. The MPA utilizes the concepts of Levy and Brownian motions to replicate the movement of predators as they search for prey. The identification model for parameter estimation of harmonics is presented, and an objective function is developed that minimizes the difference between the real and predicted harmonic signals. The efficacy of the MPA is assessed for different levels of noise, population sizes, and iterations. Further, the comparison of the MPA is conducted with a recent metaheuristic of the Reptile Search Algorithm (RSA). The statistical analyses through sufficient autonomous executions established the accurate, stable, reliable and robust behavior of MPA for all variations. The substantial enhancement in estimation accuracy indicates that MPA holds great potential as a strategy for estimating harmonic parameters in distributed power systems. © 2024 The Author(s)

关键词： Harmonic estimation Marine predator algorithm Power systems Renewable energy systems

来源：评论

学校读者我要写书评

暂无评论

Measurement of Water Diffusion Coefficient in Cross-Linked Gelatins Using the Terahertz Time-Domain Spectroscopy Technique

Measurement of Water Diffusion Coefficient in Cross-Linked G...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Walden, D. Chakraborty, D. Cheng, J. Straksys, A. Stirke, A. Melo, W.C.M.A. Jukna, A. Komissarov, I. Sobolewski, Roman Department of Physics and Astronomy University of Rochester RochesterNY14627 United States Laboratory for Laser Energetics University of Rochester RochesterNY14623-1299 United States Materials Science Graduate Program University of Rochester RochesterNY14627 United States State Research Institute Center for Physical Sciences & Technology Vilnius Lithuania Department of Physics Vilnius Gediminas Technical University Vilnius Lithuania Department of Electrical and Computer Engineering University of Rochester RochesterNY14627 United States

A novel method has been developed to evaluate the water diffusion dynamics in gelatin-based gels, based on transient terahertz time-domain spectroscopy measurements. Such gels are widely used models for human skin. &#... 详细信息

ISBN: (纸本)9781957171395

关键词： Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Regression Model for Optimum Solar Collectors' Tilt Angles in Libya 8

Regression Model for Optimum Solar Collectors' Tilt Angles i...

引用

8th International engineering Conference on Renewable Energy and Sustainability, ieCRES 2023

作者： Nassar, Yasser F. Khozondar, Hala J. El- Abouhmod, Nasser M. Abubaker, Ahmed A. Ahmed, Abdussalam A. Alsharif, Abdulgader Khaleel, Mohamed M. Elnaggar, Mohamed El-Khozondar, Rifa J. Wadi Alshatti University Mechancal & Renewable Energy. Eng. Dept. Brack Libya The Islamic University of Gaza Electrical Eng. and Smart Systems Dept. Gaza Palestine Wadi Alshatti University Eng. Faculty Electrical and Electronic Eng. Dept. Brack Libya Bani Waleed University Mechanical Eng. Dept. Bani Waleed Libya Faculty of Engineering Johor Malaysia Karabu University Dept. of Electrical and Electronic Eng. Karabuk Turkey Palestine Technical College - Deir ElBalah Engineering Program Department Deir El-Balah Palestine Al-Aqsa University Faculty of Science Physics Departments Gaza Palestine

ISBN: (纸本)9798350300758

The present study presents a regression function for optimum tilt angle for fixed mode flat-plate solar harvesters suitable for different locations in Libya, sky conditions and albedo values. The research based on 14 years -15 minutes time series solar irradiation components which provided by Solargis database platform for 24 different locations in Libya, based on the contract signed between the Solargis Company and Wadi AlShatti University. Several transposition models are applied - corresponding to each location - for estimating the tilted global solar irradiance components according to recommendation of a local recent study. The proposed model corrects the optimum tilt angle by involving the three components of the solar irradiation: direct beam, sky-diffused and ground reflected solar irradiances. The results proved the applicability and reliability of the obtained regression model. In addition, results showed the high potential of the proposed model for use in engineering design, eco-energetic analysis and optimum design processes. © 2023 IEEE.

关键词： Location

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：