检索结果-内蒙古大学图书馆

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

Structure-from-Sherds++: Robust Incremental 3D Reassembly of Axially Symmetric Pots from Unordered and Mixed Fragment Collections

arXiv

引用

arXiv 2025年

作者： Yoo, Seong Jong Liu, Sisung Arshad, Muhammad Zeeshan Kim, Jinhyeok Kim, Young Min Aloimonos, Yiannis Fermüller, Cornelia Joo, Kyungdon Kim, Jinwook Hong, Je Hyeong Department of Computer Science University of Maryland College ParkMD United States Department of Artificial Intelligence Hanyang University Korea Republic of Faculty of Health Sciences University of Ottawa ON Canada Artificial Intelligence Graduate School UNIST Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Intelligence and Interaction Research Center Korea Institute of Science and Technology Korea Republic of Artificial Intelligence Graduate School The Department of Computer Science and Engineering UNIST Korea Republic of Department of Electronic Engineering Hanyang University Korea Republic of

Reassembling multiple axially symmetric pots from fragmentary sherds is crucial for cultural heritage preservation, yet it poses significant challenges due to thin and sharp fracture surfaces that generate numerous false positive matches and hinder large-scale puzzle solving. Existing global approaches, which optimize all potential fragment pairs simultaneously or data-driven models, are prone to local minima and face scalability issues when multiple pots are intermixed. Motivated by Structure-from-Motion (SfM) for 3D reconstruction from multiple images, we propose an efficient reassembly method for axially symmetric pots based on iterative registration of one sherd at a time, called Structure-from-Sherds++ (SfS++). Our method extends beyond simple replication of incremental SfM and leverages multi-graph beam search to explore multiple registration paths. This allows us to effectively filter out indistinguishable false matches and simultaneously reconstruct multiple pots without requiring prior information such as base or the number of mixed objects. Our approach achieves 87% reassembly accuracy on a dataset of 142 real fragments from 10 different pots, outperforming other methods in handling complex fracture patterns with mixed datasets and achieving state-of-the-art performance. Code and results can be found in our project page https://***/sfs/. Copyright © 2025, The Authors. All rights reserved.

关键词： Historic preservation

来源：评论

学校读者我要写书评

暂无评论

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

arXiv

引用

arXiv 2024年

作者： Jin, Peng Li, Hao Cheng, Zesen Li, Kehan Yu, Runyi Liu, Chang Ji, Xiangyang Yuan, Li Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China -Preferred Program Peking University Shenzhen Graduate School Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China

Text-to-motion generation requires not only grounding local actions in language but also seamlessly blending these individual actions to synthesize diverse and realistic global motions. However, existing motion generation methods primarily focus on the direct synthesis of global motions while neglecting the importance of generating and controlling local actions. In this paper, we propose the local action-guided motion diffusion model, which facilitates global motion generation by utilizing local actions as fine-grained control signals. Specifically, we provide an automated method for reference local action sampling and leverage graph attention networks to assess the guiding weight of each local action in the overall motion synthesis. During the diffusion process for synthesizing global motion, we calculate the local-action gradient to provide conditional guidance. This local-to-global paradigm reduces the complexity associated with direct global motion generation and promotes motion diversity via sampling diverse actions as conditions. Extensive experiments on two human motion datasets, i.e., HumanML3D and KIT, demonstrate the effectiveness of our method. Furthermore, our method provides flexibility in seamlessly combining various local actions and continuous guiding weight adjustment, accommodating diverse user preferences, which may hold potential significance for the community. The project page is available at https://***/GuidedMotion-project/. Copyright © 2024, The Authors. All rights reserved.

关键词： Blending

来源：评论

学校读者我要写书评

暂无评论

Investigating the Impact of Data Augmentation for Fine-Grained Grocery Product Classification Based on Vision Transformer

Investigating the Impact of Data Augmentation for Fine-Grain...

引用

Artificial Intelligence Robotics, Signal and Image Processing (AIRoSIP), International Conference on

作者： Rissa Rahmania Yaya Heryadi Lukas Lukas Wayan Suparta Ilvico Sonata Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Group (CEG) Faculty of Engineering Universitas Katolik Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

ISBN: (数字)9798350327472

ISBN: (纸本)9798350327489

The existence of fine-grained image classification supporting smart retail provides effectiveness in recognizing products with high similarity. However, the generic classification method performs poorly in identifying products from a subordinate category. This paper aims to identify augmentation techniques to leverage the Vision Transformer (ViT) model to classify the fine-grained grocery product, which involves embedding patches and transformer encoders to extract the main features. First, we develop a fine-grained image dataset with ColorJitter, CutOut, and combining both augmentations. Secondly, we perform experiments and analysis of ViT size, embedded patch size and image size in the patch embedding process. Lastly, the ViT model are evaluated according to the image sizes 224, 384, and 512 in accuracy, loss, and confusion matrix. The highest accuracy was obtained at 0.9922. The ColorJitter and CutOut improved the confusion matrix in ViT-B/16 and ViT-L/16 with an image size of 384 and 512. The results show that both augmentations in the ViT model are able to distinguish fine-grained grocery products.

关键词： Surveys Computer vision Accuracy Image recognition Transformers Feature extraction Data augmentation Artificial intelligence Image classification

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：