检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Asokan, Siddarth Mohammed, Fatwir Sheikh Sekhar Seelamantula, Chandra Indian Institute of Science Robert Bosch Center for Cyber-Physical Systems Bengaluru12 India University of Washington SeattleWA98195 United States Indian Institute of Science Department of Electrical Engineering Bengaluru12 India

ISBN: (纸本)9781728163277

Generative adversarial networks (GANs) comprise generator and discriminator networks trained adversarially to learn the underlying distribution of a dataset. Recently, we have shown that the optimal GAN discriminator can be obtained in closed-form as the solution to the Poisson partial differential equation (PDE). While existing approaches either train a network or solve the PDE in closed-form, we propose training the generator through the gradient field of the optimal discriminator. In this paper, we establish a connection between active contour models (snakes) and GANs. We evolve a set of snake points over the gradient field of radial basis function (RBF) Coulomb GAN. The generator is then trained to follow the trajectory of the snake. The proposed approach benefits from both the sample diversity seen in flow-based approaches and the fast sampling capability of GANs. Experimental validation on 2-D synthetic data shows that the proposed approach leads to accelerated convergence, compared against the baseline approaches that either employ network or kernel-based discriminators. © 2023 IEEE.

关键词： active contours models (snakes) Generative adversarial networks Laplacian operator optimal discriminator

来源：评论

学校读者我要写书评

暂无评论

Transmission Line Differential Protection Based on Numerical Solution of Partial Differential Equations

Transmission Line Differential Protection Based on Numerical...

引用

2023 IEEE International Conference on Advanced Power System Automation and Protection, APAP 2023

作者： Liu, Zhiquan Liu, Yu Lu, Dayou Yang, Yayu Fan, Rui Center for Intelligent Power and Energy Systems School of Information Science and Technology ShanghaiTech University China China Shanghai Maritime University Department of Electrical Engineering China University of Denver United States

ISBN: (纸本)9798350306668

Current differential protection is a widely adopted and effective high-voltage AC transmission line protection scheme. The long distance of the transmission line determines that the distributed parameters and corresponding capacitive currents are not negligible. In fact, the physical laws of a distributed parameter transmission line can be expressed as a set of partial differential equations (PDEs). In this paper, a time-domain current differential protection method based on two-terminal electrical quantities and the PDE line model is proposed. The method does not depend on the power frequency phasors, can accurately compensate line capacitive current, and can effectively improve the protection speed and sensitivity. Numerical experiments validate the effectiveness and reliability of the proposed method. Additionally, the proposed method demonstrates satisfactory real-time performance under relatively low sampling rates (4k Hz). © 2023 IEEE.

关键词： Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Coffee Bean Binary Classification Through Deep Learning Techniques 1

引用

International Conference on Innovative Technologies in Intelligent systems and Industrial Applications, CITISIA 2022

作者： Islamy, Fajrul Muchtar, Kahlil Arnia, Fitri Dawood, Rahmad Febriana, Alifya Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department Master of Computer Science Program BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Coffee beans are one of the high-value commodities in Indonesia, but the sorting method for the quality of coffee beans still uses visual methods and sieves with mechanical machines. This study aims to provide an alternative to classifying coffee beans using Deep Learning algorithms, such as the ResNet-18 and MobileNetV2. The dataset used is USK-COFFEE which consists of two classes, the normal coffee bean class, and the defect coffee bean class. The models were trained using the balanced and imbalanced datasets, meaning that two scenarios were performed. From the results of this study, the accuracy value for the ResNet-18 model was 91.50% when trained on the balanced dataset and 90.87% on the imbalanced dataset. It outperformed the MobileNetV2 architecture, which only achieved 0.8125 and 0.8112 accuracy scores when trained on the balanced and imbalanced datasets, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity ML-Based Methods for Malware Classification

引用

Computers, Materials & Continua 2024年第9期80卷 4833-4857页

作者： Mahmoud E.Farfoura Ahmad Alkhatib Deema Mohammed Alsekait Mohammad Alshinwan Sahar A.El-Rahman Didi Rosiyadi Diaa Salama Abd Elminaam Cybersecurity Department Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Computer Systems Program-Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairo11629Egypt Research Center for Artificial Intelligence and Cybersecurity Electronics and Informatics OrganizationNational Research and Innovation Agency(BRIN)KST Samaun SamadikunBandung40135Republic of Indonesia Jadara Research Center Jadara UniversityIrbid21110Jordan MEU Research Unit Middle East UniversityAmman11831Jordan

The article describes a new method for malware classification,based on a Machine Learning(ML)model architecture specifically designed for malware detection,enabling real-time and accurate malware *** an innovative feature dimensionality reduction technique called the Interpolation-based Feature Dimensionality Reduction Technique(IFDRT),the authors have significantly reduced the feature space while retaining critical information necessary for malware *** technique optimizes the model’s performance and reduces computational *** proposed method is demonstrated by applying it to the BODMAS malware dataset,which contains 57,293 malware samples and 77,142 benign samples,each with a 2381-feature *** the IFDRT method,the dataset is transformed,reducing the number of features while maintaining essential data for accurate *** evaluation results show outstanding performance,with an F1 score of 0.984 and a high accuracy of 98.5%using only two reduced *** demonstrates the method’s ability to classify malware samples accurately while minimizing processing *** method allows for improving computational efficiency by reducing the feature space,which decreases the memory and time requirements for training and *** new method’s effectiveness is confirmed by the calculations,which indicate significant improvements in malware classification accuracy and *** research results enhance existing malware detection techniques and can be applied in various cybersecurity applications,including real-timemalware detection on resource-constrained *** and scientific contribution lie in the development of the IFDRT method,which provides a robust and efficient solution for feature reduction in ML-based malware classification,paving the way for more effective and scalable cybersecurity measures.

关键词： Malware detection ML-based models dimensionality reduction feature engineering

来源：评论

学校读者我要写书评

暂无评论

Promoting effect of d-band center and in-situ precipitation strategy on sulfur evolution reaction

引用

Journal of Energy Chemistry 2025年第5期104卷 740-748页

作者： Jun Pu Yun Tan Jiasen Yin Zihan Shen Shoujie Liu Kai Zhang Lei Zhou Yagang Yao Key Laboratory of Functional Molecular Solids Ministry of EducationAnhui Provincial Engineering Laboratory for New-Energy Vehicle Battery Energy-Storage MaterialsCollege of Chemistry and Materials ScienceAnhui Normal UniversityWuhu 241002AnhuiChina National Laboratory of Solid State Microstructures College of Engineering and Applied SciencesJiangsu Key Laboratory of Artificial Functional MaterialsCollaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210093JiangsuChina State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China School of Materials Science and Engineering Anhui UniversityHefei 230601AnhuiChina School of Energy and Power Engineering Jiangsu UniversityZhenjiang 212013JiangsuChina Department of Electrical Engineering Eindhoven University of TechnologyEindhoven MB 5600the Netherlands

The slow conversion of polyphase in lithium-sulfur(Li-S)batteries not only intensifies the shuttle effect of lithium polysulfides(LiPSs),but also causes the continuous accumulation of inactive sulfur species,resulting in rapid capacity attenuation and sluggish dynamic ***,the promoting effect of atomic interface stress on sulfur reaction was investigated via CoFe-CoFe_(2)O_(4)heterogeneous nanosheets with a cavity *** strain force induced by the in-situ precipitation of Co Fe bimetallic alloy in oxide matrix increased the d-band center,which was conducive to the interaction between catalyst and Li *** sulfur cathode based on this two-dimensional(2D)nanosheet design showed an extremely high capacity of 751 mAh g^(-1)at 4 *** with a sulfur loading of 5.55 mg cm^(-2),its area capacity was still as high as 7.15 mAh cm^(-2).Meanwhile,the enhanced stability greatly improved the practical potential of Li-S batteries.

关键词： 2D nanosheets In-situ precipitation Strain effect D-band center Li-S batteries

来源：评论

学校读者我要写书评

暂无评论

Accelerating Deep Neural Networks with a Low-Cost Lossless Compression

Accelerating Deep Neural Networks with a Low-Cost Lossless C...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Kim, Seongwook Byeon, Gwangeun Lee, Seungeui Bae, Youngseok Hong, Seokin Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of Advanced R&D Center Hanwha Systems Co. Ltd. Korea Republic of Agency for Defense Development Emerging Science and Technology Directorate Korea Republic of

ISBN: (纸本)9798331510756

Since deep learning inference involves a significant amount of computations, there have been a lot of efforts to accelerate the inference process by eliminating ineffectual compu-tations. As a solution to this problem, several sparsity-aware deep learning accelerators have been proposed. These accelerators perform the inference on compressed data (filters and feature maps) and dynamically remove the ineffectual multiplications with zero operands. For efficiently handling the compressed data on the accelerators, a simple and effective compression scheme, which encodes the whole data with its nonzero values and their positions, is necessary. However, prior approaches have several shortcomings, such as low compression efficiency and high complexity in compression and decompression hardware. This paper proposes a low-cost compression scheme that can be applied to sparsity-aware deep-learning accelerators. The compression scheme synergistically combines two low-cost compression schemes: Zero-Value Compression (ZVC) and Base-Delta-Immediate Compression (BDI). Our experimental evaluation shows that the proposed compression scheme achieves an average compression ratio of 2.26, resulting in 2.33x performance improvement, © 2025 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Investigation on Structures of Axial Gap Type Magnetic Multiple Spur Gear for In-Wheel Motor System of Electric Vehicle

Investigation on Structures of Axial Gap Type Magnetic Multi...

引用

2023 IEEE Transportation Electrification Conference and Expo, Asia-Pacific, ITEC Asia-Pacific 2023

作者： Kamijo, Taiga Aiso, Kohei Akatsu, Kan Aoyama, Yasuaki Shibaura Institute of Technology Electrical Engineering and Computer Science Tokyo Japan Shibaura Institute of Technology Department of Electrical Engineering Tokyo Japan Yokohama National University Division of Intelligent Systems Engineering Department of Faculty of Engineering Yokohama Japan Center for Technology Innovation - Materials Hitachi Ltd. Research & Development Group Ibaraki Japan

ISBN: (纸本)9798350314274

A novel drive system using Magnetic Multiple Spur Gear (MMSG) and multiple high-speed motors is characterized by small size, lightweight, and high efficiency even at high-speed region, it is expected to apply to in-wheel motor systems. However, there is a risk of contact between the rotors when applied to in-wheel motor system. In this study, a novel axial-gap MMSG is proposed to solve this problem, stabilize the air gap between the high-speed and low-speed rotors, and effectively utilize the magnets, and its performance is evaluated by finite element analysis. © 2023 IEEE.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

A Stable Discontinuous Galerkin Time-Domain Method for Simulation of Thin Conductive Layers

A Stable Discontinuous Galerkin Time-Domain Method for Simul...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio science Meeting, AP-S/URSI 2022

作者： Özakin, M. Burak Chen, Liang Ahmed, Shehab Bagci, Hakan Electrical and Computer Engineering Program Computer Electrical and Mathematical Science and Engineering Division Thuwal23955 Saudi Arabia Ali I. Al-Naimi Petroleum Engineering Research Center Thuwal23955 Saudi Arabia

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

A conductive layer that is much thinner than the skin depth is often incorporated into electromagnetic solvers as a resistive boundary condition (RBC) to avoid fine meshes (and consequently small time steps for time-domain methods). When the discontinuous Galerkin time-domain (DGTD) method, which relies on an explicit Runge-Kutta (RK) scheme for time integration, is used in a simulation involving an RBC surface with high conductivity, the solution becomes unstable. In this work, to circumvent this bottleneck, a locally-implicit time marching scheme is developed. The proposed method uses implicit Euler backward and explicit Euler forward schemes to discretize the time derivatives in local DG equations associated with the elements that "touch"and do not "touch"the RBC surface, respectively. This yields a locally-implicit Euler (LIME) time marching scheme that maintains its stability in the presence of a highly conductive layer. Indeed, numerical results demonstrate that LIME-DGTD is more stable than RK-DGTD for a transmission problem involving a thin metal sheet. © 2022 IEEE.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Integrated Preparation of Photonic Spin-Orbit Qudits

Integrated Preparation of Photonic Spin-Orbit Qudits

引用

CLEO: science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Zhao, Haoqi Zhang, Yichi Gao, Zihe Yim, Jieun Wu, Shuang Litchinitser, Natalia M. Ge, Li Feng, Liang Department of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA19104 United States Department of Materials Science and Engineering University of Pennsylvania PhiladelphiaPA19104 United States Department of Electrical and Computer Engineering Department of Physics Duke University DurhamNC27708 United States Department of Engineering Science and Physics College of Staten Island CUNY Staten IslandNY10314 United States The Graduate Center CUNY New YorkNY10016 United States

ISBN: (纸本)9781957171395

Preparing and manipulating N-dimensional flying qudits as well as subsequently establishing their entanglement are still challenging tasks. Here, using an integrated approach, we explore the synergy from two degrees of freedom of light, spatial mode and polarization, to generate, encode, and manipulate flying photon qudits in a four-dimensional Hilbert space with high quantum fidelity, intrinsically enabling enhanced noise resilience and higher quantum data rates. © Optica Publishing Group 2024

关键词： Degrees of freedom (mechanics)

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：