检索结果-内蒙古大学图书馆

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Afrin, Fahmida Li, Haipeng Wang, Boyang Ghose, Nirnimesh School of Computing University of Nebraska-Lincoln United States University of Cincinnati Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798331508050

Deep-learning radio fingerprinting is not robust against spatial variations, where a neural network trained on location A does not perform well over RF signals from location B. We promote the robustness of deep-learning radio fingerprinting against spatial variations by synergizing Complex-Valued Neural Networks (CVNNs) and pseudo-labeling. Compared to existing solutions, we leverage pseudo-labeling to fine-tune a CVNN without needing labeled RF signals from a new location. We collect large-scale real-world datasets across different locations. We conduct comprehensive evaluations of these datasets with multiple complex-valued activation functions. Our experimental results significantly improve the accuracy of radio fingerprinting when training data and test data are from two different locations (e.g., increasing accuracy from 40.0% to 62.8%). © 2025 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Synthetic Supervising and Multi-view Consistency Self-supervising Based Animal 3D Reconstruction by Single Image 4th

Two-Stage Synthetic Supervising and Multi-view Consistency ...

引用

4th International Conference on Smart Multimedia, ICSM 2024

作者： Kuang, Zijian Ying, Lihang Jin, Shi Cheng, Li Department of Computing Science University of Alberta Edmonton Canada Zerobox Inc. Edmonton Canada Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

ISBN: (纸本)9783031824746

Pixel-aligned Implicit Function (PIFu) effectively captures subtle variations in body shape within a low-dimensional space through extensive training with human 3D scans, its application to live animals presents formidable challenges due to the difficulty of obtaining animal cooperation for 3D scanning. To address this challenge, we propose the combination of two-stage supervised and self-supervised training to address the challenge of obtaining animal cooperation for 3D scanning. In the first stage, we leverage synthetic animal models for supervised learning. This allows the model to learn from a diverse set of virtual animal instances. In the second stage, we use 2D multi-view consistency as a self-supervised training method. This further enhances the model’s ability to reconstruct accurate and realistic 3D shape and texture from largely available single-view images of real animals. The results of our study demonstrate that our approach outperforms state-of-the-art methods in both quantitative and qualitative aspects of bird 3D digitization. The source code is available at https://***/kuangzijian/drifu-for-animals. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

RIS with Nanomaterials for FutureG Applications 18

RIS with Nanomaterials for FutureG Applications

引用

18th IEEE Nanotechnology Materials and Devices Conference, NMDC 2023

作者： Al-Duhni, Ghaleb Saleh Ghaleb Valera, Tatiana Pulugurtha, Markondeya Raj Volakis, John L. Venkatakrishnan, Satheesh B. Florida International University College of Engineering and Computing Department of Electrical and Computer Engineering MiamiFL33185 United States

ISBN: (纸本)9798350335460

Reconfigurable Intelligent Surfaces (RIS) also known as Intelligent Reflecting Surfaces (IRS) often depend upon metasurfaces. These typically comprise of a large array of passive elements that can be fabricated to modulate reflection amplitude or phase or both to create tunable functions that are independently controlled. Various RIS are developed to improve spectral efficiency through ultrawideband antennas, enhanced beamforming with higher gain and bandwidth, spatial reconfigurability, selective and adjustable isolation, and other desired features. Several approaches to tune the RIS performance are being explored. This paper reviews the primary approaches and the benefit of emerging tunable nanomaterials in achieving such RIS functions. Designs with 1-bit and 6-bit phase shifters are discussed in the first part. Various opportunities with nanomaterials and nanodevices to induce such phase shifts are discussed in the last part of the paper. © 2023 IEEE.

关键词： Nanostructured materials

来源：评论

学校读者我要写书评

暂无评论

Two Birds with One Stone: A Dense Attentive GAN-based Model for Detecting Alzheimer's and Parkinson's Disorders 14

Two Birds with One Stone: A Dense Attentive GAN-based Model ...

引用

14th International Conference on Cloud computing, Data Science and engineering, Confluence 2024

作者： Devika, K. Murthy Oruganti, V. Ramana Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Electrical and Electronics Engineering Coimbatore India School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amaravati India

ISBN: (纸本)9798350344837

This paper investigates two neurodegenerative disorders in adults - Alzheimer's (AD) and Parkinson's (PD). Most works in the research explored these diseases independently - AD vs. healthy subjects and PD vs. healthy subjects. We consider a one-class framework for capturing the characteristics of healthy subjects. This one-class model views any subject with AD or PD as an outlier. We employ Dense Attentive GAN for the one-class model. T1-weighted longitudinal structural magnetic resonance images (sMRI) are used as input. Furthermore, we use longitudinal samples to train the framework (two scans per subject over a 12-month gap). Most traditional methods relied on cross-sectional data (one scan per subject). The proposed method is analogous to doctor's diagnoses of the subject in different sessions to recognise the disorder. Extensive experimental studies have shown that our proposed method outperforms all other AD and PD-based works in the literature. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

FedSTGNN: A Federated Spatio-Temporal Graph Neural Network 15

FedSTGNN: A Federated Spatio-Temporal Graph Neural Network

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Yoon, Heeyong Chon, Kang-Wook Kim, Min-Soo Dgist Department of Electrical Engineering and Computer Science Daegu Korea Republic of School of Computer Science and Engineering Koreatech Cheonan Korea Republic of School of Computing Kaist Daejeon Korea Republic of

ISBN: (纸本)9798350364637

Owing to the explosive growth of the Internet of Things (IoT), there have been vast volumes of sensor-generated time series data in various locations. A lot of network usage occurs through these locations to process the sensor-generated data. To reduce network usage, the point of data processing gradually shifts from the central cloud to servers at the edge of the Internet, called edge servers. To cover the paradigm shift, there has been a challenging issue in training a neural network model, which aggregates the data generated by different locations and causes a massive amount of transmitted data across the network. Federated learning successfully resolves this issue by exchanging model parameters in the edge server through the central cloud. Meanwhile, Spatio-Temporal Graph Neural Networks (STGNNs) have gained much attention for analyzing time series data transmitted from several locations in IoT environments. Despite the increasing number of STGNN models that have been examined, the integration of STGNNs and federated learning remains underexplored. This paper presents FedSTGNN, a framework that seamlessly adapts arbitrary STGNN models to edge computing environments. The proposed method partitions the spatio-temporal graph with a mathematical definition and then trains each partitioned data with an arbitrary STGNN model on edge servers separately. Then, it aggregates all the model parameters in the central cloud with dramatically reduced network usage. Through experiments, we demonstrate that the FedSTGNN framework could train the model with a reduced amount of network communication by utilizing the advantages of edge computing and a slight loss in accuracy. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Automatic Skull Shape Completion of Defective Skulls Using Transformers for Cranial Implant Design 2

Automatic Skull Shape Completion of Defective Skulls Using T...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Resmi, S. Singh, Rimjhimpadam Palaniappan, Kannappan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Dept. of Electrical Engineering and Computer Science University of Missouri MO United States

Cranioplasty is a surgical method that restores the aesthetic and protecting function of a damaged skull by implanting material into the damaged *** and accurate design of patient specific cranial implants is very much required in the process of *** time consumption for designing and manufacturing of patient specific cranial implant has become an obstruction for cranioplasty procedures. Hence, a fully automatic and fast design of cranial implant becomes very important. The cranial implant design processmainly comprises of two steps. The former step concentrates on the automatic skull shape completion of defective skulls to fill the gaps and the cracks created in the skull. While the second step computes the difference between defective input and the completed skull for generating the implant. Currently computer aided design is used for the skull shape completion task which is a time consuming process. The application of deep learning techniques may result to faster and accurate skull shape completionwhich can be used for the design of patient specific cranial implants. This work proposes a novel approach combining 3D U-Net with Transformers for the automatic skull shape completion *** are using a vision transformer in the encoder section of the 3D U-Net architecture to consider the volumetric skull reconstruction as sequence- to-sequence prediction problem and to efficaciously grasp the global contextual information. The work also compares its performance with the famous variants of 3D U-Net deep network model namely, 3D U-Net and 3D U-Net with attention. From the values resulted for the dice coefficient metric it is clear that the proposed 3D U-Net with transformer approach performs better than the other two models on test images. © 2024 Elsevier B.V.. All rights reserved.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

PAC-MC: An Efficient Password-Based Access Control Framework for Time Sequence Aware Media Cloud

引用

IEEE Transactions on Mobile computing 2025年第7期24卷 5632-5648页

作者： Wang, Haiyan Liu, Penghui Zhong, Xiaoxiong Luo, Fucai Xiao, Bin Yang, Yuanyuan Peng Cheng Laboratory Department of New Networks Shenzhen518000 China Zhejiang Gongshang University School of Computer Science and Technology Hangzhou China Hong Kong Polytechnic University Department of Computing Hong Kong Stony Brook University Department of Electrical and Computer Engineering Stony BrookNY11794 United States

Cloud storage makes it easier for users to access and share data remotely, but it often requires integration with cryptographic technologies to address consumer-oriented applications, such as fine-grained data access, secure data sharing and retrieval. This paper focuses on the fine-grained access problem of media applications based on time sequence, that is, certain critical media applications based on time sequences should ideally be accessible only to authorized clients. The traditional keyword-based searchable encryption (SE) allows effective search and access over encrypted data while preserving data privacy, but most existing solutions do not support temporal access control (i.e., a mechanism that grants access permissions to users within a specified time range). In this paper, we propose PAC-MC, an efficient password-based access control framework for media cloud relying on content control with the time sequence attribute. PAC-MC not only supports multi-keyword search using any monotonic boolean formulas but also allows media owners to control content-encryption keys for different time periods with an updatable password. Furthermore, it supports the self-retrieval of content-encryption keys. In addition, PAC-MC is provably secure under the standard model. Finally, the detailed performance evaluation results and experimental comparisons indicate that PAC-MC is very efficient and outperforms the previous solutions in terms of computation, communication, and storage costs. © 2025 IEEE.

关键词： Media Encryption Access Control Cloud computing Servers Passwords Keyword Search Copyright Protection Streaming Media Performance Evaluation Access Control Content Protection Media Cloud Password Searchable Encryption Time Sequence Access Policy Access Control Framework Computational Cost Cloud computing Communication Cost Storage Cost Encrypted Data Security Proof User Data Hash Function Computational Overhead Secret Key Public Key Access Structure Symmetric Encryption Data Owner Communication Overhead Key Material Encryption Scheme Number Of Keywords Cloud Users Encryption Key Bilinear Pairing Security Model Encrypted File Media Services Single Search L 2 Cache Internet Of Things

来源：评论

学校读者我要写书评

暂无评论

DaC-GANSAEBF:Divide and Conquer-Generative Adversarial Network-Squeeze and Excitation-Based Framework for Spam Email Identification

引用

computer Modeling in engineering & Sciences 2025年第3期142卷 3181-3212页

作者： Tawfeeq Shawly Ahmed A.Alsheikhy Yahia Said Shaaban M.Shaaban Husam Lahza Aws I.Abu Eid Abdulrahman Alzahrani Department of Electrical Engineering Faculty of Engineering at RabighKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Electrical Engineering College of EngineeringNorthern Border UniversityArar91431Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border UniversityArar73213Saudi Arabia Department of Information Technology College of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information and Communication Technology College of Computing StudiesArab Open UniversityKuwait BranchKuwait City13033Al-SafatState of Kuwait Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddah23218Saudi Arabia

Email communication plays a crucial role in both personal and professional contexts;however,it is frequently compromised by the ongoing challenge of spam,which detracts from productivity and introduces considerable security *** spam detection techniques often struggle to keep pace with the evolving tactics employed by spammers,resulting in user dissatisfaction and potential data *** address this issue,we introduce the Divide and Conquer-Generative Adversarial Network Squeeze and Excitation-Based Framework(DaC-GANSAEBF),an innovative deep-learning model designed to identify spam *** framework incorporates cutting-edge technologies,such as Generative Adversarial Networks(GAN),Squeeze and Excitation(SAE)modules,and a newly formulated Light Dual Attention(LDA)mechanism,which effectively utilizes both global and local attention to discern intricate patterns within textual *** approach significantly improves efficiency and accuracy by segmenting scanned email content into smaller,independently evaluated *** model underwent training and validation using four publicly available benchmark datasets,achieving an impressive average accuracy of 98.87%,outperforming leading methods in the *** findings underscore the resilience and scalability of DaC-GANSAEBF,positioning it as a viable solution for contemporary spam detection *** framework can be easily integrated into existing technologies to enhance user security and reduce the risks associated with spam.

关键词： Email spam fraud light dual attention squeeze and excitation divide and conquer-generative adversarial network-squeeze and excitation-based framework security

来源：评论

学校读者我要写书评

暂无评论

Anomalies in light scattering: A circuit-model approach

引用

Physical Review Applied 2024年第3期22卷 034061页

作者： Deepanshu Trivedi Arjuna Madanayake Alex Krasnok Department of Electrical and Computer Engineering Knight Foundation School of Computing and Information Sciences

Photonics is crucial for communication and computing, as it involves controlling how light scatters. Recent breakthroughs like bound states in the continuum (BICs) and parity-time-symmetric systems are linked to the scattering matrix, governed by passivity and causality. However, using complex-frequency excitations overcomes these limitations, allowing us to study systems with losses or gains and discover phenomena like virtual critical coupling and virtual gain. Applying complex-frequency-excitation concepts to more complicated systems is challenging. In this work, we extend the lumped-element model from circuit theory to analyze light-scattering anomalies in the complex-frequency domain. This approach helps us design and understand effects such as virtual perfect absorption, BICs, real and virtual critical coupling, exceptional points, and anisotropic transmission resonances. These insights broaden our knowledge of electromagnetic wave phenomena and open possibilities in photonics, offering innovative ways to create and optimize optical devices and systems for various applications.

关键词： Classical optics Light propagation, transmission & absorption Light-matter interaction Photonics Scattering theory Wave scattering Non-Hermitian systems Light scattering

来源：评论

学校读者我要写书评

暂无评论

Maximizing Profit of the Service Providers through Efficient Content Placement and Retrieval in an IoT-enabled Edge-Cloud Platform 18

Maximizing Profit of the Service Providers through Efficient...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Gandhi, Preet Mahanta, Abhishriya Ghose, Manojit Sahu, Aryabartta Indian Institute of Technology Department of Computer Science and Engineering Guwahati India Indian Institute of Technology School of Computing and Electrical Engineering Mandi India Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798350391725

In today's 5G era, the amount of data generated by the Internet of Things (IoT) devices is enormous. Data is processed and stored in the cloud under a traditional cloud computing architecture, and real-time processing and retrieval of these data is time-consuming. Therefore, an edge-cloud framework comes in handy where the content generated is placed on the edge nodes of the network, and it can reach the endusers in a time-bound manner. A majority of the previous research works on content placement under the edge-cloud architecture primarily aimed at improving the latency of the system. However, the approach proposed in this paper aims to maximize the profit of the service provider by effectively placing the content in a hierarchically organized edge-cloud network. We propose two strategies and compare them with random and greedy approaches for both synthetic and real data sets. The experimental results demonstrate the effectiveness of the proposed strategies, and the profit of the service providers increases by 38.81% (maximum) and 10.51% (on average) for the synthetic dataset and by 65.74% (maximum) and 22.83% (on average) for the real-world dataset when compared with the greedy approach. © 2024 IEEE.

关键词： Cloud platforms

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：