检索结果-内蒙古大学图书馆

2nd International Conference on computing and Data Analytics, ICCDA 2024

作者： Palarimath, Suresh Maran, Pyingkodi Wilfred Blessing, N.R. Kavitha, S.J. Cibi, A. Sutherlin, Subitha G. College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Oman Kongu Engineering College Department of Computer Applications Erode India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Computer Science and Engineering Pallavaram Chennai India Virtusa Consulting Services Private Limited Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Kanyakumari India

ISBN: (纸本)9798331542573

The growing occurrence of cybersecurity hazards, such as Android zero-day vulnerabilities, poses substantial difficulties because they are unattended and imperceptible. With the increasing popularity of Android smartphones, hackers are taking advantage of these weaknesses to quickly spread advanced malware. Conventional detection approaches frequently prove inadequate due to the absence of shown criteria for emergent threats. In order to address this crucial problem, this article presents the Zero-Vuln method, an advanced technique specifically developed to identify and categorize previously unidentified malware on Android platforms. Zero-Vuln combines sophisticated supervised deep learning methods with zero-shot learning algorithms to accurately detect zero-day threats. Through the utilization of comprehensive datasets, the method attains an average classification metric score of 84.22%, showcasing exceptional accuracy, precision, and recall. This advanced solution significantly improves the ability to identify and handle Android zero-day threats, representing a major progress in cybersecurity research and implementation. The Zero-Vuln strategy provides a strong and adaptable solution for the constantly changing mobile security risks, representing a notable advancement in the sector. © 2024 IEEE.

关键词： Zero-shot learning

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

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

Ruppert's Delaunay Triangulation Refinement Scheme for Optimal RSUs Placement in Vehicle to Infrastructure Communication Network

引用

China Communications 2023年第7期20卷 303-320页

作者： Selvakumari P Chinnasamy A Sree Rathna Lakshmi NVS Sheela D Department of Computer Science and Engineering Tagore Engineering CollegeChennai 600048India Department of Data Science and Business Systems School of ComputingSRMIST kattankulathur CampusChennai 603203India Department of Electronics and Communication Engineering Department of ECE at Agni College of TechnologyChennai 603103India Department of Electronics and Communication Engineering Saveetha School of Engineering SIMATSChennai 600124India

Road Side Units(RSUs)are the essential component of vehicular communication for the objective of improving safety and mobility in the road *** are generally deployed at the roadside and more specifically at the intersections in order to collect traffic information from the vehicles and disseminate alarms and messages in emergency situations to the neighborhood vehicles cooperating with the ***,the development of a predominant RSUs placement algorithm for ensuring competent communication in VANETs is a challenging issue due to the hindrance of obstacles like water bodies,trees and *** this paper,Ruppert’s Delaunay Triangulation Refinement Scheme(RDTRS)for optimal RSUs placement is proposed for accurately estimating the optimal number of RSUs that has the possibility of enhancing the area of coverage during data *** RDTRS is proposed by considering the maximum number of factors such as global coverage,intersection popularity,vehicle density and obstacles present in the map for optimal RSUs placement,which is considered as the core improvement over the existing RSUs optimal placement *** is contributed for deploying requisite RSUs with essential transmission range for maximal coverage in the convex map such that each position of the map could be effectively covered by at least one RSU in the presence of *** simulation experiments of the proposed RDTRS are conducted with complex road traffic *** results of this proposed RDTRS confirmed its predominance in reducing the end-to-end delay by 21.32%,packet loss by 9.38%with improved packet delivery rate of 10.68%,compared to the benchmarked schemes.

关键词： road side units(RSUs) ruppert’s delau-nay triangulation refinement area of global coverage optimal RSUs placement

来源：评论

学校读者我要写书评

暂无评论

Decentralized Private Peer-to-Peer Energy Trading using Public Blockchains 4

Decentralized Private Peer-to-Peer Energy Trading using Publ...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Mansour, Sandra Kamal, Naheel Faisal Texas A&M University at Qatar Qatar Foundation Department of Electrical and Computer Engineering Doha Qatar Texas A&M University Electrical and Computer Engineering Department College Station United States

ISBN: (纸本)9798350306262

Peer-to-Peer (P2P) energy trading is a decentralized system that allows consumers and prosumers to trade energy without the need of a third party. P2P energy trading could be integrated to create a smart market within smart grid to form a decentralized energy trading platform. Such energy trading approach promotes consumers to become prosumers. The objective of this research is to create a secure and private P2P energy trading system using a public blockchain. This research reviews different approaches of energy trading and blockchain technologies. Then, a novel blockchain-based trading model is proposed to construct the system. The proposed energy trading model is implemented using Ethereum's blockchain and smart contracts. Simulation and experimental analyses are performed to show that the proposed methodology is reliable, safe, and secure for energy trading. © 2024 IEEE.

关键词： Blockchain

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

Analysis of Encryption Techniques for Secure Data in Cloud Environment 1

Analysis of Encryption Techniques for Secure Data in Cloud E...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Kumar, M. Ravi Jeya, I. Jasmine Selvakumari Athira, S. Hindusthan College of Engineering and Technology Department of Computer Science And Engineering Coimbatore India Vit Bhopal University School of Computing Science and Engineering Sehore India Hindusthan College of Engineering and Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798331529246

Over the years, Cloud computing is becoming increasingly popular due to the continually changing technology. The primary goal of the cloud computing network is to offer consumers pay-per-use usage of on-demand processing and storage resources, enabling low-cost, efficient infrastructure utilization for smaller businesses. However, because of the feature of cloud resource sharing, data security and privacy create issues, and prevent smart systems from continuously transferring produced data to the cloud computing resources. Many encryption methods were presented to address data security concerns. This article presents the processes of several data protection and encryption systems currently in use and critically analyzes them based on common factors. The purpose of this survey is to compile data encryption methods now in use, often discussed in the survey of smart systems for data security when applied to the cloud platforms. © 2025 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

SARP: Spatial Agnostic Radio Fingerprinting with Pseudo-Labeling 22

SARP: Spatial Agnostic Radio Fingerprinting with Pseudo-Labe...

引用

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

All-photonic artificial-neural-network processor via nonlinear optics

引用

Physical Review Applied 2024年第1期22卷 014009-014009页

作者： Jasvith Raj Basani Mikkel Heuck Dirk R. Englund Stefan Krastanov Department of Electrical and Electronics Engineering Department of Electrical and Computer Engineering Institute for Research in Electronics and Applied Physics and Department of Electrical Engineering and Computer Science Department of Electrical and Photonics Engineering College of Information and Computer Sciences

Optics and photonics have recently captured interest as a platform to accelerate linear matrix processing, otherwise a bottleneck in traditional digital electronics. In this paper we propose an all-photonic computational accelerator wherein information is encoded in the amplitudes of frequency modes stored in a single ring resonator. Interaction among these modes is enabled by nonlinear optical processes. Both the matrix multiplication and elementwise activation functions on these modes (the artificial neurons) are performed through coherent processes, enabling the direct representation of negative and complex numbers without having to pass through digital electronics, a common limitation in today’s photonic architectures. This design also has a drastically lower hardware footprint compared with today’s electronic and optical accelerators, as the entirety of the matrix multiplication happens in a single multimode resonator on chip. Our architecture is unique in providing a completely unitary, reversible mode of computation, enabling on-chip analog Hamiltonian-echo backpropagation for gradient descent and other self-learning tasks. Moreover, the computational speed increases with the power of the pumps to arbitrarily high rates, as long as the circuitry can sustain the higher optical power. Lastly, the design presented here is a less demanding version of a future room-temperature quantum computational device. Therefore, while this architecture is already viable today, direct reinvestments in it would be enabling its evolution into quantum computational hardware.

关键词： Machine learning Neuromorphic computing Nonlinear optics Photonics Artificial neural networks Deep learning Neural network simulations Optical computing

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

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：