检索结果-内蒙古大学图书馆

2024 Ieee Global Communications Conference, GLObeCOM 2024

作者： Yu, Yantao Guan, Yunguo Xue, Xiaoping Lu, Rongxing Tongji University College of Electronic and Information Engineering Shanghai201804 China Eastern Michigan University School of Information Security and Applied Computing YpsilantiMI48197 United States University of New Brunswick Faculty of Computer Science FrederictionNBE3B 5A3 Canada

ISBN: (纸本)9798350351255

Aggregation query, which is one of the most crucial data analysis tools applied to vehicular crowdsensed data, is expected to extract valuab.e.insights and support smart decision-making. Meanwhile, the edge servers are deployed to cope with the escalation of service scale, which however raises privacy concerns about the query requests and reported data. Previously reported privacy-preserving aggregation query schemes are either tailored for static datasets or lack an index structure for deployed queries, which makes them impractical in vehicular crowdsensing (VCS) scenarios characterized by large volumes of real-time data and high data update frequencies. To tackle these challenges, we propose an efficient privacy-preserving edge-based dynamic aggregation query scheme with an encrypted tree-based index. Concretely, we first design two building blocks, namely the balanced spatial encoding quadtree (b.e.tree) and a predicate encryption scheme for membership testing (PeMT), which enab.e.the edge servers to obliviously match data and queries by traversal over the encrypted b.e.tree. based on the above blocks and arithmetic secret sharing (ASS), we construct our scheme, in which the edge servers can efficiently and securely aggregate newly reported data to related query results. Our security analysis shows the privacy preservation of our scheme, and the experiment results on a real dataset validate the efficiency of our scheme. © 2024 Ieee.

关键词： Data aggregation

来源：评论

学校读者我要写书评

暂无评论

AN AUTOeNCODeR AND GeNeRATIVe ADVeRSARIAL NeTWORKS APPROACH FOR MULTI-OMICS DATA IMbALANCeD CLASS HANDLING AND CLASSIFICATION

arXiv

引用

arXiv 2024年

作者： Al-Hurani, Ibrahim Alkhateeb, Abedalrhman Ikki, Salama Lakehead University Department of Electrical and Computer Engineering Thunder BayONP7B 5E1 Canada Lakehead University Department of Computer Science Thunder BayONP7B 5E1 Canada

In the relentless efforts in enhancing medical diagnostics, the integration of state-of-the-art machine learning methodologies has emerged as a promising research area. In molecular biology, there has b.e. an explosion of data generated from multi-omics sequencing. The advent sequencing equipment can provide large number of complicated measurements per one experiment. Therefore, traditional statistical methods face challenging tasks when dealing with such high dimensional data. However, most of the information contained in these datasets is redundant or unrelated and can be effectively reduced to significantly fewer variab.e. without losing much information. Dimensionality reduction techniques are mathematical procedures that allow for this reduction;they have largely b.e. developed through statistics and machine learning disciplines. The other challenge in medical datasets is having an imbalanced number of samples in the classes, which leads to biased results in machine learning models. This study, focused on tackling these challenges in a neural network that incorporates autoencoder to extract latent space of the features, and Generative Adversarial Networks (GAN) to generate synthetic samples. Latent space is the reduced dimensional space that captures the meaningful features of the original data. Our model starts with feature selection to select the discriminative features before feeding them to the neural network. Then, the model predicts the outcome of cancer for different datasets. The proposed model outperformed other existing models by scoring accuracy of 95.09% for bladder cancer dataset and 88.82% for the b.e.st cancer dataset. © 2024, CC bY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A study on Cloud enab.e. Applications and their Security Issues 11

A study on Cloud enabled Applications and their Security Iss...

引用

11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020

作者： Mody, Vidhi Mody, Vrushti Parekh, Soham B.Tech. Computer Engineering Mukesh Patel School of Technology Management and Engineering NMIMS India B.E. Computer Engineering Dwarkadas Jivanlal Sanghvi College of Engineering India

ISBN: (纸本)9781728168517

Cloud computing was first established to connect people and data at anytime from anywhere in the 1960s. Today cloud computing is one of the most widely used technologies. Its applications include Multi-cloud, healthcare, testing, finance, data storage and handling big data to increase efficiency and how it differs from traditional systems. We have stated how cloud computing can be used in various domains and have compared its efficiency to traditional systems in terms of data recovery, access control, management, security and cost. However, like any other technology, this one too might have flaws which can be exploited. This paper also lists the security challenges that will have to be kept in mind while implementing these systems. © 2020 Ieee.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Secure Transmission Design for Aerial IRS Assisted Wireless Networks

Secure Transmission Design for Aerial IRS Assisted Wireless ...

引用

作者： Wei, Wenjing Pang, Xiaowei Tang, Jie Zhao, Nan Wang, Xianbin Nallanathan, Arumugam Dalian University of Technology School of Information and Communication Engineering Dalian116024 China South China University of Technology School of Electronic and Information Engineering Guangzhou510640 China Western University Department of Electrical and Computer Engineering LondonONN6A 5B9 Canada Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom

Combining intelligent reflecting surface (IRS) and unmanned aerial vehicle (UAV) offers a new degree of freedom to improve the coverage performance. However, it is more challenging to secure the air-ground transmission, due to the line-of-sight (LoS) links established by UAV. Since IRS is a promising solution for wireless environment reconfiguration, in this paper, we propose an aerial IRS-assisted secure transmission design in wireless networks. In particular, an access point (AP) equipped with a uniform planar array serves several single-antenna legitimate users in the presence of multiple single-antenna eavesdroppers, whose precise positions are unknown. An IRS is mounted on the UAV to help establish desired virtual LoS links between the AP and legitimate users, while ensuring their security. We aim to maximize the worst-case sum secrecy rate by jointly optimizing the hovering position of UAV, the transmit beamforming of AP and the phase shifts of IRS, sub.e.t to the requirement of minimum rate for legitimate users. To tackle this non-convex prob.e., we first decompose it into three subprob.e.s, which are transformed into convex ones via successive convex approximation. An alternating algorithm is then proposed to solve them iteratively. Simulation results show the effectiveness of the proposed scheme and the security improvement by the joint optimization. © 1972-2012 Ieee.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

backdoor Attacks against Image-to-Image Networks

arXiv

引用

arXiv 2024年

作者： Jiang, Wenbo Li, Hongwei He, Jiaming Zhang, Rui Xu, Guowen Zhang, Tianwei Lu, Rongxing The School of Computer Science and Engineering University of Electronic Science and Technology of China China The School of Computer Science and Cyber Security Chengdu University of Technology China City University of Hong Kong Hong Kong The School of Computer Science and Engineering Nanyang Technological University Singapore The Faculty of Computer Science University of New Brunswick FrederictonNBE3B 5A3 Canada

Recently, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks such as image super-resolution and denoising. Despite their remarkab.e.performance, the backdoor vulnerability of I2I networks has not b.e. explored. To fill this research gap, we conduct a comprehensive investigation on the susceptibility of I2I networks to backdoor attacks. Specifically, we propose a novel backdoor attack technique, where the compromised I2I network behaves normally on clean input images, yet outputs a predefined image of the adversary for malicious input images containing the trigger. To achieve this I2I backdoor attack, we propose a targeted universal adversarial perturbation (UAP) generation algorithm for I2I networks, where the generated UAP is used as the backdoor trigger. Additionally, in the backdoor training process that contains the main task and the backdoor task, multitask learning (MTL) with dynamic weighting methods is employed to accelerate convergence rates. In addition to attacking I2I tasks, we extend our I2I backdoor to attack downstream tasks, including image classification and ob.e.t detection. extensive experiments demonstrate the effectiveness of the I2I backdoor on state-of-the-art I2I network architectures, as well as the robustness against different mainstream backdoor defenses. Copyright © 2024, The Authors. All rights reserved.

关键词： Ob.e.t detection

来源：评论

学校读者我要写书评

暂无评论

enhancing Wireless Sensor Network Longevity and Security: A Quad-LeACH Approach

Enhancing Wireless Sensor Network Longevity and Security: A ...

引用

emerging Technologies in computer science for Interdisciplinary Applications (ICeTCS), International Conference on

作者： J J Lohith S Shreya J L Hamsa Priya Dept. of Computer Science and Engineering B.M.S. College of Engineering Bangalore India Dept. of Information Science and Engineering D.S.C.E. Bangalore India Dept. of Electronics and Telecommunications B.M.S. College of Engineering Bangalore India

ISBN: (数字)9798350372502

ISBN: (纸本)9798350372519

Researchers have increasingly focused on Wireless Sensor Networks (WSNs) in recent years, recognizing their versatile applications. The primary focus within WSNs is enhancing network longevity for efficient resource utilization, coupled with a strong emphasis on security and authentication. This paper specifically delves into the implementation of Quad LeACH for homogeneous networks, aiming to substantially improve network lifetime, stability, and throughput. The proposed protocol achieves this by employing a cluster head selection process and integrating security and authentication measures between cluster heads in the Quad-LeACH routing protocol. The research addresses the integration of a security agent within WSNs using the NS-2 tool, contributing to enhanced authentication. The implementation is carried out through the simulation software NS 2, where the security agent is seamlessly combined with the WSN infrastructure. The ob.e.tive of this research is to incorporate a reliab.e.authentication and security agent into NS-2 in conjunction with the LeACH protocol, which is the standard for wireless sensors networks (WSNs). The efficacy of the suggested methodology will be validated through simulated outcomes.

关键词： Wireless sensor networks Authentication Throughput Stability analysis Software Routing protocols Software reliability

来源：评论

学校读者我要写书评

暂无评论

Unlocking efficiency in Agricultural Supply Chains: A Secure and Transparent Approach through blockchain Technology

Unlocking Efficiency in Agricultural Supply Chains: A Secure...

引用

emerging Technologies in computer science for Interdisciplinary Applications (ICeTCS), International Conference on

作者： J J Lohith S Shreya J L Hamsa Priya Dept. of Computer Science and Engineering B.M.S. College of Engineering Bangalore India Dept. of Information Science and Engineering D.S.C.E Bangalore India Dept. of Electronics and Telecommunications B.M.S. College of Engineering Bangalore India

ISBN: (数字)9798350372502

ISBN: (纸本)9798350372519

Supply Chain Management (SCM) involves orchestrating various processes that extend from acquiring raw materials to delivering finished products to end consumers. The key ob.e.tives of a proposed supply chain in agriculture, emphasizes information-driven processes, cost reduction, and customer impact. It creates a versatile system capab.e.of managing the supply chain for diverse commodities within a country, while also addressing the crucial need for increased transparency and traceability in data throughout the chain of activities. In our proposed approach to agricultural supply chain management (SCM), the focus is on creating a secure, transparent, and traceab.e.SCM. To achieve this, we leverage cutting-edge technologies like the ethereum blockchain and the Interplanetary File System (IPFS). The resulting software is a Decentralized Application (DApp) that orchestrates a series of activities within the agricultural industry, using cryptocurrencies to establish a seamless and efficient supply chain management system. This software platform is fortified by the secure algorithms of blockchain, providing an added layer of reliability. Additionally, our application incorporates transparency and traceability, ensuring user-friendly functionality and making it more accessib.e.for users.

关键词： Supply chain management Costs Supply chains Software algorithms Decentralized applications Software blockchains

来源：评论

学校读者我要写书评

暂无评论

employing a deep learning technique to categorize Internet of Things (IoT) traffic in a smart city context

Employing a deep learning technique to categorize Internet o...

引用

2023 Ieee International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATe 2023

作者： Anu Priya, S. Rajesh kanna, b. beaulah Jeyavathana, R. bhat, Niyati Rajalakshmi, S. Srimathi, S. Chennai600117 India Department of Electronics and Communication Engineering Alagappa Chettiyar College of Engineering and Technology Karaikudi India Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai India B.E Computer Engineering University of Mumbai Mumbai India Department of Electronics and Communication Engineering RMK College of Engineering and Technology India Department of Bio Technology Saveetha School of Engineering SIMATS Tamilnadu Chennai India

ISBN: (纸本)9798350305708

The exponential increase in quantity of cars on the roads of smart cities has led to traffic jams, air contamination, and delays in the delivery of essential goods. every day road accidents continue to be a leading cause of death and serious injury. The Internet of Things-based Traffic Management System is utilized to manage traffic flow, ensure safe data transfer, and spot accidents. Autonomous vehicles and smart devices have sensors built into an IoT-based ITM system to help with identification, data collection, and transmission. Connectivity options for the Internet of Things are being severely tested by the proliferation of IoT devices and applications. This can lead to severe difficulties in the allocation of the spectrum, the resources needed to analyze the IoT data, and the allowab.e.delay for important spare situations throughout the end-to-end communication chain. Therefore, accurate categorization or forecasting of the IoT devices' time-varying traffic characteristics is essential. However, the difficulty of making this sort of categorization remains open. Current approaches tend to be based on machine learning methods, which have a high computational cost despite not taking into account the traffic's fine-grained flow features. In this research, we address this issue by developing a two-stage categorization system based on deep learning for IoT devices in a smart city that draws on both connectivity and statistical information. In order to excerpt the internet and statistical characteristics set for various IoT strategies, we must do data cleaning and preprocessing. based on the results of the tests, it appears that the proposed categorization has a 99% chance of being correct. © 2023 Ieee.

关键词： Autonomous Vehicle Deep Learning IoT Traffic Data Smart-City Traffic Management

来源：评论

学校读者我要写书评

暂无评论

Sensing of precipitation using laser radar

Sensing of precipitation using laser radar

引用

Propagation Through and Characterization of Atmospheric and Oceanic Phenomena, pcDVT 2021 - Part of OSA Imaging and Applied Optics Congress 2021

作者： Dave, Pranjal Yellapragada, bhavani Kumar Birla Institute of Technology and Science B.E. Electrical and Electronics Engineering Pilani Campus Pilani333031 India National Atmospheric Research Laboratory Department of Space Lidar Project Tirupati517502 India

We conducted laser radar measurements of the atmosphere during a strong thunderstorm condition over a tropical site in India. The laser radar was operated in the slant direction and has detected variability in precipi... 详细信息

ISBN: (纸本)9781557528209

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Automatic Plane Pose estimation for Cardiac Left Ventricle Coverage estimation via Deep Adversarial Regression Network

IEEE Transactions on Artificial Intelligence

引用

Ieee Transactions on Artificial Intelligence 2024年第9期5卷 4738-4752页

作者： Zhang, Le bronik, Kevin Piechnik, Stefan K. Lima, Joao A. C. Neubauer, Stefan Petersen, Steffen e. Frangi, Alejandro F. University of Birmingham School of Engineering College of Engineering and Physical Sciences BirminghamB15 2TT United Kingdom University of Oxford Department of Engineering Science OxfordOX1 3PJ United Kingdom Division of Cardiovascular Medicine OxfordOX3 9DU United Kingdom Johns Hopkins University School of Medicine Division of Cardiology BaltimoreMD21287 United States Queen Mary University of London Centre for Cardiovascular Medicine The William Harvey Research Institute LondonE1 1BB United Kingdom Barts Health Nhs Trust Barts Heart Center LondonE1 1BB United Kingdom The University of Manchester Division of Informatics Imaging and Data Science School of Health Sciences The Department of Computer Science School of Engineering ManchesterM13 9PL United Kingdom

Accurate segmentation of the ventricles plays a crucial role in determining cardiac functional parameters such as ventricular volume, ventricular mass, and ejection fraction. However, poor image quality, such as inadequate coverage of the left ventricle (LV) and right ventricle (RV) in cardiac magnetic resonance (CMR) image sequences, can significantly affect the assessment of cardiac function. This study investigates issues related to missing or corrupted imaging planes, which often lead to incomplete ventricle coverage. To address the challenge of estimating ventricle coverage in CMR images regardless of variations in imaging parameters such as device type, magnetic field strength, and protocol execution, we introduce a novel convolutional neural network (CNN) based on adversarial learning. Additionally, we integrate supplementary information (e.g., cross-view image data) as privileged information to enhance the interpretability of our model's predictions and identify potential biases or inaccuracies. This research represents the first attempt to automatically estimate ventricular coverage by identifying missing slices and plane orientations in CMR images using a dataset-agnostic approach. The effectiveness of the proposed model is demonstrated through the evaluation of datasets from three diverse and sizab.e.image acquisition cohorts, demonstrating superior performance compared to existing methods. © 2020 Ieee.

关键词： Image quality

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：