检索结果-内蒙古大学图书馆

5th International Conference on engineering technology and its Applications, IICETA 2022

作者： Hassan, Mustafa Hamid Abbas, Ali Hashim Mutar, Mohammed Hasan Jubair, Mohammed Ahmed Rashid, Sami Abduljabbar Ahmed, Ahmed Jamal Habelalmateen, Mohammed I. Mohammed, Aymen Audah, L. College of Information Technology Imam ja'Afar Al-Sadiq University Department of Computer Technical Engineering Al-Muthanna 66002 Iraq Al-Maarif University College Department of Computer Engineering Techniques Al-Anbar Iraq College of Technical Engineering Islamic University Department of Computer Technical Engineering Najaf54001 Iraq Al-Farahidi University Engineering Technical College Baghdad Iraq Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Batu Pahat Malaysia

ISBN: (纸本)9781665472159

In recent years, new networking paradigms such as Vehicular Ad Hoc Network (VANET), Flying Ad-hoc Networks (FANETs), and SEANETs have emerged as a result of Mobile Ad-Hoc Networks (MANETs). UAVs are gaining popularity as they are used in large-scale real-time applications. When UAVs are linked together, they form a FANET, which works collectively and in the most efficient manner possible. FANETs are designed to be used in a wide range of missions and rapidly changing scenarios. As a result, given the nature of the applications and services used to deploy UAVs, efficient routing protocols are essential. Other routing protocols, on the other hand, have been developed to date, each with its own set of limitations. This research investigates the AODV, DSDV, and AOMDV routing protocols in the context of a FANET. In terms of delay, the DSDV exceeds the other protocols, whereas the AOMDV outperforms the others in terms of average TP and PDR. © 2022 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Bilateral Multi-Subarray Padded Coprime Array Configuration for DOA Estimation in MIMO Radar

引用

IEEE Transactions on Vehicular technology 2025年

作者： Chen, Hua Li, Jiajie Yang, Songjie Liu, Wei Yuen, Chau So, Hing Cheung Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu610054 China The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Kowloon Hong Kong Nanyang Technological University School of Electrical and Electronics Engineering 639798 Singapore Department of Electrical Engineering City University of Hong Kong Hong Kong

Simultaneous consideration of uniform degrees of freedom (uDOF) and mutual coupling is a key focus in sparse array design. To reduce mutual coupling and increase degrees of freedom (DOF), a bilateral multi-subarray coprime array (BMSCA) is proposed with its specific hole locations in the difference co-array (DCA). To address the holes in the central DCA, an additional subarray is incorporated, resulting in the bilateral multi-subarray padded coprime array (BMSPCA), which substantially increases both DOF and uDOF. Additionally, the first three weight functions and the optimal structure are determined for BMSPCA. As an application, BMSPCA is applied to multiple-input multiple-output (MIMO) radar with sum-difference co-array, where the holes in DCA and virtual sparse sensors can be divided into similar layers and exhibit symmetry;specific sparse arrays that exhibit similar symmetrical properties are then identified, which can fundamentally enhance the uDOF of MIMO radar. Simulation results demonstrate the superior performance of both the proposed array and the sparse MIMO array in scenarios with strong mutual coupling. © 1967-2012 IEEE.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning Approach for Enhanced Vulnerability Detection in Cloud Environments Using NIST and MITRE Frameworks

Hybrid Machine Learning Approach for Enhanced Vulnerability ...

引用

Advanced Research in Computing (ICARC), International Conference on

作者： N W Chanaka Lasantha M W P Maduranga Ruvan Abeysekara Valmik Tilwari Nilotpal Chakraborty Debashree Sharma Faculty of Graduate Studies IIC University of Technology Phnom Penh Cambodia Department of Electrical and Electronic Engineering University of Sri Jayewardenepura Nugegoda Sri Lanka Faculty of Computing BCAS Campus Colombo Sri Lanka Department. of Electronics & Communication Engineering Indian Institute of Information Technology Guwahati India Department of Computer Science Engineering Indian Institute of Information Technology Guwahati India Department of Electronics & Communication Engineering Indian Institute of Information Technology Guwahati India

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

Cloud security is challenged by constant adaptive cyber threats and traditional detection methods lack real time adaptability. In this paper, we propose a new hybrid ML approach stitching data from National Institute of Standards and technology (NIST) and MITRE Adversarial Tactics, Techniques and Common Knowledge (ATT&CK) databases together. In contrast to existing methods, this framework combines, in unique and unprecedented fashion, ensemble ML models and Realtime data processing for increased detection accuracy and reduced false positives. This approach addresses specific challenges in the cloud environments and by leveraging standardised frameworks, it offers actionable audiences for efficient and effective vulnerability management process. The framework is validated by the experimental results which prove its robustness to evolution of the cybersecurity demands.

关键词： Adaptation models Accuracy Cloud computing security Scalability NIST Transformers Data models Threat assessment Robustness Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Automated Attendance Tracking System Through Deep Learning Methods 8

Automated Attendance Tracking System Through Deep Learning M...

引用

8th IET Smart Cities Symposium, SCS 2024

作者： Ang, E-Hui Vijean, Vikneswaran Palaniappan, Rajkumar Ravindran, Sindhu Chin, Lim Chee Abdullah, Rokiah Yogesh, C.K. Faculty of Electronic Engineering & Technology Universiti Malaysia Perlis Kampus Induk Pauh Putra Pauh Perlis Malaysia Department of Mechatronics Engineering University of Technology Bahrain Building 829 Road 1213 Block 712 Salmabad Bahrain Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus India

ISBN: (纸本)9781837242672

The recent outbreak of the COVID-19 pandemic in 2020 underscored the necessity of face recognition systems, particularly in industrial environments for attendance tracking. However, traditional approaches struggle with masked faces. This study aimed to develop robust segmentation and feature extraction algorithms to identify salient facial features and create an accurate classification system for attendance tracking despite mask-wearing. A dataset of 26 subjects was captured using a Raspberry Pi camera. Images were preprocessed, cropped, resized to 224x224 pixels, and augmented. An 80:10:10 split was used for training, validation and testing. Three deep learning models - AlexNet, ResNet 101 and MobileNet v3 - were evaluated. AlexNet achieved the highest performance, with 95.83% training, 94.23% validation and 74% testing accuracy, outperforming the others. A GUI was developed based on the trained AlexNet model for attendance recording. The results demonstrate the effectiveness of deep learning, particularly AlexNet, for face recognition in industrial settings with mask-wearing. © The Institution of engineering & technology 2024.

关键词： Deep learning

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 remarkable performance, the backdoor vulnerability of I2I networks has not been 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 object 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： Object detection

来源：评论

学校读者我要写书评

暂无评论

Theory and Practice for Trajectory Tracking of Quadrotor UAV Via a Fifth Generation Sliding Mode Approach 6

Theory and Practice for Trajectory Tracking of Quadrotor UAV...

引用

6th International Conference on Networking and Advanced Systems, ICNAS 2023

作者： Mechali, Omar Messaoui, Ali Zakaria Senouci, Abdelkader Messaoui, Aimen Abdelhak Mechali, Abdesselam Petru, Jana Ecole Superieure Ali Chabati Reghaia Algeria School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Ecole Militaire Poly Technique Laboratoire de Commande des Systèmes Complexes et Simulateurs Bordj El-Bahri Algeria University of Hull Faculty of Science and Engineering Department of Computer Science and Technology HU6 7RX United Kingdom VSB-Technical University of Os Trava Faculty of Mechanical Engineering Department of Machining Assembly and Engineering Metrology Ostrava70800 Czech Republic

ISBN: (纸本)9798350319170

This paper presents an effective approach for a quadrotor during trajectory tracking seeking fixed-Time stabilization and disturbance rejection. The quadrotor is modeled by Ordinary Differential Equations (ODE) while considering lumped disturbances. Theoretical control design and practical implementation are addressed in the paper. Motivated by the variable structure systems in the form of Sliding Mode Control (SMC) theory and homogeneous systems theory, a homogeneous-SMC-based flight control is proposed to achieve robust trajectory tracking along fixed-Time stability. First, a Homogeneous Nonlinear Chattering-Free Terminal Sliding Manifold (HNCFTSM) is synthesized. Second, a Fifth Generation-based Fixed-Time SMC (FGFTSMC) is derived based on the designed HNCFTSM and an appropriate reaching law. Moreover, to suppress the disturbances polluting the system's dynamics, the control scheme is designed within an ADRC approach. The control design and the stability analysis show that the tracking errors are guaranteed to be fixed-Time stable at the equilibrium point without being affected by the deviation of the Initial Conditions (ICs) from the origin. Outdoor flight experiments and comparative analysis are drawn to corroborate the findings of this note. The depicted outcomes approve the effectiveness of the suggested controller in the form of chattering alleviation, disturbance rejection, and uniform fast fixed-Time convergence. © 2023 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Communication Efficient ConFederated Learning: An Event-Triggered SAGA Approach

arXiv

引用

arXiv 2024年

作者： Wang, Bin Fang, Jun Li, Hongbin Eldar, Yonina C. The National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu611731 China The Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ07030 United States The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

Federated learning (FL) is a machine learning paradigm that targets model training without gathering the local data dispersed over various data sources. Standard FL, which employs a single server, can only support a limited number of users, leading to degraded learning capability. In this work, we consider a multi-server FL framework, referred to as Confederated Learning (CFL), in order to accommodate a larger number of users. A CFL system is composed of multiple networked edge servers, with each server connected to an individual set of users. Decentralized collaboration among servers is leveraged to harness all users’ data for model training. Due to the potentially massive number of users involved, it is crucial to reduce the communication overhead of the CFL system. We propose a stochastic gradient method for distributed learning in the CFL framework. The proposed method incorporates a conditionally-triggered user selection (CTUS) mechanism as the central component to effectively reduce communication overhead. Relying on a delicately designed triggering condition, the CTUS mechanism allows each server to select only a small number of users to upload their gradients, without significantly jeopardizing the convergence performance of the algorithm. Our theoretical analysis reveals that the proposed algorithm enjoys a linear convergence rate. Simulation results show that it achieves substantial improvement over state-of-the-art algorithms in terms of communication efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Classification using Vision Transformer with Selective Cross-Attention Mechanism and Feature Calibration

arXiv

引用

arXiv 2024年

作者： Khaniki, Mohammad Ali Labbaf Mirzaeibonehkhater, Marzieh Manthouri, Mohammad Hasani, Elham Faculty of Electrical Engineering K.N. Toosi University of Technology Tehran Iran Department of Electrical and Computer Engineering Indiana University Purdue University United States Faculty of Electrical and Electronic Engineering Shahed university Tehran Iran Department of Chemical and Environmental Engineering University of Cincinnati CincinnatiOH45221 United States

Brain tumor classification is a challenging task in medical image analysis, with significant implications for patient diagnosis and treatment. The objective of this paper is to propose a novel approach to brain tumor classification using a Vision Transformer (ViT) with a novel cross-attention mechanism. Our approach leverages the strengths of transformers in modeling long-range dependencies and multi-scale feature fusion. We introduce two new mechanisms to improve the performance of the cross-attention fusion module: Feature Calibration Mechanism (FCM) and Selective Cross-Attention (SCA). FCM calibrates the features from different branches to make them more compatible, while SCA selectively attends to the most informative features. Our experimental results demonstrate that the proposed approach outperforms other state-of-the-art methods, including Convolutional Neural Networks (CNN), ViT, and Cross-attention ViT, achieving an accuracy of 98.93% and an F1-score of 98.83%. Furthermore, the addition of Stochastic Depth mechanism improves the accuracy to 99.24% and the F1-score to 99.23%. The proposed FCM and SCA mechanisms can be easily integrated into other ViT architectures, making them a promising direction for future research in medical image analysis. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Social Withdrawal Symptoms in Control and Ketum Dependent Subjects 8

Comparative Study of Social Withdrawal Symptoms in Control a...

引用

8th IET Smart Cities Symposium, SCS 2024

作者： Shafawi, Nur Hanani Adzha Vijean, Vikneswaran Palaniappan, Rajkumar Ravindran, Sindhu Chin, Lim Chee Abdullah, Rokiah Yogesh, C.K. Faculty of Electronic Engineering & Technology Universiti Malaysia Perlis Kampus Induk Pauh Putra Pauh Perlis Malaysia Department of Mechatronics Engineering University of Technology Bahrain Building 829 Road 1213 Block 712 Salmabad Bahrain Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus India

ISBN: (纸本)9781837242672

Derived from the Mitragyna speciosa tree, ketum is renowned for its addictive qualities and hallucinogenic effects. Using electroencephalogram (EEG) data, this study compares the social withdrawal symptoms—specifically, depression, irritability, and restlessness—between control and ketum-dependent people. After pre-processing the EEG data, the Dual-Tree Complex Wavelet Transform (DT-CWT) was used to extract features. The study employed statistical analyses, namely the two-sample t-tests, to determine significant differences between the groups and to develop indices for social withdrawal symptoms. To verify the distinction between social withdrawal symptoms, classification models such as Coarse Decision Tree, Logistic Regression, and Cubic K-Nearest Neighbor (KNN) were utilized. The EEG patterns of the control and ketum subjects differed significantly, according to the results, with Task 1 exhibiting more noticeable differences than Task 2. This study highlights the possibility of a trustworthy test for ketum-induced social withdrawal and advances the development of objective diagnostic tools for ketum-related social withdrawal. © The Institution of engineering & technology 2024.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Congestion Aware Genetic Q-learning Based RPL Routing Protocol for Vehicle Ad-Hoc Networks 5

Congestion Aware Genetic Q-learning Based RPL Routing Protoc...

引用

5th International Conference on engineering technology and its Applications, IICETA 2022

作者： Rashid, Sami Abduljabbar Habelalmateen, Mohammed I. Ahmed, Ahmed Jamal Abbas, Ali Hashim Jubair, Mohammed Ahmed Hassan, Mustafa Hamid Abdulhadi, Ahmed Hammed, Shimah Audah, L. Al-Maarif University College Department of Computer Engineering Techniques Al-Anbar Iraq Islamic University College of Technical Engineering Department of Computer Technical Engineering Najaf54001 Iraq Imam ja'Afar Al-Sadiq University College of Information Technology Department of Computer Technical Engineering Al-Muthanna 66002 Iraq Al-Farahidi University Engineering Technical College Baghdad Iraq Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Batu Pahat Malaysia

ISBN: (纸本)9781665472159

Vehicular Ad-Hoc Network (VANET) is the one among the prominent research area. On behalf of its eminent behaviour link dynamically varying topology, huge mobility, irregular connectivity and density it is still in the open research area. Its dynamic nature is the biggest challenge to do data transmission among the network. This research work introduced a novel protocol which is Congestion Aware Genetic Q-Learning (CAGQ) based RPL routing protocol for VANET networks. The major sub sections of the protocol are system model, mobility model, and preeminent path selection and trickle timer based genetic Q-Learning. The extensive evaluation is done through simulation which analysed the performance of RPL routing protocol in extremely dynamic vehicular environment. The contiki based Cooja simulator is employed for the process of simulation. The calculated results of the protocol CAGQ model is compared with the earlier works such as MRHOFL and EMCC. The analysis is done by calculating the parameters such as packet delivery ratio and Routing overhead. This result indicates that the proposed CAGQ method performed better and produced good results in data transmission even in huge mobility based VANETs. © 2022 IEEE.

关键词： Genetic algorithms

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：