检索结果-内蒙古大学图书馆

Topology Construction for Max-Min Rate Optimization in Heterogeneous UAVs Networks

IEEE Internet of Things Journal 2025年第12期12卷 20203-20214页

作者： Wu, Kefeng Chin, Kwan-Wu Soh, Sieteng Sun Yat-sen University School of Cyber Science and Technology Guangzhou510275 China University of Wollongong School of Electrical Computer and Telecommunications Engineering NSW2522 Australia Curtin University School of Electrical Engineering Computing and Mathematical Sciences PerthWA6102 Australia

This paper considers a topology construction problem involving a fixed-wing Unmanned Aerial Vehicle (UAV), a set of quad-rotor UAVs and mobile ground users. The constructed topology must maximize the max-min flow rate of ground users over a given planning horizon. To this end, we outline a Mixed Integer Linear Program (MILP) that jointly optimizes the trajectory of the fixed-wing UAV, placement of quad-rotor UAVs, and routing of traffic from each source-destination ground user pair. Solving the MILP is challenging because it requires an exhaustive collection of topologies. To this end, this paper outlines a solution called Rollout to determine the network topology in each time slot of a given planning horizon iteratively. The main idea of Rollout is to generate a sequence of future decisions using a heuristic, where a decision corresponds to the placement of quad-rotor UAVs. Further, each sequence of decisions has a cost-to-go value. Rollout then selects the sequence with the highest cost-to-go value. The results show that the max-min flow rate achieved by Rollout is on average 81% that of MILP. © 2014 IEEE.

关键词： Antenna grounds

来源：评论

学校读者我要写书评

暂无评论

Enhancing Early Exit Performance with Uncertainty-Aware Training in Convolutional Neural Networks for Image classification

引用

IEEE Access 2025年 13卷 91671-91681页

作者： Kurian, Thanu Thangam, S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India

Deep Neural Networks have become more and more complex over the past years delivering efficient results but demanding more requirements for resources. The traditional cloud-based DNN inference produces poor real-time performance due to its high latency requirement in the network. Nowadays, fog and edge have been popular, where computation occurs near the data source or between the source and the cloud. High usage of computational resources by DNN incurs limited room for its deployment in such resource-constrained devices. Deep Neural Networks with multiple exit architecture are an optimal approach to preserve time and computational resources by predicting results at an early stage using multiple early exits to support Edge and Fog Intelligence. Early exit, although lightweight and energy efficient, mostly exhibits degraded performance compared to later exits due to the count of samples that are misclassified. To overcome the downfall, we propose uncertainty estimation in the loss function as an additional parameter for classification. Observational results on CIFAR, MNIST, human lung CT scan, and brain MRI datasets using VGG-16, Lenet-5, and Resnet architectures exhibit that our proposed model is better than the existing models to improve performance as well as prediction confidence in Deep Learning Models with early exits. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Generative AI based Secure Wireless Sensing for ISAC Networks

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5195-5210页

作者： Wang, Jiacheng Du, Hongyang Liu, Yinqiu Sun, Geng Niyato, Dusit Mao, Shiwen Kim, Dong In Shen, Xuemin Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong Jilin University College of Computer Science and Technology 130012 China Auburn University Department of Electrical and Computer Engineering Auburn United States Sungkyunkwan University Department of Electrical and Computer Engineering Suwon16419 Korea Republic of University of Waterloo Department of Electrical and Computer Engineering Canada

Integrated sensing and communications (ISAC) is one of the crucial technologies for 6G, and channel state information (CSI) based sensing serves as an essential part of ISAC. However, current research on ISAC focuses mainly on improving sensing performance, overlooking security issues, particularly the unauthorized sensing of users. Hence, this paper proposes a diffusion model based secure sensing system (DFSS). Specifically, we first propose a discrete conditional diffusion model to generate graphs with nodes and edges, which guides the ISAC system to appropriately activate wireless links and nodes, ensuring the sensing performance while minimizing the operation cost. Using the activated links and nodes, DFSS then employs the continuous conditional diffusion model to generate safeguarding signals, which are next modulated onto the pilot at the transmitter to mask fluctuations caused by user activities. As such, only authorized ISAC devices with the safeguarding signals can extract the true CSI for sensing, while unauthorized devices are unable to perform the effective sensing. Experiment results demonstrate that DFSS can reduce the activity recognition accuracy of the unauthorized devices by approximately 70%, effectively shield the user from the illegitimate surveillance. © 2005-2012 IEEE.

关键词： Sensors Wireless communication Diffusion models Wireless sensor networks Communication system security Performance evaluation Security Integrated sensing and communication Fluctuations Accuracy

来源：评论

学校读者我要写书评

暂无评论

New Antenna Array Beamforming Techniques Based on Hybrid Convolution/Genetic Algorithm for 5G and Beyond Communications

引用

computer Modeling in engineering & sciences 2024年第3期138卷 2749-2767页

作者： Shimaa M.Amer Ashraf A.M.Khalaf Amr H.Hussein Salman A.Alqahtani Mostafa H.Dahshan Hossam M.Kassem Electronics and Communications Engineering Department Higher Institute of Engineering and TechnologyKafr ElsheikhEgypt Electronics and Electrical Communications Engineering Department Faculty of EngineeringMinia UniversityMiniaEgypt Electronics and Electrical Communications Engineering Department Faculty of EngineeringTanta UniversityTantaEgypt Electronics and Electrical Communications Engineering Department Faculty of EngineeringHorus University EgyptNew DamiettaEgypt Department of Computer Engineering College of computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia School of Computing Mathematics and EngineeringCharles Sturt UniversityBathurstNSW2795Australia

Side lobe level reduction(SLL)of antenna arrays significantly enhances the signal-to-interference ratio and improves the quality of service(QOS)in recent and future wireless communication systems starting from 5G up to ***,it improves the array gain and directivity,increasing the detection range and angular resolution of radar *** study proposes two highly efficient SLL reduction *** techniques are based on the hybridization between either the single convolution or the double convolution algorithms and the genetic algorithm(GA)to develop the Conv/GA andDConv/GA,*** convolution process determines the element’s excitations while the GA optimizes the element *** M elements linear antenna array(LAA),the convolution of the excitation coefficients vector by itself provides a new vector of excitations of length N=(2M−1).This new vector is divided into three different sets of excitations including the odd excitations,even excitations,and middle excitations of lengths M,M−1,andM,*** the same element spacing as the original LAA is used,it is noticed that the odd and even excitations provide a much lower SLL than that of the LAA but with amuch wider half-power beamwidth(HPBW).While the middle excitations give the same HPBWas the original LAA with a relatively higher *** the increased HPBWof the odd and even excitations,the element spacing is optimized using the ***,the synthesized arrays have the same HPBW as the original LAA with a two-fold reduction in the ***,for extreme SLL reduction,the DConv/GA is *** this technique,the same procedure of the aforementioned Conv/GA technique is performed on the resultant even and odd excitation *** provides a relatively wider HPBWthan the original LAA with about quad-fold reduction in the SLL.

关键词： Array synthesis convolution process genetic algorithm(GA) half power beamwidth(HPBW) linear antenna array(LAA) side lobe level(SLL) quality of service(QOS)

来源：评论

学校读者我要写书评

暂无评论

Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection

引用

Neural computing and Applications 2025年第6期37卷 4567-4583页

作者： Sayem, Faizul Rakib Islam, Md. Sakib Bin Naznine, Mansura Nashbat, Mohammad Hasan-Zia, Mazhar Kunju, Ali K Ansaruddin Khandakar, Amith Ashraf, Azad Majid, Molla Ehsanul Kashem, Saad Bin Abul Chowdhury, Muhammad E. H. Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh Department of Biomedical Engineering Military Institute of Science and Technology Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Chemical Engineering Department University of Doha for Science and Technology Doha Qatar Department of Electrical Engineering Qatar University Doha2713 Qatar Computer Applications Department Academic Bridge Program Qatar Foundation Doha Qatar Department of Computing Science AFG College With the University of Aberdeen Doha Qatar

Given the severity of waste pollution as a major environmental concern, intelligent and sustainable waste management is becoming increasingly crucial in both developed and developing countries. The material composition and volume of urban solid waste are key considerations in processing, managing, and utilizing city waste. Deep learning technologies have emerged as viable solutions to address waste management issues by reducing labor costs and automating complex tasks. However, the limited number of trash image categories and the inadequacy of existing datasets have constrained the proper evaluation of machine learning model performance across a large number of waste classes. In this paper, we present robust waste image classification and object detection studies using deep learning models, utilizing 28 distinct recyclable categories of waste images comprising a total of 10,406 images. For the waste classification task, we proposed a novel dual-stream network that outperformed several state-of-the-art models, achieving an overall classification accuracy of 83.11%. Additionally, we introduced the GELAN-E (generalized efficient layer aggregation network) model for waste object detection tasks, obtaining a mean average precision (mAP50) of 63%, surpassing other state-of-the-art detection models. These advancements demonstrate significant progress in the field of intelligent waste management, paving the way for more efficient and effective solutions. © The Author(s) 2024.

关键词： Deep learning for waste management Intelligent waste management Object detection in waste management Sustainable waste processing Urban solid waste Waste image classification

来源：评论

学校读者我要写书评

暂无评论

meMIA: Multilevel Ensemble Membership Inference Attack

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 93-106页

作者： Ullah, Najeeb Aman, Muhammad Naveed Sikdar, Biplab National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore University of Nebraska-Lincoln School of Computing LincolnNE68588 United States

Leakage of private information in machine learning models can lead to breaches of confidentiality, identity theft, and unauthorized access to personal data. Ensuring the safe and trustworthy deployment of AI systems necessitates addressing privacy concerns to prevent unintentional disclosure and discrimination. One significant threat, membership inference (MI) attacks, exploit vulnerabilities in target learning models to determine if a given sample was part of the training set. However, the effectiveness of existing MI attacks is often limited by the number of classes in the dataset or the need for diverse multilevel adversarial features to exploit overfitted models. To enhance MI attack performance, we propose meMIA, a novel framework based on stacked ensemble learning. meMIA integrates embeddings from a neural network (NN) and a long short-term memory (LSTM) model, training a subsequent NN, termed the meta-model, on the concatenated embeddings. This method leverages the complementary strengths of NN and LSTM models;the LSTM captures order differences in confidence scores, while the NN discerns probability distribution differences between member and nonmember samples. We extensively evaluate meMIA on seven benchmark datasets, demonstrating that it surpasses current state-of-the-art MI attacks, achieving accuracy up to 94.6% and near-perfect recall. meMIA's superior performance, especially on datasets with fewer classes, underscores the urgent need for robust defenses against privacy attacks in machine learning, contributing to the safer and more ethical use of AI technologies. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Leveraging AI to Compromise IoT Device Privacy by Exploiting Hardware Imperfections

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1561-1574页

作者： Baig, Mirza Athar Iqbal, Asif Aman, Muhammad Naveed Sikdar, Biplab University of Nebraska-Lincoln School of Computing LincolnNE68588 United States National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore

The constrained design, remote deployment, and sensitive data generated by Internet of Things (IoT) devices make them susceptible to various cyberattacks. One such attack is profiling IoT devices by tracking their packet transmissions. While existing methods mitigate these attacks using pseudonymous identities, we propose a novel attack strategy that exploits the physical layer characteristics of IoT devices. Specifically, we demonstrate how an attacker can leverage features extracted from device transmissions to identify packets originating from the same device. Once identified, the attacker can isolate the device's signals and potentially determine its physical location. This attack exploits the fact that microcontroller clock variations exist across devices, even within the same model line. By extracting transmission features and training Machine Learning (ML) models, we accurately identify the originating device of the packets. This study reveals inherent privacy vulnerabilities in IoT systems due to hardware imperfections that are beyond user control. These limitations have profound implications for the design of security frameworks in emerging ubiquitous sensing environments. Our experiments demonstrate that the proposed attack achieves 99% accuracy in real-world settings and can bypass privacy measures implemented at higher protocol layers. This work highlights the urgent need for privacy protection strategies across multiple layers of the IoT protocol stack. © 2020 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Deep Learning Models on Lane Detection Through Semantic Segmentation

引用

SN computer science 2024年第1期5卷 139页

作者： Kumar, Sunil Pandey, Ankur Varshney, Sudeep School of Computing Science and Engineering Galgotias University Greater Noida India Department of Computer Science & Engineering Manipal University Jaipur Jaipur India Department of Computer Science & Engineering Sharda School of Engineering & Technology Greater Noida India

Due to advancements in the deep learning technology, object detection has become significantly important for lane detection and vehicle detection. In recent times, lane detection has become more popular as it plays a significant role in traffic surveillance compared to other object detection technology. However, these strategies have several intrinsic flaws which need to be addressed. Traditional-based techniques still suffer from the challenges of the effectiveness and accuracy, whereas a complex convolutional layer is a challenge for deep learning-based strategies. A parameter selection issue affects the majority of the available lane detection algorithms, which further contributes to their unsatisfactory detection performance. In this study, we provide an effective lane detection method based on semantic segmentation to identify lane lines in a high-dimensional dataset by adding vertical spatial properties and contextual driving information. This paper employs two created frames—feature merging block and information exchange block—to identify unclear and obstructed lane lines more effectively. The simulations have been carried out for the proposed model on TUSimple and CULane datasets which resulted with 94.42% accuracy, 93.47% precision, 92.85% recall, and 93.17% F1-score. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： CNN Deep learning Lane detection Occluded lane lines Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Learning Based Cybersecurity Phishing Email Detection and Classification

引用

computers, Materials & Continua 2023年第3期74卷 5901-5914页

作者： R.Brindha S.Nandagopal H.Azath V.Sathana Gyanendra Prasad Joshi Sung Won Kim Department of Computing Technologies SRM Institute of Science and TechnologyKattankulathur603203India Department of Computing Science and Engineering Nandha College of TechnologyErode638052India School of Computing Science and Engineering VIT Bhopal UniversityBhopal466114India Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Information and Communication Engineering Yeungnam UniversityGyeongsan-si38541Gyeongbuk-doKorea

Phishing is a type of cybercrime in which cyber-attackers pose themselves as authorized persons or entities and hack the victims’sensitive data.E-mails,instant messages and phone calls are some of the common modes used in *** the security models are continuously upgraded to prevent cyberattacks,hackers find innovative ways to target the *** this background,there is a drastic increase observed in the number of phishing emails sent to potential *** scenario necessitates the importance of designing an effective classification *** numerous conventional models are available in the literature for proficient classification of phishing emails,the Machine Learning(ML)techniques and the Deep Learning(DL)models have been employed in the *** current study presents an Intelligent Cuckoo Search(CS)Optimization Algorithm with a Deep Learning-based Phishing Email Detection and Classification(ICSOA-DLPEC)*** aim of the proposed ICSOA-DLPEC model is to effectually distinguish the emails as either legitimate or phishing *** the initial stage,the pre-processing is performed through three stages such as email cleaning,tokenization and stop-word ***,the N-gram approach is;moreover,the CS algorithm is applied to extract the useful feature ***,the CS algorithm is employed with the Gated Recurrent Unit(GRU)model to detect and classify phishing ***,the CS algorithm is used to fine-tune the parameters involved in the GRU *** performance of the proposed ICSOA-DLPEC model was experimentally validated using a benchmark dataset,and the results were assessed under several *** comparative studies were conducted,and the results confirmed the superior performance of the proposed ICSOA-DLPEC model over other existing *** proposed model achieved a maximum accuracy of 99.72%.

关键词： Phishing email data classification natural language processing deep learning cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Data-driven output regulation control for constrained linear systems

引用

science China(Information sciences) 2025年第3期68卷 338-353页

作者： Chaoyu XIA Yi DONG Chaoli WANG Shengyuan XU Shanghai Research Institute for Intelligent Autonomous Systems Tongji University College of Electronic and Information Engineering Shanghai Research Institute for Intelligent Autonomous SystemsTongji University Department of Control Science and Engineering School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and Technology Department of Automation Nanjing University of Science and Technology

This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking performance while satisfying the state and input constraints, even when system matrices are not available. We first establish a sufficient condition necessary for the existence of a solution pair to the regulator equation and propose a data-based approach to obtain the feedforward and feedback control gains for state feedback control using linear programming. Furthermore, we design a refined Luenberger observer to accurately estimate the system state, while keeping the estimation error within a predefined set. By combining output regulation theory, we develop an output feedback control strategy. The stability of the closed-loop system is rigorously proved to be asymptotically stable by further leveraging the concept of λ-contractive sets.

关键词： output regulation constrained system data-driven.

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：