检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Bagherkhani, Sahar Earls, Jackson Christopher De Flaviis, Franco Baldi, Pierre Department of Electrical Engineering and Computer Science University of California at Irvine Irvine United States Department of Computer Science University of California at Irvine Irvine United States

Electromagnetic field reconstruction is crucial in many applications, including antenna diagnostics, electromagnetic interference analysis, and system modeling. This paper presents a deep learning-based approach for Far-Field to Near-Field (FF-NF) transformation using Convolutional Neural Networks (CNNs). The goal is to reconstruct near-field distributions from the far-field data of an antenna without relying on explicit analytical transformations. The CNNs are trained on paired far-field and near-field data and evaluated using mean squared error (MSE). The best model achieves a training error of 0.0199 and a test error of 0.3898. Moreover, visual comparisons between the predicted and true near-field distributions demonstrate the model’s effectiveness in capturing complex electromagnetic field behavior, highlighting the potential of deep learning in electromagnetic field reconstruction. Copyright © 2025, 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

Capacity on BMS Channels via Code Symmetry and Nesting

arXiv

引用

arXiv 2025年

作者： Pfister, Henry D. Reeves, Galen Department of Electrical and Computer Engineering Department of Mathematics Duke Quantum Center Duke University United States Department of Electrical and Computer Engineering Department of Statistical Science Duke University United States

The past decade has seen notable advances in our understanding of structured error-correcting codes, particularly binary Reed–Muller (RM) codes. While initial breakthroughs were for erasure channels based on symmetry, extending these results to the binary symmetric channel (BSC) and other binary memoryless symmetric (BMS) channels required new tools and conditions. Recent work uses nesting to obtain multiple weakly correlated "looks" that imply capacity-achieving performance under bit-MAP and block-MAP decoding. This paper revisits and extends past approaches, aiming to simplify proofs, unify insights, and remove unnecessary conditions. By leveraging powerful results from the analysis of boolean functions, we derive recursive bounds using two or three looks at each stage. This gives bounds on the bit error probability that decay exponentially in the number of stages. For the BSC, we incorporate level-k inequalities and hypercontractive techniques to achieve the faster decay rate required for vanishing block error probability. The results are presented in a semitutorial style, providing both theoretical insights and practical implications for future research on structured codes. Copyright © 2025, The Authors. All rights reserved.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

Neural network-assisted effective lossy compression of medical images

引用

PROCEEDINGS OF THE IEEE 1996年第10期84卷 1474-1487页

作者： Panagiotidis, NG Kalogeras, D Kollias, SD Stafylopatis, A Division of Computer Science the Department of Electrical and Computer Engineering National and Technical University of Athens Athens Greece

A neural network architecture is proposed and shown to be very effective in performing lossy compression of medical images. A novel ROI-JPEG technique is introduced as the coding platform, in which the neural architecture adaptively selects regions of interest (ROI's) in the images. By letting the selected ROI's be coded with high quality, in contrast to the rest of image areas, high compression ratios are achieved, while retaining the significant (from medical point of view) image content. The performance of the method is illustrated by means of experimental results in real life problems taken from pathology and telemedicine applications.

关键词： Neural networks Image coding Biomedical imaging Image reconstruction Telemedicine Magnetic resonance imaging Pathology Image quality Solids Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Enhanced ROI guided deep learning model for Alzheimer’s detection using 3D MRI images

引用

Informatics in Medicine Unlocked 2025年 56卷

作者： Israt Jahan Khan Md. Fahim Bin Amin Md. Delwar Shahadat Deepu Hazera Khatun Hira Asif Mahmud Anas Mashad Chowdhury Salekul Islam Md. Saddam Hossain Mukta Swakkhar Shatabda Department of Computer Science and Engineering United International University Bangladesh Department of Electrical and Computer Engineering North South University Bangladesh LUT School of Engineering Sciences Lappeenranta-Lahti University of Technology Finland Department of Computer Science and Engineering BRAC University Bangladesh

Alzheimer’s disease is an incurable condition that predominantly affects the human brain, leading to the shrinkage of various brain regions and the disruption of neuronal connections. Current state-of-the-art methods for detecting Alzheimer’s disease using 3D MRI images are resource-intensive and time-consuming. In this paper, we propose a Regions of Interest (ROI)-guided detection paradigm to address these challenges. We employ a 3D ResNet integrated with a Convolutional Block Attention Module (CBAM), demonstrating that emphasising ROIs in brain imaging can substantially reduce both computational expenditure and training time. Our model exhibits robust performance in discriminating Alzheimer’s disease from mild cognitive impairment, achieving an accuracy of 88% across the entire brain and 92% within targeted ROIs on the ADNI dataset. The accuracy on the OASIS dataset is even higher, reaching 98% for all regions and 98.33% for the ROIs. When distinguishing Alzheimer’s disease from cognitively normal individuals, the accuracy improves further, achieving 93.33% for the ROIs on the ADNI dataset and 97.8% on the OASIS dataset. In differentiating cognitively normal individuals from those with mild cognitive impairment, the model attains an accuracy of 88.2% for the ROIs on the ADNI dataset and 98.6% on the OASIS dataset. These findings highlight a notable enhancement in detection accuracy through the utilisation of fewer, yet more salient brain regions, underscoring the efficacy of our ROI-guided approach.

关键词： Alzheimer’s disease Regions of Interest (ROIs) 3D MRI Transfer learning ResNet 3D Efficient computation

来源：评论

学校读者我要写书评

暂无评论

PROGRAMMING IN THE LARGE

引用

IEEE TRANSACTIONS ON SOFTWARE engineering 1986年第7期12卷 769-783页

作者： RAMAMOORTHY, CV GARG, V PRAKASH, A Department of Electrical Engineering and Computer Sciences Computer Science Division University of California Berkeley CA 94720

Ad hoc programming methods do not work in the development of bid software systems. The problems faced in developing large software include: 1. starting from fuzzy and incomplete requirements, 2. enforcing a methodology on the developers, 3. coordinating multiple programmers and managers, 4. achieving desired reliability and performance in the network, 5. managing a multitude of resources in a meaningful way, and 6. completing the system within a limited time frame. Some of the trends in requirement specification, life-cycle modeling, programming environments, design tools, and other software engineering areas are examined for tackling these development problems. Several phase-independent and phase-dependent techniques are suggested for programming in the large system. It is demonstrated how research in automatic programming, knowledge-based systems, metrics, and programming environments can make a great difference in the ability to develop large systems.

关键词： Software Measurement Complexity Theory Software engineering Libraries Databases Programming Software Life Cycle Information Abstraction Knowledge Based Systems Metrics Programming Environments Reusability

来源：评论

学校读者我要写书评

暂无评论

Robust Attacks Detection Model for Internet of Flying Things based on Generative Adversarial Network (GAN) and Adversarial Training

引用

IEEE Internet of Things Journal 2025年

作者： Gaber, Tarek Ali, Tarek Nicho, Mathew Torky, Mohamed Engineering and Environment University of Salford School of Science Manchester United Kingdom Suez Canal University Faculty of Computers and Informatics Ismailia Egypt Manchester Metropolitan University Department of Computing and Mathematics Manchester United Kingdom Rabdan Academy Research and Innovation Centre Abu Dhabi United Arab Emirates University of Queensland School of Electrical Engineering and Computer Science Australia Egyptian Russian University-Badr City Faculty of Artificial Intelligence Cairo Egypt

The Internet of Flying Things (IoFT) holds significant promise in fields like disaster management and surveillance. However, it is increasingly vulnerable to cyberattacks that can compromise the confidentiality, integrity, and availability (CIA) of sensitive data. Despite the growing interest in proposing Intrusion Detection Systems (IDSs) for IoFT networks, current literature faces key limitations, particularly the shortage of publicly available IoFT datasets with diverse attacks, and the fact that existing IDSs lack robustness against sophisticated adversarial machine learning attacks. This paper is the first study to address these limitations by proposing a more resilient and accurate IDS tailored for IoFT networks (RIDS-IoFT). We introduce a novel IDS that leverages Generative Adversarial Networks (GANs) to generate a hybrid dataset that combines real IoFT traffic data with GAN-generated adversarial attacks, addressing the dataset diversity issue. Additionally, we introduce an innovative adversarial training method to enhance the system’s defense against evolving threats, such as Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), and Carlini & Wagner (C&W) attacks. The proposed RIDS-IoFT was evaluated using four machine learning models, Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Logistic Regression (LR), on two datasets: ECU-IoFT and CICIDS2018. The IDS’s performance was assessed based on its ability to detect both traditional and adversarial attacks. The results show that the Random Forest model achieved the highest detection accuracy, up to 96.5%, demonstrating superior performance across both real and hybrid datasets. The proposed RIDS-IoFT not only enhances detection accuracy but also strengthens resilience against adversarial threats, making it suitable for resource-constrained IoFT environments. In conclusion, this study presents a comprehensive approach to securing IoFT networks by combining real and synthetic d

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Faster shortest-path algorithms using the acyclic-connected tree

arXiv

引用

arXiv 2025年

作者： Stefansson, Elis Biggar, Oliver Johansson, Karl H. School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Sweden Department of Computer Science Columbia University United States

This paper gives a fixed-parameter linear algorithm for the single-source shortest path problem (SSSP) on directed graphs. The parameter in question is the nesting width, a measure of the extent to which a graph can be represented as a nested collection of graphs. We present a novel directed graph decomposition called the acyclic-connected tree (A-C tree), which breaks the graph into a recursively nested sequence of strongly connected components in topological order. We prove that the A-C tree is optimal in the sense that its width—the size of the largest nested graph—is equal to the nesting width of the graph. We then provide a linear-time algorithm for constructing the A-C tree of any graph. Finally, we show how the A-C tree allows us to construct a simple variant of Dijkstra’s algorithm which achieves a time complexity of O(e + n log w), where n (e) is the number of nodes (arcs) in the graph and w is the nesting width. The idea is to apply the shortest path algorithm separately to each component in the order dictated by the A-C tree. We obtain an asymptotic improvement over Dijkstra’s algorithm: when w = n, our algorithm reduces to Dijkstra’s algorithm, but it is faster when w ∈ o(n), and linear-time for classes of graphs with bounded width, such as directed acyclic graphs. Copyright © 2025, The Authors. All rights reserved.

关键词： Data flow graphs

来源：评论

学校读者我要写书评

暂无评论

DISCRETE MODEL-REFERENCE ADAPTIVE-CONTROL OF CONTINUOUS-TIME LINEAR MULTIINPUT MULTIOUTPUT SYSTEMS VIA MULTIRATE SAMPLED-DATA CONTROLLERS

引用

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS 1995年第3期84卷 471-493页

作者： ARVANITIS, KG PARASKEVOPOULOS, PN Division of Computer Science Department of Electrical and Computer Engineering National Technical University of Athens Athens Greece

The use of multirate sampled-data controllers for linear multivariable time-invariant systems with unknown parameters is investigated. Such controllers contain periodically time-varying elements and a multirate sampling mechanism with different sampling periods at each system input. Their application to unknown continuous-time linear multi-input, multi-output systems results in a sampled closed-loop system for which an arbitrary discrete-time transfer function matrix can be assigned, as is shown in the present paper. The contribution of the present paper is twofold: the use of multirate sampled-data controllers in the area of model reference adaptive control;and the application, for the first time, of periodically varying controllers for model reference adaptive control of multi-input, multi-output systems.

关键词： MODEL REFERENCE ADAPTIVE CONTROL LINEAR MULTIVARIABLE SYSTEMS MULTIRATE SAMPLED-DATA CONTROLLERS DIGITAL CONTROL

来源：评论

学校读者我要写书评

暂无评论

FIDSUS: Federated Intrusion Detection for Securing UAV Swarms in Smart Aerial Computing

引用

IEEE Internet of Things Journal 2025年第9期12卷 11312-11328页

作者： Deng, Jiangtao Wang, Wei Wang, Lina Bashir, Ali Kashif Gadekallu, Thippa Reddy Feng, Hailin Lv, Meilei Fang, Kai Zhejiang A&F University College of Mathematics and Computer Science Hangzhou311300 China Quzhou University College of Electrical and Information Engineering Quzhou324000 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Shenzhen518172 China Beijing Institute of Technology School of Medical Technology Beijing100081 China Manchester Metropolitan University Department of Computing and Mathematics ManchesterM15 6BX United Kingdom Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Rajpura140401 India Lovely Professional University Division of Research and Development Phagwara144411 India Chitkara University Center of Research Impact and Outcome Rajpura140401 India

The dynamic environment of UAV swarms in forest management is characterized by communication instability, heterogeneous nodes, and frequent topology changes due to challenging terrain. These systems are vulnerable to network attacks, requiring advanced intrusion detection technologies. Traditional methods struggle with rapid changes due to data privacy concerns and centralized computational limits, while existing federated learning (FL) algorithms lack robustness against client heterogeneity and dynamic data distribution, especially in complex forest environments. To address these challenges, we propose federated intrusion detection for securing UAV swarms (FIDSUS). FIDSUS improves intrusion detection systems by leveraging collaborative sensing among UAVs, enabling better monitoring and response to security threats in forestry. By quantifying the similarity between UAVs’ local feature extractors through an affinity matrix, FIDSUS guides the aggregation of feature extractors, improving detection capabilities. It also uses AI-driven aerial and distributed computing to enhance data processing efficiency and decision-making speed. The framework addresses data heterogeneity by cross-round feature fusion, improving detection in dynamic environments. Experimental results on the NSL-KDD and UNSW-NB15 datasets show that FIDSUS outperforms existing FL methods with a 4%–34% accuracy improvement. FIDSUS shows robustness and accuracy in dynamic environments, providing an effective solution for securing UAV swarms in forestry. © 2014 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Improving Software Quality Assurance Using a Cross-Context-Attentive Cosine Convolutional Model 2

Improving Software Quality Assurance Using a Cross-Context-A...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Sunil, Deena Dabke, Devika Saini, Surendra Kumar Singh Jandail, Ravendra Ratan Maduranga, M.W.P. Raw, Sharada Nandan Indira Gandhi National Tribal University Department of Mathematics Madhya Pradesh Amarkantak India Central University of Karnataka Department of Mathematics Karnataka Gulbarga India Indira Gandhi National Tribal University Department of Mathematics MadhyaPradesh Amarkantak India South Asian University Department of Computer Science New Delhi New Delhi India University of Sri JayewardenepuraNugegoda Department of Electrical and Electronic Engineering India National Institute of Technology Raipur Department of Mathematics Chhattisgarh Raipur India

ISBN: (纸本)9798331505745

The software quality determines system performance and reliability. As software systems are becoming increasingly complex, this is an important determinant. Detection of defects at the early stages of the development lifecycle improves software reliability and reduces costs. Traditional Software Defect Prediction (SDP) models suffer from class imbalance, complexity of datasets, and inefficient use of contextual information, which affect the accuracy of their predictions. Therefore, the development of reliable software systems still requires a more robust and efficient defect prediction model. In this manuscript, Improving Software Quality Assurance Using a Cross-Context-Attentive Cosine Convolutional Model (Sox-CNN-XA) is proposed. This study uses the NASA-MDP dataset containing historical records of software defects and various software metrics. Data pre-processing included data cleaning, normalization, and splitting, which was done in order to enhance the quality of the data and make it ready for training and validation purposes. A new framework for Software Defect Prediction (SDP) has been proposed by using the integration of Cosine Convolutional Neural Networks (Cos-CNN) and Cross-Contextual Attention (XCA), which captures spatial and contextual features of data effectively. The hyperparameters in this model have been fine-tuned with Sardine Optimization Algorithm (SOA) in order to get improved performances over diverse datasets. Experimental results show that the proposed framework achieves an accuracy of 99.9%, a true positive rate of 99.9%, and a precision of 99.8% while maintaining a false positive rate of 7.2%. The results clearly prove that the model is performing better than traditional methods. The conclusion shows that the framework can increase the reliability of defect prediction, thus enabling software practitioners to deliver high-quality and maintainable software within tight deadlines and budgets © 2025 IEEE.

关键词： Reliability analysis

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：