检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年

作者： Gebrehans, Ghebrebrhan Ilyas, Naveed Eledlebi, Khouloud Lunardi, Willian T. Andreoni, Martin Yeun, Chan Yeob Damiani, Ernesto Lab Khalifa University of Science and Technology Abu Dhabi United Arab Emirates University of California Riverside United States Khalifa University of Science and Technology Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Abu Dhabi United Arab Emirates Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Khalifa University of Science and Technology Center for Secure Cyber-physical Systems Abu Dhabi United Arab Emirates University of Milan Dept. of Computer Science Italy

This paper highlights the critical role of Machine Learning (ML) in combating the dynamic nature of cybersecurity threats. Unlike previous studies focusing mainly on static analysis, this work surveys the literature on dynamic analysis-based malware generation and detection. The study addresses the complexities of applying GANs to tabular data with heavy-tailed and multimodal distributions. It also examines the challenges of generating sequential malware behavior data and categorizes GAN-based models and their primary use cases. Furthermore, the paper evaluates adversarial losses and their limitations in generating dynamic malware behavior. Finally, it identifies existing metrics to assess GAN generalization in malware research and suggests future research directions based on identified limitations. © 2020 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Empirical Discovery of Multi-Scale Transfer of Information in Dynamical systems

arXiv

引用

arXiv 2025年

作者： Curtis, Christopher W. Bollt, Erik M. Department of Mathematics and Statistics San Diego State University United States Department of Electrical and Computer Engineering Clarkson University United States Clarkson Center for Complex Systems Science Clarkson University United States

In this work, we quantify the timescales and information flow associated by multiscale energy transfer in a weakly turbulent system through a novel new interpretation of transfer entropy. Our goal is to provide a detailed understanding of the nature of complex energy transfer in nonlinear dispersive systems driven by wave mixing. Further, we present a modal decomposition method based on the empirical wavelet transform that produces a relatively small number of nearly decorrelated, scale separated modes. Using our method, we are able to track multiscale energy transfer using only scalar time series measurements of a weakly turbulent system. This points to our approach being of broader applicability in real-world data coming from chaotic or turbulent dynamical systems. © 2025, CC BY.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Vehicular Road Crack Detection with Deep Learning: A New Online Benchmark for Comprehensive Evaluation of Existing Algorithms

arXiv

引用

arXiv 2025年

作者： Ma, Nachuan Song, Zhengfei Hu, Qiang Liu, Chuang-Wei Han, Yu Zhang, Yanting Fan, Rui Xie, Lihua College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems the State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China School of Computer Science and Technology Donghua University Shanghai201620 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

In the emerging field of urban digital twins (UDTs), advancing intelligent road inspection (IRI) vehicles with automatic road crack detection systems is essential for maintaining civil infrastructure. Over the past decade, deep learning-based road crack detection methods have been developed to detect cracks more efficiently, accurately, and objectively, with the goal of replacing manual visual inspection. Nonetheless, there is a lack of systematic reviews on state-of-the-art (SoTA) deep learning techniques, especially data-fusion and label-efficient algorithms for this task. This paper thoroughly reviews the SoTA deep learning-based algorithms, including (1) supervised, (2) unsupervised, (3) semi-supervised, and (4) weakly-supervised methods developed for road crack detection. Also, we create a dataset called UDTIRI-Crack, comprising 2, 500 high-quality images from seven public annotated sources, as the first extensive online benchmark in this field. Comprehensive experiments are conducted to compare the detection performance, computational efficiency, and generalizability of public SoTA deep learning-based algorithms for road crack detection. In addition, the feasibility of foundation models and large language models (LLMs) for road crack detection is explored. Afterwards, the existing challenges and future development trends of deep learning-based road crack detection algorithms are discussed. We believe this review can serve as practical guidance for developing intelligent road detection vehicles with the next-generation road condition assessment systems. The released benchmark UDTIRI-Crack is available at https://***/submission/. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control for Shunt Active Power Filter under Stochastic Solar Photovoltaics Behavior

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Prakash, Surya Alkhatib, Mohamed Sindi, Hatem F. Alghamdi, Sultan Behera, Ranjan Kumar Muduli, Utkal Ranjan Nit Jamshedpur Dept. of Electrical Engg Jharkhand Jamshedpur India Uae University Al Ain Dept. of Electrical and Communication Engg Coe Abu Dhabi15551 United Arab Emirates King Abdulaziz University Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Faculty of Engineering Jeddah21589 Saudi Arabia Indian Institute of Technology Patna Dept. of Electrical Engineering Bihta801103 India Khalifa University Apec Dept. of Electrical Engineering and Computer Science Abu Dhabi127788 United Arab Emirates

The paper discusses the challenges in controlling a two-stage photovoltaic (PV)-based shunt active power filter (SAPF) under distorted grid conditions and stochastic PV system behavior. To address this, the paper proposes an adaptive proportional integral (API) regulator to regulate the DC-link voltage, which adapts its parameters based on the DC-link error voltage to provide low bandwidth for disturbance rejection and high bandwidth for dynamic performance enhancement. The paper also proposes an estimation method for the reference current using the sliding discrete Fourier transform and the instantaneous symmetrical component theory, which is suitable for non-ideal grid or load conditions. The accuracy of the proposed reference current estimation method is analyzed using time- and frequency-domain analysis. The performance of the PV-SAPF system with the proposed control algorithms is illustrated through simulation and real-time hardware validation under various grid conditions. Despite distorted grid conditions, the total harmonic distortion of the grid current is substantially within IEEE Std 519-2014. The proposed API regulator and reference current estimation method show promising results in improving the performance of the PV-SAPF system in the presence of internal and external disturbances. © 2013 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Joint Source Decomposition of Concurrent EEG-FMRI Data in Epilepsy and Control Groups

Joint Source Decomposition of Concurrent EEG-FMRI Data in Ep...

引用

IEEE International Symposium on Biomedical Imaging

作者： J. Mason Harding Haatef Pourmotabbed Yamin Li Kimberly Rogge-Obando Kate Wang Sarah E. Goodale Shiyu Wang Camden Bibro Bergen Allee Caroline Martin Victoria L. Morgan Dario J. Englot Catie Chang Department of Electrical and Computer Engineering Vanderbilt University Department of Biomedical Engineering Vanderbilt University Department of Computer Science Vanderbilt University Neuroscience Graduate Program Vanderbilt University Vanderbilt Memory and Alzheimer's Center Vanderbilt University Medical Center Department of Neurological Surgery Vanderbilt University Medical Center Department of Radiology Vanderbilt University Medical Center

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

EEG and fMRI are complementary, noninvasive technologies for investigating human brain function. These modalities have been used to uncover large-scale functional networks and their disruptions in clinical populations. Given the high temporal resolution of EEG and high spatial resolution of fMRI, integrating these modalities can provide a more holistic understanding of brain activity. This work explores a multimodal source decomposition technique for extracting shared modes of temporal variation between fMRI BOLD signals and EEG spectral power fluctuations in the resting state. The resulting components are then compared between patients with focal epilepsy and controls, revealing multimodal network differences between groups.

关键词： Neuroimaging Brain Fluctuations Epilepsy Functional magnetic resonance imaging Electroencephalography Pattern recognition Hemodynamics Spatial resolution Signal resolution

来源：评论

学校读者我要写书评

暂无评论

IntSHU: A Security-Enabled Intelligent Soft Handover Approach for UAV-Aided 5G and Beyond

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Karmakar, Raja Kaddoum, Georges Akhrif, Ouassima Heritage Institute of Technology Department of Computer Science and Engineering IoT and Cyber Security including Blockchain Technology Kolkata700107 India University of Quebec Department of Electrical Engineering ETS Montreal Canada Lebanese American University Cyber Security Systems and Applied AI Research Center Beirut Lebanon

Unmanned aerial vehicles (UAVs) play a significant role in serving as gNodeBs (gNBs), or user devices (UDs). However, considering the high data rates and low latency required by fifth generation (5G) and beyond, it is essential to maintain a reliable connection at UAVs, particularly due to frequent handovers. To minimize handover failures, the hysteresis margin and time-to-trigger (TTT) should be dynamically adjusted. Furthermore, to prevent vulnerabilities to threats, UAV and gNB authentication and secure communication should be addressed during handovers. However, available literature uses a learning-based approach to handover management in UAV-aided 5G networks, thereby neglecting security, or offers a handover authentication mechanism, but lacks a novel handover strategy. To fill this gap in the literature, in this study, we design an Intelligent Soft Handover for UAV-enabled cellular networks (IntSHU), a generative adversarial network (GAN)-based scheme designed for intelligent soft handovers in UAV-enabled 5G and beyond. IntSHU uses adapted hysteresis margins and TTT values, dynamically generated through an -greedy policy. In addition, we implement a lightweight, physically unclonable function (PUF)-based message encryption and authentication scheme via blockchain for streamlined access control during handovers. The results of our simulation indicate that IntSHU significantly enhances network performance by facilitating reliable soft handovers. © 2015 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Outage, Capacity, and Error Performance of Downlink RSMA-based systems: Analysis and Resource Optimization

引用

IEEE Transactions on Communications 2025年

作者： Vu, Thai-Hoc Da Costa, Daniel Benevides Kim, Sunghwan Pham, Quoc-Viet University of Ulsan Department of Electrical Electronic and Computer Engineering Ulsan Korea Republic of Interdisciplinary Research Center for Communication Systems and Sensing Department of Electrical Engineering Dhahran31261 Saudi Arabia Kyonggi University School of Electronic Engineering Kyonggi Korea Republic of University of Dublin School of Computer Science and Statistics Trinity College Dublin Dublin 2 D02PN40 Ireland

This paper comprehensively investigates the performance of downlink multi-user rate-splitting multiple access (RSMA) networks under Nakagami-m fading channels. We first develop the mathematical outage probability (OP) and ergodic capacity (EC) frameworks, deriving exact expressions for both, along with asymptotic analysis in high signal-to-noise ratio (SNR) and low-rate regions, which serve as the foundation for deducing the approximate and maximal energy-reliability and energy-spectral formulas. To enhance system performance, we tackle the non-convex problems of jointly optimizing common and private power allocation (PA) coefficients to minimize the maximal OP performance. Moreover, we also delve into optimizing PA coefficients and rate-splitting factors concurrently to maximize the ergodic sum capacity (ESC). Addressing the influence of modulation schemes on user error rates, we introduce mathematical frameworks for symbol error rate (SER) considering four combined modulation schemes based on binary phase-shift keying (BPSK) and quadrature-phase shift keying (QPSK), the whole cases are quantified in terms of exact and asymptotic manners. Furthermore, we present a straightforward approach to optimize the PA coefficients to minimize the maximal SER performance. Finally, Monte-Carlo simulations are presented to validate our developed frameworks and optimization solutions. © 1972-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

High-Dimensional Quantum Key Distribution by a Spin-Orbit Microlaser

引用

Physical Review X 2025年第1期15卷 011024-011024页

作者： Yichi Zhang Haoqi Zhao Tianwei Wu Zihe Gao Li Ge Liang Feng Department of Materials Science and Engineering University of Pennsylvania Philadelphia Pennsylvania 19104 USA Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia Pennsylvania 19104 USA Department of Physics and Astronomy College of Staten Island CUNY Staten Island New York 10314 USA The Graduate Center CUNY New York New York 10016 USA

Quantum key distribution offers a promising avenue for establishing secure communication networks. However, its performance is significantly hampered by the conventional two-level information carriers (i.e., qubits) due to their limited information capacity and noise resilience. A fundamental approach to overcoming these limitations involves the adoption of high-dimensional qudits. Practical qudit platforms require robust propagation, outstanding controllability, and extreme compactness, to which integrated photonics provides a promising solution. Here, we achieved, for the first time, microlaser-enabled high-dimensional quantum communication through leveraging spin-orbit photon qudits, where the dynamical generation and manipulation of these multi-degrees-of-freedom complex quantum state are realized by a non-Hermitian-physics-driven integrated microlaser quantum transmitter. Such a microlaser photon manipulation, as a novel route towards high-dimensional quantum state generation, promises high energy efficiency, along with fast, compact, and precise qudit state reconfigurability. The four spin-orbit eigenstates emitted by the microlaser possess the same spatial-temporal structures, ensuring homogeneity between all qudit states used for key distribution, which effectively eliminates propagation dephasing and walk-off problems, thereby delivering the high-dimensional spin-orbit secret key generation to construct a robust quantum link. The demonstrated long-term system stability showcases the practical potential of the microlaser quantum transmitter, providing a critical step towards compact, high-information-capacity quantum communication networks.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Stealthy Attacks on Sampled-Data Control and Encryption-Based Countermeasures

引用

IEEE Transactions on Automatic Control 2025年

作者： Shang, Jun Li, Yuzhe Chen, Tongwen Tongji University Department of Control Science and Engineering Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai200092 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110004 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada

This paper investigates stealthy attacks on sampled-data control systems, where a continuous process is sampled periodically, and the resultant discrete output and control signals are transmitted through dual channels in wireless communication networks. Acknowledging the vulnerability of these transmitted data to cyber threats, we analyze two types of stealthy attacks that compromise either one or both channels. We explicitly present the necessary and sufficient conditions for the existence of stealthy single-channel attacks. To mitigate these security risks, we implement encryption-based countermeasures, including linear time-invariant and periodic encryption methods. We detail sufficient conditions under which these encryption strategies effectively thwart single- and dual-channel stealthy attacks. The effectiveness of these approaches and the theoretical findings are demonstrated through numerical simulations. © 1963-2012 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A New Look for Outage and Ergodic Improvements in Coordinated IoT Paradigms with Hybrid Multiple Access

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Vu, Thai-Hoc Le, Anh-Tu Huynh-The, Thien da Costa, Daniel Benevides Kim, Sunghwan Kyonggi University School of Electronic Engineering Korea Republic of VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science 17. Listopadu 2172/15 Ostrava708 00 Czech Republic Ho Chi Minh City University of Technology and Education Department of Computer and Communications Engineering Viet Nam Interdisciplinary Research Center for Communication Systems and Sensing Department of Electrical Engineering Dhahran31261 Saudi Arabia

As spectrum utilization becomes increasingly scarce due to the exponential growth of intelligent connected devices in the Internet of Things (IoT), developing efficient communication protocols with simultaneous improvements in energy and spectrum usage is critical in response to the demands of cost-effective IoT devices. In this work, we propose a hybrid orthogonal and non-orthogonal multiple-access protocol in coordinated direct uplink/downlink and relay transmission for low-cost IoT paradigms, where a source node engages in direct transmission with proximate IoT users and relies on a relay node for distant connections. This protocol offers a successive interference cancellation–free approach and does not require any channel disparity for power allocation. Exact and asymptotic analytical expressions for the outage probability (OP) and ergodic capacity (EC) are derived. Numerical results demonstrate that the proposed protocol significantly improves OP–by 8 folds for the respective proximate users while maintaining the same OP for distant users over classical coordinated non-orthogonal multiple access–and delivers superior EC performance for proximate IoT users at low to moderate signal-to-noise ratios (SNRs) and distant users at most SNR. Moreover, critical tasks for minimizing the maximal OP and maximizing the ergodic sum capacity have been undertaken to achieve outage fairness and enhance the overall system's capacity. These non-convex problems are efficiently addressed by applying the analytical asymptotic-inspired alternative optimization. © 1967-2012 IEEE.

关键词： Signal to noise ratio

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：