检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Sepanj, M. Hadi Ghojogh, Benyamin Fieguth, Paul Vision and Image Processing Group Systems Design Engineering University of Waterloo ON Canada Department of Electrical and Computer Engineering University of Waterloo ON Canada

Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily address feature variance and linear correlations, they often neglect the intricate relations between samples and the nonlinear dependencies inherent in complex data. In this paper, we introduce Correlation-Dependence Self-Supervised Learning (CDSSL), a novel framework that unifies and extends existing SSL paradigms by integrating both linear correlations and nonlinear dependencies, encapsulating sample-wise and feature-wise interactions. Our approach incorporates the Hilbert-Schmidt Independence Criterion (HSIC) to robustly capture nonlinear dependencies within a Reproducing Kernel Hilbert Space, enriching representation learning. Experimental evaluations on diverse benchmarks demonstrate the efficacy of CDSSL in improving representation quality. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Grid-Forming Inverter Control Through Integral Sliding Mode Control in a Cascaded Framework 4

Enhanced Grid-Forming Inverter Control Through Integral Slid...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Rayane, Khaled Rabhi, Abdelhamid Oubbati, Brahim Khalil Benzoubir, Mohammed University of Laghouat LACoSERE Lab Laghouat Algeria Texas A and M University at Qatar Qatar Foundation Department of Electrical and Computer Engineering Doha Qatar University of Picardie Jules Verne Laboratory of Modelisation Information and Systems-MIS France

ISBN: (纸本)9798350306262

The microgrid (MG) relies heavily on the grid-forming inverter (GFI), making it a crucial component. Therefore, precise and adaptable control of the GFI is essential for microgrid operations due to its pivotal role in shaping voltage and regulating frequency. In this context, this paper introduces a Integral Sliding Mode Control (ISMC) based cascaded approach for controlling the GFI system. The primary goal of this control strategy is to produce a three-phase sinusoidal voltage with a specified amplitude while minimizing harmonic distortion in the output voltage under varying load conditions. The key advantage of the proposed GFI controller lies in its ability to deliver superior performance, characterized by low Total Harmonic Distortion (THD), rapid dynamic tracking capabilities, and robustness in the face of load fluctuations. A comparative assessment is conducted between the conventional repetitive controller and the newly proposed method, considering linear and nonlinear load scenarios. The simulation results provide strong validation for the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Integrated Sensing and Communications for Statistical-QoS Provisioning Over 6G M-MIMO Mobile Networks Using FBC

Integrated Sensing and Communications for Statistical-QoS Pr...

引用

IEEE International Conference on Communications (ICC)

作者： Xi Zhang Qixuan Zhu H. Vincent Poor Department of Electrical and Computer Engineering Networking and Information Systems Laboratory Texas A&M University TX USA Department of Electrical and Computer Engineering Princeton University Princeton NJ USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Since the 6G mobile wireless networks require the high-performances on both channel state estimations and information transmissions, the technique of integrated sensing and communication (ISAC) has attracted considerable research attention due to its ability to sense and communicate by sharing the same frequency band and hardware. However, how to jointly optimize the sensing and communication functions of the ISAC to support the 6G traffic transmissions over a time-varying wireless fading channel has imposed many new challenges not encountered before. To conquer these difficulties, in this paper we propose the ISAC scheme to jointly sense the channel state and transmit the wireless-streaming data using massive multiple-input and multiple-output (massive MIMO) communications over the Rician fading channel. First, we establish the system models for the ISAC scheme under the Rician fading wireless channel and the channel state estimation scheme using the radar sensing feedback. Second, we define the channel state estimation distortion and the capacity-distortion function of a massive MIMO channel to jointly measure the performances of sensing and communication in our ISAC scheme. Third, we integrate the capacity-distortion function with the finite blocklength coding (FBC) scheme by developing the concept of the ISAC-based E-effective capacity to implement the statistical delay and error-rate bounded provisioning for supporting the 6G traffic under our ISAC scheme. Finally, we use numerical analyses to validate and evaluate our proposed ISAC scheme with massive MIMO in the non-asymptotic regime.

关键词： 6G mobile communication Wireless sensor networks Channel estimation Rician channels Massive MIMO Radar Quality of service

来源：评论

学校读者我要写书评

暂无评论

Understanding the Impact of Unobservable Variables on the Performance of Predictive Models: The Need for Feature Space Partitioning and Fusion

Understanding the Impact of Unobservable Variables on the Pe...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Juarez Garcia, Ezequiel Stephens, Chad L. Napoli, Nicholas J. Laboratory Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States Crew Systems & Aviation Operations Branch and System-Wide Safety Project NASA Langley Research Center HamptonVA23681 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

When developing predictive models over a dataset, the model is globally optimized across the entire feature space to learn a decision boundary. However, when unobservable variables—which cannot be measured or estimated—interact with the observable variables, this can negatively impact the optimization applied to the decision boundary since the data samples introduced by unobservable variables may have little to no association with the applied global optimization. This, consequently, penalizes the entire decision boundary and model performance. This paper examines some of the detrimental effects of unobservable variables, particularly their role in creating new modes in the distribution of observable variables and reducing the separ ability of class distributions. Such challenges result in unrepresentative training data, complex skewedor warped decision boundaries, and decreased accuracy of model predictions, particularly for interpretable models like logistic regression and decision trees. Through two illustrative case examples, we highlight the need to address the challenges imposed by unobservable variables. We propose a strategy to mitigate these challenges by creating local regions with in the feature space through partitioning. This enables the optimization of local models with inthe regions to overcome the impact of un observ ability and complex decision boundaries indifferent feature space localities. Research into a more sophisticated partitioning strategy and where the partition should be relative to the sample of interest is left as future work. Through the analysis of the impact of un observability and the development of a partitioning method, we demonstrate the clear need for a partitioning strategy that integrates knowledge from multiple local models to estimate risk factors using information fusion. Thus, we establish the foundation and motivation for using partitioning and information fusion to overcome the effects of unobserv ability in predictive mo

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Learning good state and action representations for Markov decision process via tensor decomposition

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 5157-5209页

作者： Chengzhuo Ni Yaqi Duan Munther Dahleh Mengdi Wang Anru R. Zhang Department of Electrical & Computer Engineering Princeton University Laboratory for Information & Decision Systems Massachusetts Institute of Technology Electrical Engineering & Computer Science Department Massachusetts Institute of Technology Department of Biostatistics & Bioinformatics Duke University

The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning method to identify meaningful low-dimensional state and action representations from empirical trajectories. The method exploits the MDP's tensor structure by kernelization, importance sampling and low-Tucker-rank approximation. This method can be further used to cluster states and actions respectively and find the best discrete MDP abstraction. We provide sharp statistical error bounds for tensor concentration and the preservation of diffusion distance after embedding. We further prove that the learned state/action abstractions provide accurate approximations to latent block structures if they exist, enabling function approximation in downstream tasks such as policy evaluation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Faces Detection and Tracking for Crowd Management in Hajj and Umrah

引用

computers, Materials & Continua 2022年第6期71卷 6275-6291页

作者： Riad Alharbey Ameen Banjar Yahia Said Mohamed Atri Abdulrahman Alshdadi Mohamed Abid Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Electrical Engineering Department College of EngineeringNorthern Border UniversityArarSaudi Arabia Laboratory of Electronics and Microelectronics(LR99ES30) Faculty of Sciences of MonastirUniversity of MonastirTunisia College of Computer Sciences King Khalid UniversityAbhaSaudi Arabia CES Laboratory ENISUniversity of SfaxTunisia

Hajj and Umrah are two main religious duties for *** help faithfuls to perform their religious duties comfortably in overcrowded areas,a crowd management system is a must to control the entering and exiting for each *** the number of people is very high,an intelligent crowd management system can be developed to reduce human effort and accelerate the management *** this work,we propose a crowd management process based on detecting,tracking,and counting human faces using Artificial Intelligence *** detection and counting will be performed to calculate the number of existing visitors and face detection and tracking will be used to identify all the humans for security *** proposed crowd management system is composed form three main parts which are:(1)detecting human faces,(2)assigning each detected face with a numerical identifier,(3)storing the identity of each face in a database for further identification and *** main contribution of this work focuses on the detection and tracking model which is based on an improved object detection *** improved Yolo v4 was used for face detection and *** has been very effective in detecting small objects in highresolution *** novelty contained in thismethod was the integration of the adaptive attention mechanism to improve the performance of the model for the desired *** wise attention mechanism was applied to the output layers while both channel wise and spatial attention was integrated in the building *** main idea from the adaptive attention mechanisms is to make themodel focus more on the target and ignore false positive *** demonstrated the efficiency of the proposed method through expensive experimentation on a publicly available *** wider faces dataset was used for the train and the evaluation of the proposed detection and tracking *** proposed model has achieved good results with 91.2%of mAP and a processing speed

关键词： Crowdmanagement Hajj and Umrah face detection object tracking convolutional neural networks(CNN) adaptive attention mechanisms

来源：评论

学校读者我要写书评

暂无评论

A 1.65 to 1.84 GHz Filtering SPDT Switch With Fully Tunable Insertion Phase Using NRN and Mixed Electromagnetic Coupling Techniques

引用

IEEE Transactions on Circuits and systems II: Express Briefs 2023年第9期70卷 3353-3357页

作者： Wei, Zhihua Chi, Pei-Ling Xu, Ruimin Yang, Tao School of Electronic Science and Engineering University of Electronic Science and Technology of China Chengdu Sichuan611731 China Department of Electrical and Computer Engineering National Chiao Tung University Hsinchu300 Taiwan Research Center of Advanced RF Chips and Systems Nanhu Laboratory Jiaxing Zhejiang314000 China

This brief presents a novel filtering single-pole-double-throw (SPDT) switch with continuously tunable center frequency and insertion phase. It is comprised of six varactor-loaded microstrip resonators and three tunable non-resonating nodes (NRNs) at source and loads. The controllable mixed electromagnetic couplings are introduced on the two main paths of each channel of the switch. At ON-state, the designed filtering switch can generate a 4th-order bandpass filtering performance with high selectivity, and the insertion phase can be continuously tuned with a full 360° tuning range by changing the reactances of NRNs and switching the dominated modes of the mixed couplings. At OFF-state, the mixed electromagnetic couplings are set to zero, and hence high isolation can be realized. To validate the proposed technique, a circuit prototype is designed and fabricated. The measured results suggest that the designed filtering SPDT switch can operate with a tunable center frequency ranging from 1.65 GHz to 1.84 GHz, and its insertion phase at ON-state channel can be continuously tuned from -180° to 180°. During the whole tuning process, the measured in-band isolation for OFF-state channel keeps better than 40 dB. © 2023 IEEE.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

An Efficient Medical Image Deep Fusion Model Based on Convolutional Neural Networks

引用

computers, Materials & Continua 2023年第2期74卷 2905-2925页

作者： Walid El-Shafai Noha A.El-Hag Ahmed Sedik Ghada Elbanby Fathi E.Abd El-Samie Naglaa F.Soliman Hussah Nasser AlEisa Mohammed E.Abdel Samea Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Higher Institute of Commercial Science Management Information SystemsEl-Mahala El-KobraEgypt Department of the Robotics and Intelligent Machines Faculty of Artificial IntelligenceKafrelsheikh UniversityKafr El-SheikhEgypt Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadhSaudi Arabia Medical Imaging and Interventional Radiology National Liver InstituteMenoufia UniversityEgypt

Medical image fusion is considered the best method for obtaining one image with rich details for efficient medical diagnosis and *** learning provides a high performance for several medical image analysis *** paper proposes a deep learning model for the medical image fusion *** model depends on Convolutional Neural Network(CNN).The basic idea of the proposed model is to extract features from both CT and MR ***,an additional process is executed on the extracted *** that,the fused feature map is reconstructed to obtain the resulting fused ***,the quality of the resulting fused image is enhanced by various enhancement techniques such as Histogram Matching(HM),Histogram Equalization(HE),fuzzy technique,fuzzy type,and Contrast Limited Histogram Equalization(CLAHE).The performance of the proposed fusion-based CNN model is measured by various metrics of the fusion and enhancement *** realistic datasets of different modalities and diseases are tested and ***,real datasets are tested in the simulation analysis.

关键词： Image fusion CNN deep learning feature extraction evaluation metrics medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques With Digital Twin for Fault Diagnosis in Interconnected systems: A Review

引用

IEEE Access 2025年 13卷 91860-91874页

作者： Imen Nakti Majdi Mansouri Rami Al-Hmouz Atef Khedher Laboratory of Advanced Technology and Intelligent Systems ENISO University of Sousse Sousse Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman

As industrial systems become more complex and interconnected, diagnosing faults accurately and in real time has become increasingly challenging. This paper explores how combining artificial intelligence with digital twin technology can address these challenges. We focus on developing hybrid Artificial intelligence models that leverage diverse data sources to enhance fault detection and diagnosis, enabling secure and distributed diagnostics. Digital twins, virtual models of physical systems, are shown to enhance predictive maintenance and decision-making by providing real-time system insights. What sets our work apart is the way we integrate these technologies to create scalable, adaptive, and context-aware diagnostic solutions. We demonstrate the potential of this approach across applications such as smart grids, manufacturing, and autonomous systems. Our goal is to provide researchers and practitioners with a practical and forward-looking framework for developing intelligent, reliable fault diagnosis systems in today’s data-rich industrial environments.

关键词： Artificial intelligence Real-time systems Sensors Fault detection Fault diagnosis Interconnected systems Intelligent sensors Smart grids Digital twins Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Secure Resource Allocations for Polarization-Enabled Multiple-Access Cooperative Cognitive Radio Networks With Energy Harvesting Capability

Secure Resource Allocations for Polarization-Enabled Multipl...

引用

作者： Wang, Fei Zhang, Xi Southwest University College of Electronic and Information Engineering Chongqing400715 China Texas A and M University Networking and Information Systems Laboratory Department of Electrical and Computer Engineering College StationTX77843 United States

We address secure communications over energy-harvesting based orthogonal frequency-division multiple-access (OFDMA) cooperative cognitive radio networks, where one primary user (PU) cooperates with several size-limited secondary users (SUs) in terms of both data transmission and energy harvesting. To improve spectrum utilization and ensure that SU can harvest as much energy as possible, we let the size-limited SUs be equipped with orthogonally dual-polarized antennas (ODPAs). Based on these setting-ups, we propose the polarization-enabled two-phase cooperative framework, where SU transmitters first apply the power splitting technique to harvest energy from radio frequency (RF) signals radiated by the PU, and then use the harvested energy to concurrently transmit their own and the PU's data. Under our proposed framework, we develop three secure resource allocation schemes for scenarios when SUs are untrusted users, which implies that each SU may overhear the PU's and the other SUs' confidential information. For these scenarios, which has hardly been studied, we jointly optimize the allocation of relays, subcarriers, power splitting ratios, and powers when SUs adopt the decode-and-forward (DF) strategy or the amplify-and-forward (AF) strategy to relay the PU's data, with the objective to maximize the total secrecy rate of all SUs while guaranteeing the PU's secrecy rate. Finally, we validate and evaluate our proposed cooperative framework and secure resource allocation schemes through numerical analyses. © 2002-2012 IEEE.

关键词： Secure communication

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：