检索结果-内蒙古大学图书馆

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Karunakaran, E. Suresh, Y. Rao, Bhukya Nageswar Vivek, P.S.S. Aditya, K. National Institute of Technology Department of Electrical and Electronics Engineering Karnataka Surathkal India Kolhapur Institute of Technology College of Engineering Department of Computer Science and Business Systems Kolhapur India

ISBN: (纸本)9798350309140

Cascaded H-bridge (CHB) MLI have emerged as the preferred choice due to their high quality in output waveforms with low harmonic distortion. However, a key limitation in these inverters lies in the requirement of a dedicated DC source for each bridge. To overcome this challenge, there is a transition towards asymmetrical cascaded H-bridge (ACHB) MLIs, enabling the use of a variable DC source for each bridge. The variability in DC supply is achieved through a high-frequency link. This paper introduces a novel optimized switching technique for asymmetrical cascaded H-bridge (ACHB) MLIs with a single DC input incorporating a high-frequency link (HFL). The effectiveness of the suggested approach in achieving a 27-level asymmetric multilevel inverter is substantiated by experimental outcomes obtained through MATLAB/Simulink simulations. © 2024 IEEE.

关键词： DC transformers

来源：评论

学校读者我要写书评

暂无评论

An In-depth Investigation on the Structure, Characteristics, and Potential Applications of GaN/SiC Mosfet-Based systems 6

An In-depth Investigation on the Structure, Characteristics,...

引用

6th International Conference on Information Technologies and electrical engineering, ICITEE 2023

作者： Ren, Yan Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy12180 United States

ISBN: (纸本)9798400708299

In an era of rapid technological innovation, this article provides a comprehensive examination of Gallium Nitride (GaN) Metal-Oxide-Semiconductor Field-Effect Transistors (MOSFETs). The background section highlights the emergence and application of GaN MOSFETs and their significant advantages over silicon-based and Silicon Carbide (SiC) MOSFETs, such as smaller size, faster switching speed, less heat generation, and optimum operation at high temperatures, indicating that GaN MOSFETs are leading us into a more advanced, digitized future. The article delves into the basic theory of GaN MOSFETs, detailing their unique structure and properties that demonstrate massive potential and practicality in real-world applications such as electric vehicles and 5G technology. The conclusion emphasizes that GaN MOSFETs have already shown their importance in a wider range of industrial sectors and are set to revolutionize various industries, thereby driving overall progress. With diversified applications and broad prospects, the impact and value of GaN MOSFETs have gone beyond single-component applications, and their societal significance is undergoing profound changes. © 2023 ACM.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

A Nested Ensemble Method to Bilevel Machine Learning 48

A Nested Ensemble Method to Bilevel Machine Learning

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Chen, Lisha Abbas, Momin Chen, Tianyi Rensselaer Polytechnic Institute Electrical Computer and Systems Engineering Department TroyNY United States

ISBN: (纸本)9781728163277

Modern machine learning problems, such as hyperparameter optimization, meta learning, and adversarial training, adopt a bilevel learning formulation. Such problems involve a nested relation between inner- and outer-level problems, which often have suboptimal solutions with poor generalization ability. To address this issue, this paper proposes an ensemble method tailored to bilevel learning. Our method finds a nested ensemble of inner and outer parameters that improve generalization. We instantiate our general results with meta learning. We show theoretically and empirically that the diversity and the smoother loss landscape of the proposed ensemble methods lead to improved generalization over the state-of-the-art method. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Side-Channel Attack Detection for Mobile Devices Security in 5G Networks

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1012-1026页

作者： Amjed A.Ahmed Mohammad Kamrul Hasan Ali Alqahtani Shayla Islam Bishwajeet Pandey Leila Rzayeva Huda Saleh Abbas Azana Hafizah Mohd Aman Nayef Alqahtani Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Imam Alkadhim University College Department of Computer Techniques EngineeringBaghdad 10066Iraq Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Department of Networks and Communications Engineering College of Computer Science and Information SystemsNajran UniversityNajran 61441Saudi Arabia Institute of Computer Science and Digital Innovation UCSI UniversityKuala Lumpur 56000Malaysia Department of Intelligent Systems and Cyber Security Astana IT UniversityAstana 20000Kazakstan Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinah 42353Saudi Arabia Department of Electrical Engineering College of EngineeringKing Faisal UniversityAl-Hofuf 31982Saudi Arabia

Mobile devices within Fifth Generation(5G)networks,typically equipped with Android systems,serve as a bridge to connect digital gadgets such as global positioning system,mobile devices,and wireless routers,which are vital in facilitating end-user communication ***,the security of Android systems has been challenged by the sensitive data involved,leading to vulnerabilities in mobile devices used in 5G *** vulnerabilities expose mobile devices to cyber-attacks,primarily resulting from security ***-permission apps in Android can exploit these channels to access sensitive information,including user identities,login credentials,and geolocation *** such attack leverages"zero-permission"sensors like accelerometers and gyroscopes,enabling attackers to gather information about the smartphone's *** underscores the importance of fortifying mobile devices against potential future *** research focuses on a new recurrent neural network prediction model,which has proved highly effective for detecting side-channel attacks in mobile devices in 5G *** conducted state-of-the-art comparative studies to validate our experimental *** results demonstrate that even a small amount of training data can accurately recognize 37.5％of previously unseen user-typed ***,our tap detection mechanism achieves a 92％accuracy rate,a crucial factor for text *** findings have significant practical implications,as they reinforce mobile device security in 5G networks,enhancing user privacy,and data protection.

关键词： Fifth Generation(5G)networks smartphone information leakage Side-Channel Attack(SCA) deep learning

来源：评论

学校读者我要写书评

暂无评论

Conjectural Online Learning with First-order Beliefs in Asymmetric Information Stochastic Games 63

Conjectural Online Learning with First-order Beliefs in Asym...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Li, Tao Hammar, Kim Stadler, Rolf Zhu, Quanyan New York University Department of Electrical and Computer Engineering United States Kth Royal Institute of Technology Division of Network and Systems Engineering Sweden

ISBN: (纸本)9798350316339

Asymmetric information stochastic games (AISGs) arise in many complex socio-technical systems, such as cyberphysical systems and IT infrastructures. Existing computational methods for AISGs are primarily offline and can not adapt to equilibrium deviations. Further, current methods are limited to particular information structures to avoid belief hierarchies. Considering these limitations, we propose conjectural online learning (COL), an online learning method under generic information structures in AISGs. COL uses a forecaster-actorcritic (FAC) architecture, where subjective forecasts are used to conjecture the opponents' strategies within a lookahead horizon, and Bayesian learning is used to calibrate the conjectures. To adapt strategies to nonstationary environments based on information feedback, COL uses online rollout with cost function approximation (actor-critic). We prove that the conjectures produced by COL are asymptotically consistent with the information feedback in the sense of a relaxed Bayesian consistency. We also prove that the empirical strategy profile induced by COL converges to the Berk-Nash equilibrium, a solution concept characterizing rationality under subjectivity. Experimental results from an intrusion response use case demonstrate COL's faster convergence over state-of-the-art reinforcement learning methods against nonstationary attacks. © 2024 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Optimal Regulation of SIR Epidemic Model via Finite-Horizon SDRE 26

Nonlinear Optimal Regulation of SIR Epidemic Model via Finit...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Paul, Sudipta Islam, Samiul Naidu, Desineni Subbaram Abu Hanif Pramanik, Md. Rensselaer Polytechnic Institute Department of Electrical Computer & Systems Engineering New York United States Rajshahi University of Engineering & Technology Department of Electrical & Computer Engineering Bangladesh University of Minnesota Duluth Department of Electrical Engineering United States

ISBN: (纸本)9798350359015

A Susceptible-Infectious-Recovered (SIR) model is a popular and fundamental epidemiological model often used to assess the efficacy of disease prevention and control measures. SIR disease model, with the implementation of various optimal control methods, is investigated to determine the optimal ways to lessen the effects of an infectious disease. In this research work, a non-linear, closed-loop, finite-horizon, optimal regulation with state-dependent Riccati equation (FH-SDRE) is implemented in an epidemic model called SIR model with vaccination to minimize the infected and susceptible population. Given the nonlinear dynamics of the SIR epidemic model, initially, this method converts the nonlinear equations into a state-dependent coefficient (SDC) matrix, which holds the nonlinearities of the dynamical system. After that, SDRE is solved at every small time instant over a specified finite time period. The core idea here is to utilize an approximate analytical approach that transforms the differential Riccati equation (DRE) into a differential Lyapunov equation (DLE) during every time period. Then, the real-time solution of the DLE at each of these time steps will result in the control law required to achieve the desired system performance. The effectiveness of the FH-SDRE regulation for the SIR model is demonstrated by minimizing the infected and susceptible population within a desired 30-day time period. © 2023 IEEE.

关键词： finite-horizon regulation SIR epidemic model state-dependent Riccati equation

来源：评论

学校读者我要写书评

暂无评论

Soft Sensors for Industrial Applications: Comparison of Variables Selection Methods and Regression Models

Soft Sensors for Industrial Applications: Comparison of Vari...

引用

2023 International Conference on Control, Automation and Diagnosis, ICCAD 2023

作者： Leiria, Joana Salles, Rodrigo Mendes, Jerome Sousa, Pedro University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra3030-290 Portugal Oncontrol Technologies Rua Cidade Poitiers Coimbra3000-108 Portugal

ISBN: (纸本)9798350347074

The digitalization of industrial environments has enabled the development of tools that make the production process more efficient and safer. In this sense, the Soft Sensor (SS) plays a fundamental role. Through historical data and indirect measurements, it is possible to estimate the value of important variables that are difficult to measure. This paper presents the SS development process: data collection and pre-processing, variable selection, model selection for SS implementation, model training and testing, and performance evaluation. The selection of variables was made with the help of Pearson Correlation, Mutual Information, and fastTracker algorithm techniques. For the implementation of SS have been tested several models: Multiple Linear Regression, Ridge Regression, Least Absolute Shrinkage and Selection Operator, Elastic Net, Support Vector Regression and Gaussian Mixture Models. Four datasets were used to test the development of the SS. © 2023 IEEE.

关键词： Correlation methods

来源：评论

学校读者我要写书评

暂无评论

Average Current Control Design of Active Power Decoupling Converter with Low Filter Inductance Based on Double Sampling Techniques for PV Microinverter

Average Current Control Design of Active Power Decoupling Co...

引用

2024 International Conference on Sustainable Energy: Energy Transition and Net-Zero Climate Future, ICUE 2024

作者： Shen, Yidi Hasnain, Arafat Zakzewski, Daniel Resalayyan, Rakesh Khaligh, Alireza University of Maryland College Park Department of Electrical and Computer Engineering The Institute for Systems Research College ParkMD United States

ISBN: (纸本)9798331517076

Active power decoupling (APD) converter is a power dense and reliable solution in dc-ac power conversion systems to balance the fluctuating ac-side power and constant dc-side power. In boost type APD converter, filter inductor with low inductance can be beneficial in achieving efficient and compact designs or allows the implementation of zero voltage switching (ZVS) based modulation. On the other hand, the reduced inductance increases the difficulty of controller design due to reduction of the average current control loop phase margin and higher requirement in low-pass-filter (LPF). This paper proposes an average current control based on double sampling techniques to reduce the phase delay of LPF and improve the current tracking performance under low inductance. The implementation of double sampling in the digital signal processor (DSP) and the design of control loops are discussed. The proposed approach is experimentally verified using a 40 V, 400 W APD converter prototype. © 2024 IEEE.

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-based unknown reference tracking control of HMASs with nonidentical communication delays

引用

Science China(Information Sciences) 2023年第7期66卷 46-57页

作者： Yong XU Zheng-Guang WU Wei-Wei CHE Deyuan MENG School of Automation Beijing Institute of Technology Institute of Cyber-Systems and Control Zhejiang University College of Mathematics and Computer Science Zhejiang Normal University Department of Automation Qingdao University School of Automation Science and Electrical Engineering Beihang University(BUAA)

This paper focuses on the optimal output synchronization control problem of heterogeneous multiagent systems(HMASs) subject to nonidentical communication delays by a reinforcement learning *** with existing studies assuming that the precise model of the leader is globally or distributively accessible to all or some of the followers, the leader's precise dynamical model is entirely inaccessible to all the followers in this paper. A data-based learning algorithm is first proposed to reconstruct the leader's unknown system matrix online. A distributed predictor subject to communication delays is further devised to estimate the leader's state, where interaction delays are allowed to be nonidentical. Then, a learning-based local controller, together with a discounted performance function, is projected to reach the optimal output synchronization. Bellman equations and game algebraic Riccati equations are constructed to learn the optimal solution by developing a model-based reinforcement learning(RL) algorithm online without solving regulator equations, which is followed by a model-free off-policy RL algorithm to relax the requirement of all agents' dynamics faced by the model-based RL algorithm. The optimal tracking control of HMASs subject to unknown leader dynamics and communication delays is shown to be solvable under the proposed RL algorithms. Finally, the effectiveness of theoretical analysis is verified by numerical simulations.

关键词： heterogeneous multiagent systems HMAS reinforcement learning RL optimal output synchronization communication delays

来源：评论

学校读者我要写书评

暂无评论

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF 41

Principled Penalty-based Methods for Bilevel Reinforcement L...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Shen, Han Yang, Zhuoran Chen, Tianyi Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States Department of Statistics and Data Science Yale University United States

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But bilevel problems such as incentive design, inverse reinforcement learning (RL), and RL from human feedback (RLHF) are often modeled as dynamic objective functions that go beyond the simple static objective structures, which pose significant challenges of using existing bilevel solutions. To tackle this new class of bilevel problems, we introduce the first principled algorithmic framework for solving bilevel RL problems through the lens of penalty formulation. We provide theoretical studies of the problem landscape and its penalty-based (policy) gradient algorithms. We demonstrate the effectiveness of our algorithms via simulations in the Stackelberg game and RLHF. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

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：