检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Vivienne Huiling Wang, Tinghuai Yang, Wenyan Kämäräinen, Joni-Kristian Pajarinen, Joni Department of Electrical Engineering and Automation Aalto University Finland Huawei Helsinki Research Center Finland Computing Sciences Tampere University Finland

In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach. Effective HRL hinges on a suitable subgoal representation function, abstracting state space into latent subgoal space and inducing varied low-level behaviors. Existing methods adopt a subgoal representation that provides a deterministic mapping from state space to latent subgoal space. Instead, this paper utilizes Gaussian Processes (GPs) for the first probabilistic subgoal representation. Our method employs a GP prior on the latent subgoal space to learn a posterior distribution over the subgoal representation functions while exploiting the long-range correlation in the state space through learnable kernels. This enables an adaptive memory that integrates long-range subgoal information from prior planning steps allowing to cope with stochastic uncertainties. Furthermore, we propose a novel learning objective to facilitate the simultaneous learning of probabilistic subgoal representations and policies within a unified framework. In experiments, our approach outperforms state-of-the-art baselines in standard benchmarks but also in environments with stochastic elements and under diverse reward conditions. Additionally, our model shows promising capabilities in transferring low-level policies across different tasks. Copyright 2024 by the author(s)

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Research on Garbled Circuits-Based Identity Authentication and Ciphertext Hidden Access Control in Vehicular Networks 24

Research on Garbled Circuits-Based Identity Authentication a...

引用

9th International Conference on Cloud computing and Internet of Things, CCIOT 2024

作者： Jiao, Zhilong Bai, Fenhua Zhang, Chi Zhang, Xiaohui Gong, Bei Faculty of Information Engineering and Automation Kunming University of Science and Technology China Kunming China Department of Computing Beijing University of Technology China Beijing China

ISBN: (纸本)9798400717161

Since most communications in vehicular networks rely on wireless transmissions, information broadcast by vehicles is highly susceptible to interception and eavesdropping by third parties, making it vulnerable to various attacks. This can result in communication messages being tampered with and the leakage of vehicle locations and identity privacy. From a security perspective, this paper introduces Yao's garbled circuit mechanism, combining random bytes with the solutions of linear equations as identity information assigned to vehicle nodes. By employing dual authentication, the proposed approach addresses issues such as privacy protection, anonymity, replay attacks, and collusion attacks in vehicular networks, thereby enhancing security. Moreover, considering the post-authentication access control scenario, this paper proposes a novel LSSS matrix transformation algorithm for ciphertext hidden access control strategy. It realizes a partially hidden policy, which makes matrix generation more efficient by supporting both AND and OR gates, thus improving the access control efficiency while ensuring security. Performance analysis indicates that in terms of identity authentication, the scheme reduces computational costs by an average of 96.25%, and in access control, the scheme reduces key generation time by an average of 80%. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Automatic Pavement Crack Detection Based on Octave Convolution Neural Network with Hierarchical Feature Learning

引用

Journal of Beijing Institute of Technology 2024年第5期33卷 422-435页

作者： Minggang Xu Chong Li Ying Chen Wu Wei Department of Civil Engineering of Nanjing Technical Vocational College Nanjing 210019China School of Artificial Intelligence and Advanced Computing(AIAC) Xi’an Jiaotong-Liverpool UniversitySuzhou 215400China Department of Electronic Engineering Shantou UniversityShantou 515063China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510006China

Automatic pavement crack detection plays an important role in ensuring road *** images of cracks,information about the cracks can be conveyed through high-frequency and low-fre-quency signals that focus on fine details and global structures,*** output features obtained from different convolutional layers can be combined to represent information about both high-frequency and low-frequency *** this paper,we propose an encoder-decoder framework called octave hierarchical network(Octave-H),which is based on the U-Network(U-Net)architec-ture and utilizes an octave convolutional neural network and a hierarchical feature learning module for performing crack *** proposed octave convolution is capable of extracting multi-fre-quency feature maps,capturing both fine details and global *** propose a hierarchical feature learning module that merges multi-frequency-scale feature maps with different levels(high and low)of octave convolutional *** verify the superiority of the proposed Octave-H,we employed the CrackForest dataset(CFD)and AigleRN databases to evaluate this *** experimental results demonstrate that Octave-H outperforms other algorithms with satisfactory performance.

关键词： automated pavement crack detection octave convolutional network hierarchical feature multiscale multifrequency

来源：评论

学校读者我要写书评

暂无评论

Offset-free distributed predictive control based on fuzzy logic: Application to a real four-tank plant

引用

IFAC-PapersOnLine 2023年第2期56卷 3247-3252页

作者： M. Francisco E. Masero K. Morales-Rodelo J.M. Maestre P. Vega S. Revollar Department of Computing and Automation University of Salamanca Spain Department of Systems Engineering and Automation University of Seville

This paper proposes an offset-free distributed implementation of a model predictive controller that employs fuzzy negotiation between agents. The scheme is based on model augmentation with additional disturbances to enable zero-offset tracking. Moreover, we code the negotiation criteria as a set of suitable fuzzy rules and consider stability and feasibility guarantees in the controller design for the linearized subsystems. We applied the method to an experimental four-tank plant, showing its effectiveness despite the coupling between subsystems and system-model mismatch.

关键词： Linear multivariable systems Predictive control Fuzzy control systems Process control Control of distributed systems

来源：评论

学校读者我要写书评

暂无评论

Robust Object Recognition in Open Environments Based on Causal Inference 7

Robust Object Recognition in Open Environments Based on Caus...

引用

7th International Conference on Robotics, Control and automation engineering, RCAE 2024

作者： Liu, Ruonan Wu, Shuai Kong, Ping Xie, Wei Zhang, Weidong Shanghai Jiao Tong University Department of Automation Shanghai China Tianjin University College of Intelligence and Computing Tianjin China Hainan University School of Information and Communication Engineering Hainan China Shanghai Jiaotong University Department of Automation Shanghai China

ISBN: (纸本)9798350355642

The rapid development of artificial intelligence technology has drawn widespread attention to the problem of target recognition in open environments. Traditional target recognition methods are easily affected by environmental changes and interference noise, leading to insufficient recognition accuracy and robustness. This paper proposes a robust target recognition method based on causal inference, aiming to improve the robust performance of image recognition models in open environments. The method first extracts features from images, analyzes the impact of noise features such as the environment in image features, and derives the essential feature properties of the target. Then, the causal relationship is introduced into the target recognition, and by analyzing the relationship between the environment, the target, and the observation data, the features of the target are combined with the observation data to achieve accurate and stable recognition of the target. The proposed method has achieved good target recognition effects on multiple open datasets, and the experimental results show that the algorithm can effectively solve the problem of poor robustness of the target recognition model in open environments, providing strong support for practical applications. Through the application of this method, the stability and robustness of the target recognition model can be significantly improved, which has important practical application value. © 2024 IEEE.

关键词： Causal Inference Object Recognition Open Set Recognition Robustness

来源：评论

学校读者我要写书评

暂无评论

An Overview of Advanced Gate Driver Concepts for SiC Semiconductors 36

An Overview of Advanced Gate Driver Concepts for SiC Semicon...

引用

36th International Conference on Electrical Drives and Power Electronics, EDPE 2023

作者： Ivanis, Tomislav Kovacic, Marinko University of Zagreb Faculty of Electrical Engineering and Computing Department of Electric Machines Drives and Automation Unska 3 Zagreb10000 Croatia

ISBN: (纸本)9798350322750

Silicon carbide (SiC) power transistors have been steadily gaining popularity in power electronics applications as they have improved properties over silicon based devices, namely silicon MOSFETs and IGBTs. However, because of very high switching speed which results in lower losses, in general application their use is often a concern because of electromagnetic interference (EMI). In order to fully utilise the potential of SiC based devices, a careful design of power stage, commutation loop and gate drive is needed. Because of this reason, this paper presents a review of existing gate drive methods for performance improvement of SiC devices. A special emphasis is given to the gate drive concepts, as it is an important element for the further advancement of SiC-based converters. With improved switching, specifically active gate driving techniques a compromise between EMI and switching losses can be achieved. © 2023 IEEE.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Analysis of current harmonics in data center power system 45

Analysis of current harmonics in data center power system

引用

45th Jubilee International Convention on Information, Communication and Electronic Technology, MIPRO 2022

作者： Raguz, K. Raic Miletic, M. Zelenicic, V. Sumina, D. Erceg, I. Nastasic, Z. Faculty of Electrical Engineering and Computing Department of Electric Machines Drives and Automation Zagreb Croatia

ISBN: (纸本)9789532331035

This paper presents power quality analysis at different points in a data center. Electrical distribution network scheme and data center description are also given. The method of measurements performed is briefly described and the results of real measurements of current and voltage Total Harmonic Distortion (THD) are presented and compared with IEEE 519-2014 recommended practice and requirements for harmonic control in electric power system. All measured values comply with the standard but measurements at downstream levels closer to the nonlinear loads have larger THD. © 2022 Croatian Society MIPRO.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Privacy-Preserving Approach to Incorporate Distributed Generators in AC Optimal Power Flow

A Machine Learning-Based Privacy-Preserving Approach to Inco...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Dindar, Burak Saner, Can Berk Polat, Dogukan Yigit Çakmak, Huseyin Kemâl Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany National University of Singapore Department of Electrical and Computer Engineering Singapore National University of Singapore School of Computing Singapore

ISBN: (纸本)9789531842976

In order to achieve the goal of a carbon-neutral power system, significant changes to the power grid are underway, necessitating enhanced interoperability between Transmission System Operators (TSOs) and Distribution System Operators (DSOs) for effective grid operation, particularly in light of the growing number of distributed generators (DGs). Data privacy concerns, however, complicate decision-making processes, particularly when integrating DGs into system-wide dispatch decisions. In this paper, we propose a machine-learning (ML)-based method to incorporate DGs located within the distribution system (DS) into dispatch decisions, adhering to data privacy by mitigating the exchange of sensitive data, such as system topology and demand profiles, between TSOs and DSOs. The methodology involves training three ML models to represent the behavior of the DS, thereby replacing the standard power flow model that contains sensitive information. Notably, we utilize a novel tailored neural network (NN) architecture to enhance computational efficiency in mapping the feasible region of the DS. Additionally, we employ open-source data to construct the Baden-Wü rttemberg (Germany) electricity grid, allowing to test our method not only on standard systems but also on a model that more accurately represents real-world power systems. The numerical case studies verify that the proposed method achieves results comparable to standard AC optimal power flow (AC-OPF) in both cost-optimality and computational time. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Simplified Control Strategies for Power Converters in a Grid-Connected Hybrid DC-AC Microgrid

Simplified Control Strategies for Power Converters in a Grid...

引用

2023 International Conference on Future Energy Solutions, FES 2023

作者： Busarello, Tiago Davi Curi Simões, Marcelo Godoy Laaksonen, Hannu Kauhaniemi, Kimmo Federal University of Santa Catarina Department of Control Automation and Computing Engineering Blumenau Brazil University of Vaasa School of Technology and Innovations Vaasa Finland

ISBN: (纸本)9798350332308

Many typical converter control strategies used in microgrids are complex or require modifications in the power structure. The complexities are due coupling effects among controllers and time-delay caused in exchanging information in the system. This paper proposes simplified control strategies for power converters in a grid-connected hybrid DC-AC microgrid, aiming to ensure precise voltage and current regulation. The used controllers are proportional-resonant, integral-double-lead, proportional-integral and single integral controller. In this paper, the methodology for tuning each controller is carefully described in detail and recommendation for choosing their bandwidth is given. Then, the designed controllers are discretized through the Backward-Euler approximation. The power converters of the microgrid are an inverter, a Buck, a Boost and a bidirectional DC-DC. A case study is conducted through simulations with Matlab/Simulink. Results show that the controlled variables follow their reference signals with negligible steady-state error, proving the efficacy of the simplified control strategies and allowing an stable operation of the microgrid. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Detecting Double Mixed Compressed Images Based on Quaternion Convolutional Neural Network

引用

Chinese Journal of Electronics 2024年第3期33卷 657-671页

作者： Hao WANG Jinwei WANG Xuelong HU Bingtao HU Qilin YIN Xiangyang LUO Bin MA Jinsheng SUN Department of Automation Nanjing University of Science and Technology Engineering Research Center of Digital Forensics Ministry of Education Department of Computer and Software Nanjing University of Information Science and Technology School of Management Nanjing University of Posts and Telecommunications Department of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University State Key Laboratory of Mathematical Engineering and Advanced Computing Qilu University of Technology

Detection of color images that have undergone double compression is a critical aspect of digital image *** the existence of various methods capable of detecting double Joint Photographic Experts Group(JPEG) compression,they are unable to address the issue of mixed double compression resulting from the use of different compression *** particular,the implementation of Joint Photographic Experts Group 2000(JPEG2000)as the secondary compression standard can result in a decline or complete loss of performance in existing *** tackle this challenge of JPEG+JPEG2000 compression,a detection method based on quaternion convolutional neural networks(QCNN) is *** QCNN processes the data as a quaternion,transforming the components of a traditional convolutional neural network(CNN) into a quaternion *** relationships between the color channels of the image are preserved,and the utilization of color information is ***,the method includes a feature conversion module that converts the extracted features into quaternion statistical features,thereby amplifying the evidence of double *** results indicate that the proposed QCNN-based method improves,on average,by 27% compared to existing methods in the detection of JPEG+JPEG2000 compression.

关键词： Color image forensics JPEG JPEG2000 Mixed double compression Quaternion convolutional neural network

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：