检索结果-内蒙古大学图书馆

Chinese control Conference (CCC)

作者： Yi-Fan Zhang Tao Sun Song Ma Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China Department of Automation Tsinghua University Beijing China

Multi-agent path planning is one of the most challenging problems in the field of artificial intelligence. In this paper, an improved generative adversarial network model with hybrid attention mechanism for data-driven path planning is proposed. Firstly, by introducing spatial attention mechanism, positional attention mechanism and channel attention mechanism, a hybrid attention module is designed. This module not only establishes feature relationship between different locations, but also provides adaptive feature weights to highlight key information. Next, by embedding the hybrid attention module into the generative adversarial network, an improved generative adversarial network model is developed. The proposed model can capture effective feature information in the image and ensures that the generated path can evade obstacles accurately. Finally, some simulation results are provided to verify the superiority and accuracy of the model in path planning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive constrained generalized predictive controller for the PMSM speed servo system to reduce the effect of different load torques

引用

e-Prime - Advances in Electrical engineering, Electronics and Energy 2022年 2卷

作者： Asvadi-Kermani, Omid Felegari, Bashir Momeni, Hamidreza Department of Control Tarbiat Modares University Faculty of Electrical and Computer Engineering Iran

Fractional-order models have been used in recent years to model the number of processes and applications like boilers, supercapacitors, power electronic devices, permanent magnet synchronous motor (PMSM) speed servo systems, and batteries in many papers. In this paper DC motor equivalent fractional-order model is used to model the PMSM speed servo system. This model has two parts: The electrical part and the Mechanical part. Every aspect has a fractional-order differential equation with an independent fractional order parameter. Its real value is unknown, but its span is evident. To specify the model stability region and to simulate it, the fractional model is approximated with a recursive (Oustaloup) filter. In this work, the PMSM motor's speed is controlled by applying the adaptive recursive least squares (RLS-based) constrained generalized predictive controller (GPC) over the system with unknown model order and in the presence of two types of loads: constant load torque, sinusoidal load. In the last section, adaptive constrained generalized predictive controller (AGPC) has been implemented on the real system. Experimental results also show this controller performance. © 2022 The Author(s)

关键词： Adaptive control Constrained generalized predictive control Disturbance effect Fractional-order model PMSM speed servo

来源：评论

学校读者我要写书评

暂无评论

LiFi-CFI: Light-weight Fine-grained Hardware CFI Protection for RISC-V

LiFi-CFI: Light-weight Fine-grained Hardware CFI Protection ...

引用

IEEE International Conference on Design & Test of Integrated Micro & Nano-Systems (DTS)

作者： Mahboobe Sadeghipour Roodsari Fatemeh Sheikhshoaei Nicolo Maunero Paolo Prinetto Zain Navabi Department of Automation and Information Politecnico di Torino Turin Italy School of Electrical and Computer Engineering University of Tehran Tehran Iran IMT School for Advanced Studies Lucca Italy

In today’s open-source industry, RISC-V based embedded devices are used in various applications where security is critical. RISC-V processors are vulnerable to many runtime attacks, including powerful code reuse and code injection in jump/return-oriented programming (JOP/ROP), known as control flow attacks (CFA). For this, several security techniques have been proposed to protect embedded devices from CFA, and one of the most secure categories is control Flow Integrity (CFI). Alternative techniques consider the tradeoff between runtime hardware overhead and security protection. In particular, hardware-based techniques have attracted more attention in recent years because they consume less power and have less runtime overhead, which is critical in embedded systems. Considering these constraints, we have proposed a novel fine-grained technique for jump-oriented programming, where the required memory is replaced with a short Programmable Array Logic (PAL) to reduce runtime and hardware overhead. Also, a low-overhead shadow stack is proposed for return-oriented programming to reduce the required memory capacity compared to the traditional shadow stack implementation by handling the recursive function calls. The proposed Architecture called LiFi-CFI, is a lightweight hardware monitoring solution that can be attached to any IoT-class soft processor. LiFi-CFI not only reduces power consumption and hardware overhead compared to other advanced solutions but also maintains the security guarantees of the main CFI solution. It is a compact solution as a countermeasure with less than 1% hardware resource utilization for Xilinx Artix7 and 0.5% runtime overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anderson Acceleration for Partially Observable Markov Decision Processes: A Maximum Entropy Approach

arXiv

引用

arXiv 2022年

作者： Park, Mingyu Shin, Jaeuk Yang, Insoon Department of Electrical and Computer Engineering Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of

Partially observable Markov decision processes (POMDPs) is a rich mathematical framework that embraces a large class of complex sequential decision-making problems under uncertainty with limited observations. However, the complexity of POMDPs poses various computational challenges, motivating the need for an efficient algorithm that rapidly finds a good enough suboptimal solution. In this paper, we propose a novel accelerated offline POMDP algorithm exploiting Anderson acceleration (AA) that is capable of efficiently solving fixed-point problems using previous solution estimates. Our algorithm is based on the Q-function approximation (QMDP) method to alleviate the scalability issue inherent in POMDPs. Inspired by the quasi-Newton interpretation of AA, we propose a maximum entropy variant of QMDP, which we call soft QMDP, to fully benefit from AA. We prove that the overall algorithm converges to the suboptimal solution obtained by soft QMDP. Our algorithm can also be implemented in a model-free manner using simulation data. Provable error bounds on the residual and the solution are provided to examine how the simulation errors are propagated through the proposed algorithm. Finally, the performance of our algorithm is tested on several benchmark problems. According to the results of our experiments, the proposed algorithm converges significantly faster without degrading the solution quality compared to its standard counterparts. Copyright © 2022, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Self-Sovereign Identity Architecture Based on Blockchain and the Utilization of Customer's Banking Cards : The Case of Bank Scam Calls Prevention 15

A Self-Sovereign Identity Architecture Based on Blockchain a...

引用

15th International Conference on computer engineering and Systems, ICCES 2020

作者： Ahmed, Khaled A. M. Saraya, Sabry F. Wanis, John F. Ali-Eldin, Amr M. T. Mansoura University Faculty of Engineering Computer Engineering and Control Systems Department Mansoura Egypt

ISBN: (纸本)9780738105598

The need to use a wide variety of online services is rising every day in today's digital age. In order to authenticate and authorize users to access services, identity management is essential. To solve several problems such as fragment identity repositories, aim for identity theft and data breaches and identity correlation, the evolution of identity models across siloes, centralized and presently self-sovereign identity based on distributed ledger is emerging. Self-sovereign identity returns the power to the proprietor of the identity and puts the user at the core of the model. In this paper, we propose a framework to identify scam bank service calls and avoid possible loss of personal accounts. Our framework is based on Hyperledger Indy, a public and permissioned Distributed Ledger Technology. The proposed framework strengthens the Know Your Customer process and enhances the trust of third party agencies delegated by banks to deliver many financial items. © 2020 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Adequacy and Security Assessment: Machine Learning Trends for Reliable Smart Energy Networks

Data-Driven Adequacy and Security Assessment: Machine Learni...

引用

Smart Grid Conference (SGC)

作者： Mohammad Mohsen Hayati Hassan Majidi Hossein Shahinzadeh Mehdi Abapour Mahmud Fotuhi-Firuzabad Gevork B. Gharehpetian Faculty of Electrical and Computer Engineering Energy Systems Research Institute (ESRI) University of Tabriz Tabriz Iran Department of Electrical Engineering Amirkabir University of Technology Tehran Iran Center of Excellence in Power System Management and Control (CEPSMC) Sharif University of Technology Tehran Iran

ISBN: (数字)9798331511333

ISBN: (纸本)9798331511340

Smart energy networks (SENs) face numerous challenges related to security, reliability, operational uncertainties, and increasing penetration of renewable energies (REs), necessitating advanced methodologies for adequacy and security assessment. This study delves into the utilization of machine learning-driven approaches (MLDAs) to quantify reliability and gauge the dependability of future sustainable SENs. By autonomously acquiring knowledge from datasets, MLDAs offer swift and reliable evaluations, surpassing traditional methodologies. The integration of artificial intelligence (AI) in enhancing power system reliability is highlighted, emphasizing the importance of extensive datasets and evolving AI algorithms. Data-driven approaches empower energy network operators to proactively identify and mitigate security risks, enhancing the reliability of critical infrastructure systems. The research underscores the significance of constructing reliable databases, addressing challenges in real-time operations, and ensuring the performance and trustworthiness of machine learning (ML) algorithms. Overall, the study showcases the potential of ML techniques in revolutionizing reliability management and risk assessment in smart energy networks, paving the way for sustainable and reliable power systems.

关键词： Uncertainty Machine learning algorithms Databases Machine learning Power system reliability Smart grids Management Reliability Security Risk management

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition

A Multi-Stage Adaptive Feature Fusion Neural Network for Mul...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Shinan Zou Jianbo Xiong Chao Fan Shiqi Yu Jin Tang School of Automation Central South University Department of Computer Science and Engineering Southern University of Science and Technology Research Institute of Trustworthy Autonomous System Southern University of Science and Technology

Gait recognition is a biometric technology that has received extensive attention. Most existing gait recognition algorithms are unimodal, and a few multimodal gait recognition algorithms perform multimodal fusion only once. None of these algorithms may fully exploit the complementary advantages of the multiple modalities. In this paper, by considering the temporal and spatial characteristics of gait data, we propose a multi-stage feature fusion strategy (MSFFS), which performs multimodal fusions at different stages in the feature extraction process. Also, we propose an adaptive feature fusion module (AFFM) that considers the semantic association between silhouettes and skeletons. The fusion process fuses different silhouette areas with their more related skeleton joints. Since visual appearance changes and time passage co-occur in a gait period, we propose a multiscale spatial-temporal feature extractor (MSSTFE) to learn the spatial-temporal linkage features thoroughly. Specifically, MSSTFE extracts and aggregates spatial-temporal linkages information at different spatial scales. Combining the strategy and modules mentioned above, we propose a multi-stage adaptive feature fusion (MSAFF) neural network, which shows state-of-the-art performance in many experiments on three datasets. Besides, MSAFF is equipped with feature dimensional pooling (FD Pooling), which can significantly reduce the dimension of the gait representations without hindering the accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Label-Free EGFR Sensing by Using a Flexible IrOx Extended-Gate Field-Effect Transistor-Based Biosensor

IEEE Sensors Letters

引用

IEEE Sensors Letters 2024年第9期8卷

作者： Singh, Kanishk Chen, Chao-Hung Tai, Li-Chia Huang, Wei-Chen Pan, Tung-Ming Chang Gung University Department of Electronics Engineering Taoyuan33302 Taiwan National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu30093 Taiwan National Yang Ming Chiao Tung University Institute of Electrical and Control Engineering Hsinchu30093 Taiwan Chang Gung Memorial Hospital Division of Urology Taoyuan33305 Taiwan

In this research work, we present a flexible iridium oxide (IrOx) extended-gate field-effect transistor (EGFET) biosensor for label-free detection of the epidermal growth factor receptor (EGFR) biomarker. IrOx was employed as the sensing membrane material due to its excellent electrochemical properties, high conductivity, stability, biocompatibility, and ability to facilitate redox reactions. The IrOx film was deposited on a flexible polyimide (PI) substrate through a sol-gel process and characterized using atomic force microscopy and X-ray photoelectron spectroscopy. As a pH sensor, the IrOx EGFET exhibited a super-Nernstian sensitivity of 68.54 mV/pH with high linearity, a low hysteresis of ∼ 6 mV, and a drift rate of 0.50 mV/h at pH 7 over 12 h. For EGFR detection, the IrOx surface was functionalized with 3-aminopropyltriethoxysilane and glutaraldehyde to immobilize anti-EGFR antibodies. The EGFR sensor demonstrated a wide linear detection range from 1 to 1000 ng/mL with a sensitivity of 11.78 mV/log(ng/mL) and a linearity of 99.8%, making it suitable for clinical EGFR monitoring in cancer patients. The flexible IrOx EGFET shows promise for reliable label-free detection of EGFR. © 2017 IEEE.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

Alzheimer Disease Early Detection Using Convolutional Neural Networks 15

Alzheimer Disease Early Detection Using Convolutional Neural...

引用

15th International Conference on computer engineering and Systems, ICCES 2020

作者： Ebrahim, Doaa Ali-Eldin, Amr M. T. Moustafa, Hossam E. Arafat, Hesham Faculty of Engineering Mansoura University Computer Engineering and Control Systems Department Mansoura Egypt

ISBN: (纸本)9780738105598

Alzheimer's disease is the extremely popular cause of dementia that causes memory loss. People who have Alzheimer's disease suffer from a disorder in neurodegenerative which leads to loss in many brain functions. Nowadays researchers prove that early diagnosis of the disease is the most crucial aspect to enhance the care of patients' lives and enhance treatment. Traditional approaches for diagnosis of Alzheimer's disease (AD) suffers from long time with lack both efficiency and the time it takes for learning and training. Lately, deep-learning-based approaches have been considered for the classification of neuroimaging data correlated to AD. In this paper, we study the use of the Convolutional Neural Networks (CNN) in AD early detection, VGG-16 trained on our datasets is used to make feature extractions for the classification process. Experimental work explains the effectiveness of the proposed approach. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Decreasing perturbation signal based multivariable extremum seeking approach with application in self-optimization operation of illumination system

引用

Energy and Buildings 2025年 342卷

作者： Zhan, Yi Yin, Chun Hou, Zhiqi Dadras, Sara Yan, Zhongbao College of Tourism and Cultural Industry Chengdu University Chengdu610106 China School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Electrical and Computer Engineering Department Utah State University LoganUT84321 United States

The paper develops a multivariable extremum seeking control based on decreasing perturbation signal for multivariable dynamical systems, to speed up convergence and improve the control precision of extremum seeking (ES) and apply to self-optimization operation of illumination system. The framework of the developed ES is proposed to make the amplitudes of the perturbation signals vary with the estimated error of the extremum point, to guarantee the amplitudes converge exponentially to zero. It can be useful for avoiding effectively negative effect of the steady state chattering problem and decreasing the possibility of dropping into the local extremum point. The multivariable ES scheme can also enhance the convergence speed to fasten the tracking of the extremum point. The analysis of stability for the developed multivariable ES is given by utilizing the averaging theory and center manifold method. Simulation and experimental studies in the lighting system display advantages of the considered approach, in comparison with the multivariable Gradient/Newton-based ESs. © 2025 Elsevier B.V.

关键词： Luminescent devices

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：