检索结果-内蒙古大学图书馆

Enhanced Parallel sparse-MLP for Monocular Depth Estimation of Autonomous UAV

Journal of Institute of Control, Robotics and systems 2023年第11期29卷 928-935页

作者： Park, Cheol-Hoon Choi, Hyun-Duck Department of ICT Convergence System Engineering Chonnam National University Korea Republic of

Estimating a high-quality depth map from a single RGB image is a challenging task due to its ill-posed nature. Recently, two dominant trends in computer vision have been the subject of extensive research: attention mechanisms and multi-layer perceptron (MLP)-based vision models. Attention mechanisms, especially multi-head attention (MHA), have demonstrated significant improvements in depth estimation. MHA excels in capturing long-distance information and pixel relationships, yet its complexity quadratically increases with spatial resolution. Consequently, applying MHA to unmanned aerial vehicles with limited hardware resources is infeasible. In contrast, MLP-based vision models offer faster inference due to their linear computational complexity concerning spatial resolution. However, the inherent weakness of the MLP’s inductive bias can hinder generalization without a substantial amount of data. Moreover, the absence of location-dependent local dependencies can hinder the precise estimation of locally detailed depth maps. To address these challenges, this study introduces a novel module called EPsMLP (Enhanced Parallel sparse-MLP), which consists of three parallel branches, including sparse-MLP, local sparse attention, and channel attention. This module can capture global and local dependencies while benefiting from the inductive bias on locality. Furthermore, multi-scale convolutions are used to extract context at various scales for diverse objects. The architecture adopts an encoder-decoder-based structure, incorporating a pre-trained DenseNet-121 encoder. Experimental evaluations were conducted using the NYU-Depth-V2 and KITTI datasets, which are commonly used in monocular depth estimation. The extensive results demonstrate that our network is more efficient and effective than previously proposed methods. © ICROS 2023.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Anisotropic Grain Growth of Al-Si Wire Under Electromigration Tests in Power Devices

引用

JOM 2023年第9期75卷 3807-3815页

作者： Tsau, Yan-Wen Ouyang, Fan-Yi Department of Engineering and System Science National Tsing Hua University Hsinchu Taiwan

The microstructure evolution of Al-1 wt% Si alloy wires with a diameter of 50.8 μm bonded on Cu metallization was investigated under electromigration (EM) tests with a current density of 7 × 104 A/cm2 at an ambient temperature of 150 °C. After the EM tests, microstructure of the wire evolved from submicron slender grains into bamboo-type grains with diameters 100 times larger than the original ones because of anisotropic grain growth (AGG) in the radial direction of wire. The orientations of grains also changed from highly [111] oriented into random distribution. In addition, bamboo nodes created by distortion of bamboo-type grains were found near cathodes while protrusions were observed near anodes of the wire. The mechanisms of AGG as well as the orientation change are proposed and delineated in this study. © 2023, The Minerals, Metals & Materials Society.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Design of Fractional-order Sliding Mode Controller and Fractional-order Extended State Observer for a PMSG-based Wind Turbine system with MPPT Control

引用

Journal of Institute of Control, Robotics and systems 2023年第5期29卷 443-451页

作者： Han, Seong-Ik Department of Mechanical System Engineering Dongguk University WISE Campus Korea Republic of

This paper designs a fractional-order sliding mode control (FSMC) of a permanent magnet synchronous generator (PMSG)-based wind energy conversion system, where attempts to extract the maximum wind power point tracking (MPPT). The combination of generator nonlinearities and parameter uncertainties may be issued to obtain the desired maximum wind power. A robust FSMC and fractional-order extended state observer are considered to address the given challenges and yield the enhanced control performance of the PMSG based wind turbine system by the MPPT technique. Simulations are carried out to examine the proposed control system for two cases with the variable step and randomly varied wind speed conditions. The simulation results verified the effectiveness and superiority of the FSMC system compared with the conventional control methods. Copyright© ICROS 2023.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Static Modeling and Experimental Verification for Safety Evaluation of Human-robot Interaction in Exoskeleton Robots

引用

Journal of Institute of Control, Robotics and systems 2023年第9期29卷 726-733页

作者： Lim, Seungbum Jung, Hyein Suh, Jungwook Department of Robot and Smart System Engineering Kyungpook National University Korea Republic of

The elasticity of human skin and the complexity of human joints can lead to misalignment between an exoskeleton robot and the human body. This misalignment increases physical human-robot interaction forces, resulting in discomfort and pain for the wearer. Consequently, considering these interaction forces is crucial for ensuring the safety of wearing an exoskeleton. In this study, we propose a novel method to statically predict physical human-robot interaction forces and evaluate the safety of using exoskeleton robots. To validate the interaction model, experiments are conducted using a sensor-equipped upper limb dummy and an exoskeleton robot. The results confirm the effectiveness of the proposed method, allowing for the quantitative assessment of the safety of using exoskeleton robots without the need for manufacturing actual prototypes. © ICROS 2023.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Reconstruction Attacks in Template-Based ECG Biometric Recognition systems

引用

IEEE Internet of Things Journal 2024年第8期11卷 14971-14984页

作者： Lee, Song-Hong Nien, Cing-Ping Wu, Shun-Chi Swindlehurst, A. Lee National Tsing Hua University Department of Engineering and System Science Hsinchu30013 Taiwan University of California Department of Electrical Engineering and Computer Science IrvineCA92697 United States

The success of Internet of Things (IoT) services will be determined by how the security of the IoT devices and the networks to which they are connected can be guaranteed. Integrating biometric recognition technology into IoT systems has gained popularity as a means of accomplishing this objective. Electrocardiograms (ECGs) have become a promising biometric tool for security because their intrinsic and dynamic nature makes them difficult to steal and forge for replay attacks. However, as with other biometric-based security approaches, attacks on ECG biometric systems have been developed. This study examines the vulnerability of template-based ECG biometric systems to reconstruction attacks. These attacks involve exposing the biometric templates of registered subjects in a hacked database and attempting to reconstruct their ECGs to spoof the system. Both deep learning models and 'heuristic' approaches are used to perform this task, depending on the intruder's level of knowledge of the template construction. Several reconstruction attack strategies are proposed and evaluated for fiducial- and PCA-based systems using ECGs from the Physikalisch-Technische Bundesanstalt database of 285 subjects. The experimental results demonstrate a reconstruction similarity of at least 0.93 and an increase in the false-positive identification-error rate of more than 73%. © 2014 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Interface engineering of Carbon Fiber‑Based Electrode for Wearable Energy Storage Devices

引用

Advanced Fiber Materials 2023年第5期5卷 1749-1758页

作者： Soobeom Lee Geon‑Hyoung An Department of Energy System Engineering Gyeongsang National UniversityJinju 52828Republic of Korea Department of Energy Engineering Gyeongsang National UniversityJinju 52828Republic of Korea

Carbon-based fibrous supercapacitors(CFSs)have demonstrated great potential as next-generation wearable energy storage devices owing to their credibility,resilience,and high power *** limited specific surface area and low electrical conductivity of the carbon fiber electrode,however,impede its practical *** overcome this challenge,this study fabricated a CFS by sequentially coating graphene,carbon nanotube,and activated carbon on the carbon fiber surface(CF/G/CNT/AC).The CF/G/CNT/AC exhibited excellent electrochemical performance with a specific capacitance of 692 mF cm^(-2)at 70μA cm^(-2)and good cycling stability over 4000 *** result is ascribed to the increase of contact area between the active material and the current ***,the energy density of the as-prepared CF/G/CNT/AC fibrous supercapacitor reaches 86.6 and 37.7μW cm^(-2)at power densities of 126 and 720μW cm^(-2),respectively,demonstrating its potential for practical *** addition,the CF/G/CNT/AC demonstrated favorable traits such as mechanical flexibility,feasibility,and energy storage capacity,qualifying it as a viable alternative for wearable electronic textiles.

关键词： Interface engineering Fibrous supercapacitor Carbon fiber Carbon nanotube Graphene Activated carbon

来源：评论

学校读者我要写书评

暂无评论

The Challenges and Opportunities of Smart Cities Infrastructure

引用

SN Computer Science 2024年第6期5卷 713页

作者： Abuali, Amer Alharthi, Wejdan Althbyani, Mariam Ghabban, Fahad Ameerbakhsh, Omair Alfadli, Ibrahim Al-Shehri, Ashwaq Hasen Fallatah, Najmah Adel College of Computer Science and Engineering Information System Department Taibah University

Information communications technology (ICT) refers to the technology used for communication and managing information must be utilized to enhance the environment, economics, mobility, and governance, among other facets of urban life, in order to create smart cities. However this progress is frequently accompanied by a number of challenges and unfavorable outcomes. This study aims to uncover ICT difficulties related to smart city infrastructure through an extensive literature review. In addition, a survey was carried out among Saudi nationals to find out what they thought about, anticipated, and worried about in terms of smart city concepts and features. The study also looked at a literature checklist of ICT problems, which included dangers to information security, incompatibilities across systems, privacy concerns, and deficiencies in digital capabilities. Based on the findings it appears that privacy breaches and information security concerns are the most important issues. This is explained by heightened susceptibility and potential, cyberattacks and a pervasive ignorance of the protection of personal data. Because of the anticipated high costs and difficulties with adaption and utilization, the public is concerned about incompatibility between systems and services. Furthermore, older individuals and those with lesser educational achievement have different digital skills. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Compatibility ICT challenges Information insecurity Privacy Smart city Technology skills

来源：评论

学校读者我要写书评

暂无评论

Soft-switching predictive Type-3 fuzzy control for microgrid energy management

引用

Energy Informatics 2025年第1期8卷 1-33页

作者： Ayadi, Walid Tavoosi, Jafar Sarvenoee, Amirhossein Khosravi Mohammadzadeh, Ardashir Mechatronics and Intelligent System Abu Dhabi Polytechnic Abu Dhabi United Arab Emirates Department of Electrical Engineering Ilam University Ilam*** Iran Department of Electrical Engineering University of Bonab Bonab Iran

Because each mode has distinct optimization requirements, optimizing the economic performance of microgrids (MGs) in grid-connected and islanded modes presents unique issues. This research offers a novel methodology to overcome this difficulty and better use renewable resources while satisfying the growing needs of the energy market. To maximize the MG’s performance, this approach combines fuzzy control, machine learning, and artificial intelligence with soft switching technologies. Two predictive rules are used in the design of the control system to handle the particular requirements of either the grid-connected or islanded mode depending on the MG’s operational condition. The study’s findings demonstrate that, in addition to lowering energy expenses in large commercial buildings, the suggested strategy optimizes the use of renewable energy sources and storage capacity in a range of network scenarios. This method offers more flexibility in response to network changes and greatly improves energy efficiency. © The Author(s) 2025.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Brain inspired iontronic fluidic memristive and memcapacitive device for self-powered electronics

引用

Microsystems & Nanoengineering 2025年第1期11卷 465-476页

作者： Muhammad Umair Khan Bilal Hassan Anas Alazzam Shimaa Eissa Baker Mohammad Center for Cyber-Physical Systems-System on Chip Lab Khalifa UniversityAbu Dhabi 127788UAE Department of Computer and Information Engineering Khalifa UniversityAbu Dhabi 127788UAE Department of Electrical Engineering Khalifa UniversityAbu Dhabi 127788UAE Division of Engineering New York UniversityAbu Dhabi 129188UAE Department of Mechanical and Nuclear Engineering Khalifa UniversityAbu Dhabi 127788UAE Department of Chemistry Khalifa UniversityAbu Dhabi 127788UAE

Ionic fluidic devices are gaining interest due to their role in enabling self-powered neuromorphic computing *** this study,we present an approach that integrates an iontronic fluidic memristive(IFM)device with low input impedance and a triboelectric nanogenerator(TENG)based on ferrofluid(FF),which has high input *** incorporating contact separation electromagnetic(EMG)signals with low input impedance into our FF TENG device,we enhance the FF TENG’s performance by increasing energy harvesting,thereby enabling the autonomous powering of IFM devices for self-powered ***,replicating neuronal activities using artificial iontronic fluidic systems is key to advancing neuromorphic *** fluidic devices,composed of soft-matter materials,dynamically adjust their conductance by altering the solution *** developed voltage-controlled memristor and memcapacitor memory in polydimethylsiloxane(PDMS)structures,utilising a fluidic interface of FF and polyacrylic acid partial sodium salt(PAA Na^(+)).The confined ion interactions in this system induce hysteresis in ion transport across various frequencies,resulting in significant ion memory *** IFM successfully replicates diverse electric pulse patterns,making it highly suitable for neuromorphic ***,our system demonstrates synapse-like learning functions,storing and retrieving short-term(STM)and long-term memory(LTM).The fluidic memristor exhibits dynamic synapse-like features,making it a promising candidate for the hardware implementation of neural *** TENG/EMG device adaptability and seamless integration with biological systems enable the development of advanced neuromorphic devices using iontronic fluidic materials,further enhanced by intricate chemical designs for self-powered electronics.

关键词： iontronic memristive ionic fluidic devices memcapacitive ff teng s ff teng fluidic triboelectric nanogenerator teng based

来源：评论

学校读者我要写书评

暂无评论

An attention-based approach for Koopman modeling and predictive control of nonlinear systems

引用

ISA Transactions 2025年 162卷 47-63页

作者： Wang, Meixi Lou, Xuyang Cui, Baotong Suykens, Johan Institute of System Engineering Jiangnan University Wuxi214122 China Department of Electrical Engineering ESAT-STADIUS KU Leuven Kasteelpark Arenberg 10 LeuvenB-3001 Belgium

We develop an innovative attention-based deep learning method for constructing Koopman eigenfunctions, addressing the challenge of accurately modeling nonlinear systems for predictive control. This method is motivated by the need to identify a diffeomorphism that precisely delineates the topological conjugacy between nonlinear dynamics and their linearized counterparts. Leveraging the capabilities and suitability of invertible neural networks, we deploy an architecture equipped with conditional affine coupling layers to approximate this diffeomorphism. A pivotal feature is the integration of an attention mechanism within these layers, enhancing the capture of complex interactions across various layers. Additionally, we propose an alternative strategy, which employs an invertible decoding neural network in conjunction with a frozen decoder, to refine the diffeomorphism approximation further. Utilizing Koopman eigenfunctions and eigenvalues obtained from the learned diffeomorphism, we construct a lifted linear system with an optimized input matrix via multi-step error minimization, which facilitates the predictive control of nonlinear systems through an extended robust linear model predictive control framework. Numerical examples and a physical experiment validate the efficacy of our framework, demonstrating superior prediction performance compared to existing dynamic mode decomposition-based methods. © 2025 International Society of Automation

关键词： Eigenvalues and eigenfunctions

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：