检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Biomimetics

作者： Dalia M. Mahfouz Paolo Di Lillo Omar M. Shehata Elsayed I. Morgan Filippo Arrichiello Multi-Robot Systems (MRS) Research Group Cairo Egypt Mechatronics Dept. Faculty of Engineering and Materials Science German University in Cairo Egypt University of Cassino and Southern Lazio Italy Mechatronics Dept. Faculty of Engineering Ain Shams University Cairo Egypt

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Recently, there has been an increasing number of human patients who suffer from upper limb disorders limiting their motor abilities. One of the possible solutions that gained extensive research interest is the use of end-effector-based robot-aided rehabilitation training setup which showed various advantages compared to the traditional manual rehabilitation therapy. One of the main challenges of these systems is to control the robot's motion to track a desirable trajectory while being affected by either assistive or resistive human forces depending on the patient's recovery state. In this regards, this study aims to develop a robot Operating System (ROS)-based Fuzzy Logic adaptive control architecture composed of an upper-level admittance control and a lower-level inverse velocity-based joint control. The Fuzzy Logic is used to adapt the admittance control gains considering the trajectory tracking error, the external human applied force magnitude and its direction whether assisting or resisting the robot's motion. The architecture is evaluated in simulation and validated through real-life hardware experiments performing simple circular and other clinical-based trajectories. The results are satisfactory in terms of trajectory tracking accuracy while complying with the assistive forces or being stiff towards the resistive ones.

关键词： robot motion Fuzzy logic Training Limbs Trajectory tracking Operating systems Motors Trajectory robots Admittance control

来源：评论

学校读者我要写书评

暂无评论

Output Feedback Adaptive Neural Network Control for Uncertain Nonsmooth Systems with Application

SSRN

引用

SSRN 2024年

作者： Xu, Qian Zong, Guangdeng Zhao, Xudong Yi, Yang Xia, Jianwei College of Information Science and Engineering Northeastern University Shenyang110819 China School of Control Science and Engineering Tiangong University Tianjin300387 China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian116024 China College of Information Engineering Yangzhou University Yangzhou225127 China School of Mathematics Science Liaocheng University Liaocheng252000 China

The output feedback adaptive neural network control problem is addressed for uncertain nonsmooth systems with network communication constraints. First, a funnel function is provided to ensure that the tracking error restrains the pre-specified performance and improves the transient and steady-state performance simultaneously. Second, an event-triggered controller including the control input, a fixed threshold and the tracking error is designed to alleviate the communication burden. It is rigorously mathematically proved that there exists a positive lower bound to avoid the Zeno behavior. With the designed observer, the control algorithm assures that all the signals are semi-globally uniformly ultimately bounded. Finally, the validity of the proposed scheme is demonstrated through an application example. © 2024, The Authors. All rights reserved.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Research on Natural Language Recognition based on Grey Correlation Degree and TF-IDF Algorithm

Research on Natural Language Recognition based on Grey Corre...

引用

2022 IEEE International Conference on Advances in Electrical engineering and Computer Applications, AEECA 2022

作者： Yang, Liu Cai, Yuliang Sun, Shaoxin Meng, Na Wang, Junyi Li, Xiaoxian Shenyang City University The College of Intelligent Science and Technology Shenyang China Liaoning University The College of Mathematics and Statistics Shenyang China Chongqing University The College of Automation Chongqing China Shenyang City University The College of Intelligence and Engineering Shenyang China Northeastern University The College of Robot and Engineering Shenyang China Liaoning Dinghan Quickhigh Electronic System Engineering Co.Ltd Shenyang China

ISBN: (数字)9781665480901

ISBN: (纸本)9781665480901

Natural language research topic in recent years is complying with the important topic of artificial intelligence development, when dealing with text information data, the training mechanism and combined with the feature of algorithm for natural language data analysis is an effective method to deal with complex text information. For the text classification and judgment process, in combination with the concept of deep learning algorithms have been proposed, and get the argument, combined with the feature of countable characteristic of text classification problem. In the process of research, it often need a lot of samples, the complexity of the samples affect the key content of text extraction, but the lack of samples will lead to extract text content and it is too simplified, the deviation is from the characteristics of information content, On the other hand, for the huge amounts of text sample, it will lead to more redundancy in the compilation process of the algorithm, which has certain requirements for the configuration of the hardware system, and it loses timeliness in the operation time. In this paper, the accuracy of feature extraction of complex text is studied by using an innovative idea of algorithm iteration, and the mathematical grey correlation degree is used to deduce and verify the accuracy. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Method of Relay UAV Deployment for Emergency Communication Scenarios in Disaster Areas

A Method of Relay UAV Deployment for Emergency Communication...

引用

Chinese Automation Congress (CAC)

作者： Cancan Tao Bowen Liu Yi Han Qiangqiang Chen Jun Ye Ronglin Zhong School of Automation Science and Electrical Engineering Beihang University Beijing China Parallel Robot and Mechatronic System Laboratory of Hebei Province Yanshan University Qinhuangdao China Faculty of Science Kunming University of Science and Technology Kunming China School of Biological Science and Medical Engineering Beihang University Beijing China School of Information Science and Technology University of Science and Technology of China Hefei China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

This article proposes a relay deployment method that uses UAVs to provide communication services to ground users, especially for emergency communication scenarios in disaster ***, a two-layer network communication model is constructed for emergency communication scenarios in disaster areas, and the relay deployment problem is transformed into a multi-objective optimization problem. On this basis, a detailed analysis of the problem is conducted, and a UAV relay deployment method based on the K-means++ algorithm is proposed. The two indicators of the number of UAVs used and the network communication performance are considered in solving the problem. Simulation results show that the proposed method can achieve a balance between the number of relay UAVs used and the achieved network performance.

关键词： Uncertainty Automation Disasters Simulation Heuristic algorithms Interference Autonomous aerial vehicles Relays Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

Real-Time Vision-Based Chinese Sign Language Recognition with Pose Estimation and Attention Network

Real-Time Vision-Based Chinese Sign Language Recognition wit...

引用

IEEE International Conference on robotics and Biomimetics

作者： Sirui Cheng Chaorui Huang Zhaohui Wang Jiaxing Wang Zhen Zeng Fei Wang Qichuan Ding School of Computer Science Northeastern University Shenyang China College of Information Science and Engineering Northeastern University Shenyang China Software College Northeastern University Shenyang China Faculty of Robot Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781665405362

Currently, communication between deaf and hearing people is still facing great problems both at the research level and at the application level. Also, practical automatic sign language interpretation methods have become a relatively large demand. In this paper, we will recognize video sign language based on computer vision to capture skeletal key point information using multi-head attention mechanism and long and short-term memory mechanism. We construct a database of Chinese video sign language consisting of 30 words, with a total data volume of more than 1200. Meanwhile, the experiments of our proposed framework on this dataset achieved 85% accuracy rate. The experimental results show that our proposed method has the characteristics of high accuracy and light weight in the problem of Chinese sign language recognition.

关键词： Databases Face recognition Conferences Pose estimation Gesture recognition Assistive technologies Streaming media

来源：评论

学校读者我要写书评

暂无评论

Unravelling the operando structural and chemical stability of rare earth metals co-doped CeO2-based electrocatalysts for oxygen evolution reaction

引用

International Journal of Hydrogen Energy 2025年 137卷 1097-1106页

作者： Munawar, Tauseef Bashir, Ambreen Nisa, Mehar Un Alshgari, Razan A. Mukhtar, Faisal Mohammad, Saikh Ashiq, Muhammad Naeem Ehsan, Muhammad Fahad Iqbal, Faisal Allakhverdiev, Suleyman I. Guangzhou Institute of Energy Conversion Chinese Academy of Sciences No.2 Nengyuan Road Wushan Tianhe District Guangzhou510640 China Institute of Physics The Islamia University of Bahawalpur 63100 Pakistan Institute of Chemical Sciences Bahauddin Zakariya University Multan60800 Pakistan Department of Chemistry College of Science King Saud University Riyadh11451 Saudi Arabia Department of Civil and Environmental Engineering Northeastern University BostonMA02115 United States Controlled Photobiosynthesis Laboratory К.А. Timiryazev Institute of Plant Physiology RAS Botanicheskaya Street 35 Moscow127276 Russia Department of Molecular and Cell Biology Moscow Institute of Physics and Technology Institutsky Lane 9 Moscow region Dolgoprudny141700 Russia Faculty of Engineering and Natural Sciences Bahçeşehir University Istanbul Turkey

Highly efficient, abundant, and long-lasting electrocatalysts for oxygen evolution will be essential to industrial hydrogen production via water splitting. Hydrogen has emerged as an alternative to conventional fossil fuels, a sustainable and green energy source. Water electrolysis via co-doped metal oxides has been employed to reduce energy loss during electrochemical oxygen evolution reactions (OER), a great alternative to noble-metal-derived electrocatalysts. In the present work, Nd-dopped CeO2 (CeNdO2) nanostructures co-doped with rare earth metals are fabricated via sol-gel technique and analysed via state-of-the-art methods, focusing on structural, morphological, elemental, electrical and electronic capabilities. All fabricated samples were coated on nickel foam (NF) and fluorinated tin oxide (FTO) substrate for electrochemical splitting of water in a 1.0 M KOH. The Pr/Nd co-doped CeO2 grown on NF demonstrates high electrochemical activity with a significantly reduced OER overpotential of around 274 mV, Tafel slope around 84 mV/dec, and increased electrochemical surface area. This co-doped metal oxide nanostructure causes interactions with oxy-radicals (confirmed from XPS and Raman), which are thought to be source of easy charge transport and decrease overpotential. The least charge transfer resistance of Pr-doped CeNdO2/NF presented excellent electroactivity due to reduced polarization resistance between electrolyte and catalyst material. Additionally, for a practical water electrolysis system, the high stability of Pr doped CeNdO2/NF electrode was exposed by continuous cyclic voltammetry sweeps of electrolysis up to 1500 cycles. This work reveals a synergistic effect between metal atoms (Ce, Nd, and Pr) on nickel foam substrate, which is mainly responsible for electron transfer and well-balanced kinetics under beginning conditions. © 2024 Hydrogen Energy Publications LLC

关键词： Electrocatalysts

来源：评论

学校读者我要写书评

暂无评论

T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems

arXiv

引用

arXiv 2023年

作者： Wang, Ming Wang, Daling Wu, Wenfang Feng, Shi Zhang, Yifei School of Computer Science and Engineering Northeastern University Liaoning Shenyang110167 China Faculty of Mathematics and Computer Science University of Göttingen Niedersachsen Göttingen37077 Germany

To address the interpretability challenge in machine learning (ML) systems, counterfactual explanations (CEs) have emerged as a promising solution. CEs are unique as they provide workable suggestions to users, in addition to explaining why a certain outcome was predicted. The application of CEs encounters two main challenges: general user preferences and variable ML systems. User preferences tend to be general rather than specific, and CEs need to be adaptable to variable ML models while maintaining robustness even as these models change. Facing these challenges, we present a solution rooted in validated general user preferences, which are derived from thorough user research. We map these preferences to the properties of CEs. Additionally, we introduce a novel method, Tree-based Conditions Optional Links (T-COL), which incorporates two optional structures and multiple condition groups for generating CEs adaptable to general user preferences. Meanwhile, we employ T-COL to enhance the robustness of CEs with specific conditions, making them more valid even when the ML model is replaced. Our experimental comparisons under different user preferences show that T-COL outperforms all baselines, including Large Language Models which are shown to be able to generate counterfactuals. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Extended Coronavirus Optimization Algorithm for Trajectory Planning of a Model-Based Racing Track

An Extended Coronavirus Optimization Algorithm for Trajector...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Rana E. Aly Youmna A. Abu-Krisha Omar M. Fatehy Ahmed Y. Ali Catherine M. Elias Omar M. Shehata Multi-Robot Systems (MRS) Research Group Cairo Egypt Mechatronics Department Faculty of Engineering and Materials Science German University in Cairo Egypt

In light of the latest pandemic, many researchers proposed a nature-inspired Coronavirus algorithm to aid in tackling different optimization problems. Many meta-heuristic techniques were conducted to handle the trajectory planning of vehicles on track; however, no implementation or comparison is formulated using the aforementioned new technique. This paper proposes a modified version of the Coronavirus optimization algorithm to aid the drivers offline prior to entering the track. To ensure this algorithm's capability, a comparative study is conducted between the extended Coronavirus Optimization Algorithm (CVOA) and other meta-heuristic techniques such as: Genetic Algorithm (GA) and Grey Wolf Optimization Algorithm (GWO). Using MATLAB, two different tracks were visualized and the aforementioned techniques were employed to generate a feasible trajectory plan. All equations are represented using a real vehicle model to verify the algorithms' outputs with real case scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multi-Parametric Optimization for Mobility-Aware Scheduling of Electric Vehicles Charging Station

Hybrid Multi-Parametric Optimization for Mobility-Aware Sche...

引用

International Conference on Intelligent Transportation

作者： Silvana E. Guirguis E. I. Morgan Ahmed Elguindy Omar M. Shehata Multi-Robot Systems (MRS) Research Group Cairo Egypt Mechatronics Department Faculty of Engineering and Materials Science German University in Cairo Egypt Mechatronics Department Faculty of Engineering Ain Shams University Cairo Egypt

In the past few years, the significant increase of Electric Vehicles (EVs) in the global market has shed light upon the issue of their long charging time. One key challenge in this field is the EVs' charging scheduling in a station, for the purpose of maximizing the profitability of charging stations while minimizing the number of rejected vehicles due to in-frastructure constraints; thus considering customer satisfaction. Due to the permutation nature of the scheduling problem, non-permutation-based algorithms are incapable of solely solving it. Moreover, the literature mostly overlooks the charging priority of each EV based on its individual condition. To address this gap, an algorithm hybridizing a priority-based scheduling algorithm (PBA) with arithmetic meta-heuristic techniques; i.e. Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) is proposed. These algorithms; namely Genetic Multi-Parametric Optimization (GMPO) and Particle Swarm Multi-Parametric Optimization (PSMPO) respectively, are compared against permutation GA for performance evaluation. A case study is conducted on an EV charging station equipped with Photovoltaic (PV) panels and an Energy Storage System (ESS); where this equipment significantly enhanced the station's prof-itability. The results indicate the effectiveness of the proposed approach. Furthermore, GMPO mostly outperformed both PSMPO and GA in finding better solutions. Despite the higher time complexity of the proposed algorithms compared to GA, they reach convergence faster. This time delay is acceptable relative to the problem scale and the resulting accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dissolution and Structural Evolution of Yb2o3 in the Eutectic Lif-Ybf3 Molten Salt

SSRN

引用

SSRN 2023年

作者： Yongjian, Zhang Boqing, Cai Xu, Wang Ruixiang, Wang Zhongning, Shi Faculty of Materials Metallurgy and Chemistry Jiangxi University of Science and Technology Ganzhou341000 China School of Metallurgical Engineering Northeastern University Shenyang110006 China

Dissolution of Yb2O3 in a eutectic LiF–YbF3 system and the structural changes in the system are key factors in efficient electrolysis in preparing rare-earth Yb alloys. In this study, isothermal saturation was used to determine the solubilities of Yb2O3 in eutectic LiF and LiF–YbF3 molten salts. The interactions between the components of the LiF–YbF3–Yb2O3 system were studied using a combination of quantum chemical calculations, thermodynamic analysis, and experimental verification. The structural evolution of the system was analyzed using high-temperature Raman spectroscopy and ab initio molecular dynamics simulations during the integration of Yb2O3 into the eutectic LiF–YbF3 molten salt. The main phases in the LiF–(21 mol.%)YbF3 system saturated with Yb2O3 consisted of LiF, LiYbF4, and a minimal amount of YbOF and its derivatives. Yb2O3 did not change the main structure of the LiF–LiYbF4 system and Li+, F−, and YbF4− were the main ionic forms in the system. The Yb–F bond in YbOF was less stable than the Yb–O bond, and YbOF easily dissociated to YbO+ and F−. © 2023, The Authors. All rights reserved.

关键词： Raman spectroscopy

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：