检索结果-内蒙古大学图书馆

2024 International Convention on Rehabilitation engineering and Assistive Technology and World Rehabilitation Robot Convention, i-CREATE and WRRC 2024

作者： Cao, Wujing Guo, Xinqiang Zou, Yupeng Zhang, Shuo Luo, Mingxiang Kobsiriphat, Worawarit Wu, Xinyu Yin, Meng Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518005 China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society SIAT-CUHK Joint Laboratory of Robotics and Intelligent Systems China School of Mechanical Engineering China University of Petroleum China National Metal and Materials Technology Center Thailand

ISBN: (纸本)9798350355123

Stroke, as one of the leading causes of long-term disability globally, often results in motor impairments, particularly in the hands, significantly affecting patients' daily activities and causing profound psychological trauma. Rehabilitation gesture recognition, as one of the key means of active rehabilitation medicine, holds significant potential in stroke rehabilitation, providing real-time feedback on patient progress and enabling personalized interventions to meet individual needs. Traditional gesture recognition methods face numerous challenges when dealing with stroke patient data, such as noise, motion blur, and individual differences. To address these challenges, this paper proposes a novel approach for stroke patient gesture recognition using deep learning models. We adopt a strategy combining denoising autoencoder (DAE), convolutional neural network (CNN), and long short-term memory (LSTM) to enhance the accurate recognition of hand movements in stroke patients. Specifically, DAE is utilized for denoising EMG signals, extracting features, and reducing noise to improve the signal's noise resistance. CNN is employed for spatial feature extraction, while LSTM captures temporal dependencies in gesture sequences. By integrating these three deep learning models, our aim is to enhance the accuracy and robustness of rehabilitation gesture recognition. We validate the proposed method's effectiveness on an EMG dataset from seven subjects through experiments and compare it with traditional machine learning and individual CNN and LSTM algorithms. Experimental results demonstrate significant performance improvements of our hybrid model in rehabilitation gesture recognition tasks, indicating promising application prospects and practical significance. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

High-precision trajectory calibration for robot surface machining by meta-heuristic search algorithm from local error in machining area

引用

International Journal of advanced Manufacturing Technology 2025年第5期138卷 2281-2295页

作者： Bi, Guangde Lu, Lei Zhang, Lei Fan, Cheng Sun, Lining School of Mechanical and Electric Engineering Jiangsu Provincial Key Laboratory of Advanced Robotics Soochow University Suzhou215123 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

Industrial robots used in complex surface machining are gradually increasing because of their high flexibility and large workspace. However, due to their low geometric accuracy, their application in high-precision surface machining is hindered. In order to improve the machining accuracy, a high-precision robot trajectory calibration method for complex surface machining is proposed. In the machining process, the machining trajectory is usually only within a certain machining area. In the method, high-precision standard balls are set at the boundary of the machining area. Based on the precise position information of these standard balls, the trajectory of the robot in the machining area is calibrated. Compared with the global robot calibration method, the proposed method can calibrate the robot trajectory in the machining area through standard parts, which will improve the trajectory accuracy of the machining robot to the level of repeated positioning accuracy. In this method, a large amount of standard ball data is obtained by the in-place measuring device before the machining process. Then, based on these data, a meta-heuristic search algorithm is used to calibrate the kinematic deviation of the robot measurement and the machining system. The trajectory of the machining robot is adjusted by the kinematic deviation after calibration, and it is applied to the motion control of the machining process to improve the positioning accuracy of the machining trajectory. In the end, to verify the accuracy and practicability of the machining trajectory obtained by this method, measurement and machining experiments are carried out. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Channel-distribution Hybrid Deep Learning for sEMG-based Gesture Recognition

Channel-distribution Hybrid Deep Learning for sEMG-based Ges...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Lu, Keyi Guo, Hao Qi, Fei Gong, Peihao Gu, Zhihao Sun, Lining Huang, Haibo School of Mechanical and Electric Engineering Jiangsu Provincial Key Laboratory of Advanced Robotics Soochow University Suzhou215123 China School of Mechanical and Electric Engineering Soochow University Suzhou215123 China

ISBN: (纸本)9781665481090

In recent years, CNNs (Convolutional Neural Networks) with their powerful feature representation and feature learning capabilities, have played an important role in gesture recognition tasks based on sparse multichannel surface EMG signals. As each muscle group in the upper limb plays a different role in a particular hand movement, we propose a hybrid CNN model that considers the spatial distribution of muscle groups in the myoelectric channel to improve the accuracy of hand gesture recognition. The model takes the spectrogram of CWT (Continuous Wavelet Transform) as input, based on the spatial distribution of channels, decomposes all channels into multiple input streams, lets the CNN learn the features of each stream separately, and gradually fuses (slowly fusion) the features learned by each stream, and then performs gesture classification. Finally, the results of several of these stream-division methods are fused for decision making to obtain classification accuracies. The proposed model was validated and tested on the Nina Pro DB4 dataset, and the average accuracy was improved compared to both traditional machine learning methods and multi-stream CNN models that do not take into account the spatial distribution of channels. © 2022 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Toward broad optimal output bandwidth dielectric elastomer actuators

引用

Science China(Technological Sciences) 2022年第5期65卷 1137-1148页

作者： CAO ChongJing CHEN LiJin LI Bo CHEN GuiMin NIE ZeDong WANG Lei GAO Xing Research Centre for Medical Robotics and Minimally Invasive Surgical Devices Shenzhen Institute of Advanced Technology(SIAT)Chinese Academy of SciencesShenzhen518055China Shaanxi Key Laboratory of Intelligent Robots School of Mechanical EngineeringXi’an Jiaotong UniversityXi’an710049China

Dielectric elastomer actuators(DEAs)are one of the most promising soft actuation technologies owing to their relatively high power density and electromechanical efficiency enabled by a resonant actuation ***,existing DEA designs suffer from a very narrow optimal output bandwidth close to resonance and poor output control capability due to their fixed geometrical *** condition greatly limits their applications in programmable actuation and broad-bandwidth ***,this work developed a novel resonance tunable DEA(RTDEA)design for broad-optimal-output actuation bandwidths that is enabled by an integration of a stiffness and voltage control *** design features a broad resonant frequency adjustment from 84 to 126 Hz and independent tunings of its resonant amplitude and *** studies were conducted to illustrate the fundamental principles behind the resonance tuning strategy,and optimization was performed to maximize the tuning ***,a resonance tuning control strategy is proposed to achieve accurate adjustments of the RTDEA’s resonance based on the stiffness and voltage control *** resonance tunable soft actuators are envisioned to greatly expand DEAs’applications in,for instance,soft robotic locomotion,human–robot communication,and active vibrational control with demands of broad actuation bandwidths and high output performance.

关键词： dielectric elastomer actuators soft robotics soft actuators resonance tuning resonant actuation

来源：评论

学校读者我要写书评

暂无评论

An Information Model with Voxelated Data from Computer Aided Systems and the Additive Manufacturing Workflow 15

An Information Model with Voxelated Data from Computer Aided...

引用

15th CIRP Conference on Intelligent Computation in Manufacturing engineering, ICME 2021

作者： Maguire, Conor George, Abraham Kelly, Matthew Egan, Darragh Dowling, Denis Papakostas, Nikolaos Laboratory for Advanced Manufacturing Simulation and Robotics School of Mechanical and Materials Engineering University College Dublin Ireland I-Form Advanced Manufacturing Research Centre School of Mechanical and Materials Engineering University College Dublin BelfieldDublin 4 Ireland

This paper discusses diverse data management approaches and proposes a comprehensive information model that is built from voxelated data from across the Additive Manufacturing and Computer Aided (AM - CAx) platforms workflow. The information model is developed using discretisation and data management techniques to provide a robust method of managing and structuring the product / process data throughout the AM - CAx domain. The result is a voxelated representation of the design, manufacturing, in-situ process data and quality control stages of an AM build within a single Hierarchical Data Format (HDF5) file. Demo files were developed for two different AM processes during this work. With further research and by applying statistical methods or machine learning techniques, it would then be possible to filter through and potentially predict the optimal process parameters required for an AM build. The comprehensive information model is designed to provide insight to track changes along the AM process flow. © 2022 The Author(s).

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

Framework for monitoring electric vehicle battery second life health and estimating remaining useful life

引用

Procedia CIRP 2025年 132卷 209-214页

作者： Mohammad Rajabzadeh Vincent Hargaden Pezhman Ghadimi Christoph F. Strnadl Nikolaos Papakostas Laboratory for Advanced Manufacturing Simulation and Robotics School of Mechanical & Materials Engineering University College Dublin Belfield Dublin Ireland IOTA Foundation 10437 Berlin Germany

The rapid development of electric vehicles has led to the increasingly important role of lithium batteries in the field of performance sources. New technologies make people become more environmentally conscious and switch from buying to controlling electric vehicle life cycles. The mass production of lithium batteries may lead to environmentally friendly transportation. However, traditional lithium battery manufacturers and government policies often focus on the production and recycling phases. The challenges for battery life cycle management and circular economy are increasingly complex and diverse. This paper presents a comprehensive framework for the secondary utilization of lithium batteries by discussing battery aging, monitoring, recycling, secondary use, and lithium battery health prediction. As a result, multiple algorithms were used to evaluate their effectiveness in battery performance prediction. The analysis of the experiments’ results revealed the importance of data pre-processing in improving predictive accuracy, the dependence of model selection on data adaptability, and the need for continuous adjustments during the predictive modeling process.

关键词： Sustainability Lithium batteries Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Functional Materials and Innovative Strategies for Wearable Thermal Management Applications

引用

Nano-Micro Letters 2023年第9期15卷 562-603页

作者： Yeongju Jung Minwoo Kim Taegyeom Kim Jiyong Ahn Jinwoo Lee Seung Hwan Ko Applied Nano and Thermal Science Lab Department of Mechanical EngineeringSeoul National University1 Gwanak-roGwanak-guSeoul 08826South Korea Department of Mechanical Roboticsand Energy EngineeringDongguk University30 Pildong-ro 1-gilJung-guSeoul 04620South Korea Institute of Advanced Machinery and Design(SNU-IAMD) Seoul National UniversityGwanak-roGwanak-guSeoul 08826South Korea Institute of Engineering Research Seoul National University1 Gwanak-roGwanak-guSeoul 08826South Korea

Thermal management is essential in our body as it affects various bodily functions,ranging from thermal discomfort to serious organ failures,as an example of the worst-case *** have been extensive studies about wearable materials and devices that augment thermoregulatory functionalities in our body,employing diverse materials and systematic approaches to attaining thermal *** paper reviews the recent progress of functional materials and devices that contribute to thermoregulatory wearables,particularly emphasizing the strategic methodology to regulate body *** exist several methods to promote personal thermal management in a wearable *** instance,we can impede heat transfer using a thermally insulating material with extremely low thermal conductivity or directly cool and heat the skin ***,we classify many studies into two branches,passive and active thermal management modes,which are further subdivided into specific *** from discussing the strategies and their mechanisms,we also identify the weaknesses of each strategy and scrutinize its potential direction that studies should follow to make substantial contributions to future thermal regulatory wearable industries.

关键词： Thermal management Passive heat transfer Active heat transfer Wearable materials Wearable device

来源：评论

学校读者我要写书评

暂无评论

Multi-particles micromanipulation in focused sound field for single-beam acoustic tweezer

Multi-particles micromanipulation in focused sound field for...

引用

2024 International Conference on Mechatronic engineering and Artificial Intelligence, MEAI 2024

作者： Zhu, Guolong Li, Bo Xu, Junlei Zhang, Lue Sun, Lining School of Mechanical and Electric Engineering Jiangsu Provincial Key Laboratory of Advanced Robotics Soochow University Suzhou215137 China

ISBN: (纸本)9781510689176

In this paper, for the prediction of sound field distribution, a spherical piezoelectric transducer is designed for focused acoustic field according to piezoelectricity equation and vibration analysis. Based on the predicted acoustic fields distribution, the Acoustic Radiation Force(ARF) of the particles with different material and different sizes are obtained, according to a perturbation expansion of the acoustic fields in fluid. Besides, the trapping and micro-manipulation of particles are realized perpendicular to the acoustic axis through experimental according to the predicted ARF. © 2025 SPIE.

关键词： Acoustic fields

来源：评论

学校读者我要写书评

暂无评论

Development of a low-cost microfluidic chip for hyaluronidase-free oocyte denudation in mammals

引用

Biotechnology Notes 2025年 6卷 133-142页

作者： Dessouky, Ashraf Hisham El-Hussieny, Haitham El-Sherry, Taymour Mohammed Parque, Victor Fath El-Bab, Ahmed M.R. Department of Mechatronics and Robotics Engineering Egypt-Japan University of Science and Technology (E-JUST) Alexandria Alexandria 21934 Egypt Mechanical Engineering Department Helwan University Cairo Cairo 11792 Egypt Department of Theriogenology Veterinary Hospital Faculty of Veterinary Medicine Assiut University Assiut Assiut Egypt of Advanced Science and Engineering Hiroshima University Hiroshima HigashiHiroshima 739-8527 Japan

Infertility in mammals is one of the most intricate medical issues requiring non-traditional interventions. In Vitro Fertilization (IVF) is one of the modern medical technologies currently used to treat infertility. However, current IVF procedures are inaccessible and unaffordable to the majority due to the high cost, the complexity of the procedure, and the reliance on highly qualified operators. For successful IVF, oocyte denudation, the process of removing cumulus cells from oocytes, is often performed. Here, microfluidics offers the potential to enhance denudation procedures and to minimize operator variability. In this paper, we propose the configuration of a microfluidic chip for oocyte denudation whose structure hybridizes inner jagged surfaces and expansion units. The jagged surface units have the role of removing the cumulus cells surrounding the oocyte by using the wall shear stress principle, and the (rounded) expansion units have the role of rotating the cumulus cells for further deployment in subsequent jagged surfaces. The proposed device can be manufactured at a low cost (<1 USD)) by the engraving of CO₂ laser machine on PMMA material, and is able to circumvent the use of enzymatic components such as hyaluronidase. Experiments using computational simulations and manufactured microfluidic chips evaluated distinct geometry configurations of the jagged surfaces and identified the suitable flow rates for maximal shear stress and denudation performance. Manufactured samples of the proposed microfluidic devices have shown the denudation performance of 96.7 % and yield rate of 90 % at a constant flow rate of 1 ml/min. © 2025 The Authors

关键词： CO2 laser In vitro fertilization Microfluidics Oocyte denudation

来源：评论

学校读者我要写书评

暂无评论

Coverage Path Planning of Agricultural Spraying Drones with Graph Convolutional Network

Coverage Path Planning of Agricultural Spraying Drones with ...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Amirmasood Khaloujini Amin Talaeizadeh Alireza Taheri Aria Alastya Advanced Research Lab for Control and Agricultural Robotics Department of Mechanical Engineering Social and Cognitive Robotics Lab. Sharif University of Technology Tehran Iran

ISBN: (数字)9798331529734

ISBN: (纸本)9798331529741

Optimal route planning for autonomous robots is a crucial element of contemporary agriculture, especially for activities like spraying and pollination. This paper presents a Graph Convolutional Network (GCN) model especially developed to address the Coverage Path Planning (CPP). The aim of this paper is to convert the CPP problem into a Traveling Salesman Problem (TSP), so that by solving the TSP using the proposed neural network, an optimal route can be extracted for each agricultural field in the shortest possible time and with sufficient accuracy, ensuring full coverage of the field's area. The proposed model is a GCN, augmented with a transformer layer and a Multi-Layer Perceptron (MLP), was trained using datasets produced by a Genetic Algorithm (GA) Method. The model obtained a network error of 0.12 while solving TSP cases with 20 points. It showed robust generalization skills, as evidenced by validation and test errors of 0.1261 and 0.1264, respectively. Significantly, the GCN model reduces the solution time to approximately one-tenth compared to conventional approaches, a benefit that increases as the number of points increases. The effectiveness of the model in producing ideal coverage routes highlights its potential for wider use in optimization and coverage path planning, especially in dynamic and extensive agricultural environments.

关键词： Training Accuracy Graph convolutional networks Neural networks Spraying Traveling salesman problems Transformers Path planning Vehicle dynamics Genetic algorithms

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：