检索结果-内蒙古大学图书馆

Action recognition through fusion of sEMG and skeletal data in feature level

Journal of Ambient Intelligence and Humanized Computing 2022年第9期13卷 4125-4134页

作者： Wang, Xinming Ding, Weili Bian, Shuangshuang Liu, Honghai Department of Automation Institute of Electrical Engineering Key Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Yanshan University 438 West of Hebei Avenue Haigang District Qinhuangdao066004 China School of Mechanical Engineering and Automation State Key Laboratory of Robotics and Systems Harbin Institute of Technology Shenzhen Nanshan District Shenzhen518055 China

Human action can be recognized through a unimodal way. However, the information obtained from a single mode is limited due to the fact that a single mode contains only one type of physical attribute. Therefore, it is motivational to improve the accuracy of actions through fusion of two different complementary modality, which are the surface electromyography (sEMG) and the skeletal data. In this paper, we propose a general framework of fusion of sEMG signals and skeletal data. Firstly, vector of locally aggregated descriptor (VLAD) was extracted from sEMG sequences and skeletal sequences, respectively. Secondly, features obtained from sEMG and skeletal data are mapped through different weighted kernels using multiple kernel learning. Finally, the classification results are obtained through the model of multiple kernel learning. A dataset of 18 types of human actions is collected via KinectV2 and Thalmic Myo armband to verify our ideas. The experimental results show that the accuracy of human action recognition are improved by combining skeletal data with sEMG signals. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Potentiodynamic study and microstructural evaluation of the corrosion behavior of mill scale and alumina reinforced aluminium metal matrix composites

Potentiodynamic study and microstructural evaluation of the ...

引用

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Adeolu A. Adediran Oreofeoluwa A. Mosadomi Peter P. Ikubanni Achile Nana Omolayo Ikumapayi Cynthia C. Nwaeju Immanuel O. Ojji Sunday A. Afolalu Department of Mechanical Engineering Landmark University Omu-Aran Kwara State Nigeria Mechanical Engineering Science University of Johannesburg South Africa CSIR-National Metallurgical Laboratory Jamshedpur India Department of Mechanical Engineering Afe Babalola University Ado-Ekiti Nigeria Department of Mechanical Engineering Nigeria Maritime University Okerenkoko Delta State Nigeria Department of Mechatronics and Robotics Demontfort University Leicester City United Kingdom

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

The current study reports the corrosion behavior of aluminium metal matrix composites (AMMCs) reinforced with mill scale (MS) and alumina (Al2O3) in a simulated marine environment (3.5 % NaCl solution). Electrochemical technique and optical microscopy were used to evaluate the corrosion behavior of the composites developed at varying weight ratios of MS (0, 2, 4, 6, 8) and Al2O3 (0, 2, 4, 6, 8) respectively. From the results obtained, the average grain size of the composites after exposure to the marine environment varies significantly. Sample A showed an average grain size of 55.02 µm, B - 26.85 µm, C - 28.12 µm, D - 27.03 µm, E - 32.31 µm and F (control) - 37.02 µm. The contributory influence of the reinforcing materials is evident in the variation noted in the average grain sizes. Their presence acts as active sites for corrosion initiation. The oxidation of metal ions causes severe pitting with sample C having the optimum corrosion rate of 0.9532 mm/yr and sample D showing the least corrosion rate of 0.6188 mm/yr. The morphology of the corroded surfaces confirms the presence of pitting corrosion on the composites developed.

关键词： Grain size Optical microscopy Corrosion Microscopy Aluminum Surface morphology Morphology

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Estimation of Shape and Force along Highly Deformable Surgical Manipulators Using Sparse FBG Measurement

Simultaneous Estimation of Shape and Force along Highly Defo...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Yiang Lu Bin Li Wei Chen Junyan Yan Shing Shin Cheng Jiangliu Wang Jianshu Zhou Qi Dou Yun-Hui Liu Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Hong Kong Center for Logistics Robotics Hong Kong Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Recently, fiber optic sensors such as fiber Bragg gratings (FBGs) have been widely investigated for shape reconstruction and force estimation of flexible surgical robots. However, most existing approaches need precise model parameters of FBGs inside the fiber and their alignments with the flexible robots for accurate sensing results. Another challenge lies in online acquiring external forces at arbitrary locations along the flexible robots, which is highly required when with large deflections in robotic surgery. In this paper, we propose a novel data-driven paradigm for simultaneous estimation of shape and force along highly deformable flexible robots by using sparse strain measurement from a single-core FBG fiber. A thin-walled soft sensing tube helically embedded with FBG sensors is designed for a robotic-assisted flexible ureteroscope with large deflection up to 270° and a bend radius under 10 mm. We introduce and study three learning models by incorporating spatial strain encoders, and compare their performances in both free space without interactions as well as constrained environments with contact forces at different locations. The experimental results in terms of dynamic shape-force sensing accuracy demonstrate the effectiveness and superiority of the proposed methods.

关键词： Optical fiber sensors Shape Soft sensors Force Estimation Robot sensing systems Fiber gratings

来源：评论

学校读者我要写书评

暂无评论

Robustness Evaluation of Pre-trained vs. Fine-Tuned Computer Vision Models for Score Detection in Dynamic Sports Environments 14th

Robustness Evaluation of Pre-trained vs. Fine-Tuned Computer...

引用

14th International Conference on Information Society and Technology, ICIST 2024

作者： Ivačko, Nikola Ćirić, Ivan Dimitrijević, Nikola Mitić, Dimitrije Milošević, Maša Kitić, Ana Krstić, Dušan Department of Mechatronics and Control Faculty of Mechanical Engineering University of Niš Aleksandra Medvedeva 14 Niš18000 Serbia Faculty of Information Technologies Belgrade Metropolitan University Belgrade Serbia Faculty of Electrical Engineering University of Niš Aleksandra Medvedeva 14 Niš18000 Serbia NAIS ROBOTICS D.O.O Aleksandra Medvedeva bb Niš Serbia

ISBN: (纸本)9783031714184

This paper explores the efficacy of two distinct approaches in computer vision, particularly in intelligent sports training systems. Our focus is on the development and comparison of two methodologies for image recognition in a basketball score detection system, named "Koško." The first approach uses a pre-trained model with two combined datasets in the training phase. This method leverages diverse data to enhance the model’s ability to generalize and accurately recognize scores in basketball games. In contrast, the second approach fine-tunes a model initially trained on one dataset with a subsequent second dataset. Rooted in recent transfer learning studies, this method shows that selectively fine-tuning a subset of layers or customizing learning rates can significantly improve robustness to out-of-distribution (OOD) data. By enforcing weight projections, this approach aims to maintain the generalization capabilities of the pre-trained models while adapting to the new dataset. Our research balances precise score detection and pragmatic system development, contributing to intelligent sports training systems. This work highlights the feasibility of combining machine learning and vision-based methodologies to advance sports training systems. Research on basketball score detection using the YOLOv8n model shows the pre-trained model achieved 93.75% accuracy and a 3% false positive rate, outperforming the fine-tuned model’s 88.71% accuracy and 5% false positive rate. By evaluating both networks, this study aims to provide clear strategies for implementing computer vision systems in sports, particularly in the dynamic environment of basketball. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Basketball

来源：评论

学校读者我要写书评

暂无评论

Learning to Refine Input Constrained Control Barrier Functions via Uncertainty-Aware Online Parameter Adaptation

arXiv

引用

arXiv 2024年

作者： Kim, Taekyung Kee, Robin Inho Panagou, Dimitra Department of Robotics University of Michigan Ann ArborMI48109 United States Department of Mechanical Engineering University of Michigan Ann ArborMI48109 United States Department of Robotics Department of Aerospace Engineering University of Michigan Ann ArborMI48109 United States

Control Barrier Functions (CBFs) have become powerful tools for ensuring safety in nonlinear systems. However, finding valid CBFs that guarantee persistent safety and feasibility remains an open challenge, especially in systems with input constraints. Traditional approaches often rely on manually tuning the parameters of the class K functions of the CBF conditions a priori. The performance of CBFbased controllers is highly sensitive to these fixed parameters, potentially leading to overly conservative behavior or safety violations. To overcome these issues, this paper introduces a learning-based optimal control framework for online adaptation of Input Constrained CBF (ICCBF) parameters in discrete-time nonlinear systems. Our method employs a probabilistic ensemble neural network to predict the performance and risk metrics, as defined in this work, for candidate parameters, accounting for both epistemic and aleatoric uncertainties. We propose a two-step verification process using Jensen-Rényi Divergence and distributionally-robust Conditional Value at Risk to identify valid parameters. This enables dynamic refinement of ICCBF parameters based on current state and nearby environments, optimizing performance while ensuring safety within the verified parameter set. Experimental results demonstrate that our method outperforms both fixed-parameter and existing adaptive methods in robot navigation scenarios across safety and performance metrics. [Project Page]1 [Code] [Video] © 2024, CC BY.

关键词： Discrete time control systems

来源：评论

学校读者我要写书评

暂无评论

Development of a Gesture Analysis System for Human System Interaction

Development of a Gesture Analysis System for Human System In...

引用

International Symposium on Soft Computing and Intelligent Systems (SCIS)

作者： Chifuyu Matsumoto Yuka Sone Jinseok Woo Yasuhiro Ohyama Sustainable Engineering Program Graduate School of Engineering Tokyo University of Technology Hachioji Tokyo Japan Department of Mechanical Engineering School of Engineering Tokyo University of Technology Hachioji Tokyo Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

Recently, Japan has been facing various social issues, and to solve these problems, it is necessary to create a society where diverse people can live comfortably. To build such a society, appropriate support tailored to individuals is required, necessitating the analysis of various types of information to understand the people's needs at any given moment. In particular, analyzing non-verbal elements such as posture, facial expressions, and gestures is crucial, as these naturally indicate a person's condition. Therefore, this study focuses on human gestures, one of the non-verbal elements, and proposes a gesture recognition method using Dynamic Time Warping (DTW) and K-Means. We demonstrated that symbolic gesture recognition is possible by recording arm trajectories from skeletal measurements with an RGB-D camera.

关键词： Shape Time series analysis Gesture recognition Cameras Trajectory Recording

来源：评论

学校读者我要写书评

暂无评论

Transport and magnetic properties of Hund's metal CaRuO3 under strain modulation

引用

Physical Review B 2024年第4期110卷 L041403-L041403页

作者： Zhen Wang Arjyama Bordoloi Zhaoqing Ding Enling Wang Xiaofeng Wu Zeguo Lin Mingyu Yang Chenxu Liu Jinglin Zhou Meng Meng Fang Yang Qinghua Zhang Xiaoran Liu Sobhit Singh Huan-hua Wang Jiandong Guo Beijing National Laboratory for Condensed Matter Physics and School of Nuclear Science and Technology Department of Mechanical Engineering School of Physical Sciences Materials Science Program

We synthesized CaRuO3 (001) thin films on a set of substrates and investigated their electronic and magnetic properties via combining magnetotransport measurements with first-principles density-functional theory calculations. The experimental results indicate that a moderate strain can introduce the Kondo effect in the system, leading to a significant modulation of the non-Fermi liquid behavior. Moreover, when the strain reaches a certain threshold, the system undergoes a metal-semiconductor transition, accompanied by a transition from a nonmagnetic state to a plausible G-type antiferromagnetic state. We attribute the observed phenomena in CaRuO3 to strain-induced disruption of the delicate balance between the itinerant and the local Ru 4d electrons. These findings shed light on the intriguing magnetic and non-Fermi liquid behavior of CaRuO3, systematically tailored by heteroepitaxial strain.

关键词： Density of states Kondo effect Transport phenomena Ruthenates Ultrathin films Density functional calculations Physical deposition Resistivity measurements Strain engineering X-ray diffraction X-ray reflectivity

来源：评论

学校读者我要写书评

暂无评论

Diagnostic of Injury Risk in the Anterior Cruciate Ligament Based on Shape Context Description of the Intercondylar Notch Curvature

引用

Journal of engineering and Science in Medical Diagnostics and Therapy 2022年第2期5卷 021001页

作者： Dias, Joaõ Paulo Bhuiyan, Ariful Shamim, Nabila Department of Civil and Mechanical Engineering Shippensburg University of Pennsylvania 1871 Old Main Drive ShippensburgPA17257 United States Mechanical Engineering Program University of Houston Clear Lake 2700 Bay Area Blvd. HoustonTX77058 United States Department of Chemical Engineering Prairie View AandM University 100 University Drive Prairie ViewTX77446 United States

An estimated number of 300,000 new anterior cruciate ligament (ACL) injuries occur each year in the United States. Recent studies have pointed out a correlation between the curvature of the femur intercondylar notch and the risk of noncontact ACL injury. Although several magnetic resonance (MR) imaging-based ACL diagnostics methods have already been proposed in the literature, most of them are based on machine learning or deep learning strategies, which are computationally expensive. In this paper, we propose a diagnostics framework for the risk of injury in the ACL based on the application of the inner-distance shape context (IDSC) to describe the curvature of the intercondylar notch from MR images. First, the contours of the intercondylar notch curvature from 91 MR images of the distal end of the femur (70 healthy and 21 with confirmed ACL injury) were extracted manually using standard image processing tools. Next, the IDSC was applied to calculate the similarity factor between the extracted contours and reference standard curvatures. Finally, probability density functions of the similarity factor data were obtained through parametric statistical inference, and the accuracy of the ACL injury risk diagnostics framework was assessed using receiver operating characteristic analysis (ROC). The overall results for the area under the curve (AUC) showed that the method reached a maximum accuracy of about 66%. Furthermore, the sensitivity and specificity results showed that an optimum discrimination threshold value for the similarity factor can be pursued that minimizes the incidence of false positives and false negatives simultaneously. © 2022 American Society of mechanical Engineers (ASME). All rights reserved.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Co3O4@ZnO binary oxide microstructures for high-performance photoelectrochemical glucose sensing

引用

Ceramics International 2025年

作者： Hilal, Muhammad Ali, Yasir Fayaz, Huma Cai, Zhicheng Kim, Hyojung Abdo, Hany S. Alnaser, Ibrahim A. Department of Semiconductor System Engineering Sejong University Seoul05006 Korea Republic of Department of Mechanical Robotics and Energy Engineering Dongguk University Seoul04620 Korea Republic of Deanship of Scientific Research King Saud University Riyadh11421 Saudi Arabia

Binary metal oxides with hierarchical architectures have emerged as promising platforms for non-enzymatic glucose sensing due to their tunable optoelectronic properties and intrinsic redox activity. In this work, we report a sustainable, additive-free synthesis of a 3D Co3O4@ZnO heterostructure via a one-pot hydrothermal method followed by inert-gas calcination, effectively minimizing oxygen interference and preserving structural integrity. The composite integrates the redox-rich, narrow-bandgap Co3O4 with UV-active, high-mobility ZnO to form a type-II heterojunction that enables broad-spectrum light absorption, efficient charge separation, and suppressed carrier recombination. These features also enhance the electrochemical behavior of the material, yielding an ultra-low charge transfer resistance (Rct = 3.35 Ω) and facilitating rapid electron transport and ion diffusion at the electrode/electrolyte interface. As a result, the Co3O4@ZnO heterostructure supports high-performance dual-mode glucose sensing under both dark and illuminated conditions. In the absence of light, the sensor exhibits a sensitivity of 114 μA cm−2 mM−1, a wide linear range (0.2–4 mM), and a fast response time (21 s). Upon illumination, a photoinduced internal electric field at the heterojunction interface significantly boosts performance, achieving a photoelectrochemical sensitivity of 231 μA cm−2 mM−1 with a rapid response of 11 s. Photocurrent studies further reveal response and recovery times of 5 s and 4 s, respectively. Importantly, the sensor also demonstrates reliable glucose detection in real urine samples, confirming its suitability for real-time physiological monitoring. These results highlight the Co3O4@ZnO heterostructure as an efficient and eco-friendly platform for stable, reliable, and high-performance dual-mode glucose sensing. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Redox reactions

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Impedance Matching Approach (NIMA) for Robust Haptic Rendering During Robotic Laparoscopy Surgery

Nonlinear Impedance Matching Approach (NIMA) for Robust Hapt...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Aiden Mazidi Andrés C. Ramos Amir Sayadi Javad Dargahi Jake Barralet Liane S. Feldman Amir Hooshiar Mechanical Engineering Department Surgical Robotics Laboratory Concordia University Montreal QC Canada Surgical Performance Enhancement and Robotics (SuPER) Centre Department of Surgery McGill University Montreal QC Canada

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

The long overdue clinical need for haptic-enabled surgical robotic systems has been poorly addressed in the past two decades. Haptic systems have shown high agility and precision, which can translate into less risk to patients. However, regulatory requirements, such as validating haptic systems as “human-in-the-loop” components have impeded their commercialization. The complexity of regulatory validation arises from the “human-in-the-loop” design of the system that complicates the validation of inter-subject dynamics variations. In this study, we have implemented an Impedance Matching Approach (IMA) for force feedback estimation and rendering that does not include the “human” in the loop as a component. In other words, the amount of force feedback rendered at the haptic device does not essentially rely on the human to adequately “resist” the motion of the haptic device. This feature makes our proposed method intrinsically safe against the haptic “kick” which commonly happens if the surgeon releases the handle of the haptic interface while rendering non-zero forces. We have previously shown the accuracy and stability of the linear IMA method for single-force components [1]. In addition, we have implemented a general Non-linear IMA (NIMA) framework that accounts for the impedance parameters when the instrument-tissue interaction is not linear. We now present successful test results on the accuracy of the NIMA method with 3D contact forces and motion commands in a robot-assisted laparoscopy environment.

关键词： Accuracy Torque Three-dimensional displays Biological system modeling Impedance matching Force feedback Resists Rendering (computer graphics) Human in the loop Stability analysis

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：