检索结果-内蒙古大学图书馆

Annual IEEE Symposium on Computer-Based Medical systems

作者： Dan Li Xuechen Li Zhibin Peng Wenting Chen Linlin Shen Guangyao Wu Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology ShenZhen University Shenzhen China City University of Hong Kong Hong Kong SAR China Shenzhen Institute of Artificial Intelligence & Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University General Hospital

In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fractional Kelvin-Voigt based Viscoelastic Control for self-Balancing Exoskeleton

Fractional Kelvin-Voigt based Viscoelastic Control for self-...

引用

IEEE International Conference on robotics and Biomimetics

作者： Wentao Li Feng Li Ming Yang Jinke Li Ming Li Yuanpei Zhu Meng Yin Dingkui Tian Xinyu Wu Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Science and Technology of China Hefei China

Self-balancing exoskeleton robots enable hands-free walking for the wearer, and the problem of its stable walking has been a challenge. In this paper, to achieve compliant and stable walking of a self-balancing exoskeleton robot and reduce the shock between the robot and the ground, we propose a new fractional kelvin voigt viscoelastic controller (FKVC). The proposed FKVC incorporates the advantages of fractional order and the kelvin voigt viscoelastic to endow the self-balancing exoskeleton with stable and dynamic walking capabilities. Simulation results show that the actual CoM position of the exoskeleton well tracks the reference CoM position, and the actual ZMP converges to the reference ZMP position. The ZMP is always within the effective support region of the biped. Therefore, we experimentally proved the practicality and effectiveness of the FKVC method, and the self-balancing exoskeleton successfully realizes stable dynamic walking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fragment Distance-Guided Dual-Stream Learning for Automatic Pelvic Fracture Segmentation

SSRN

引用

SSRN 2024年

作者： Zeng, Bolun Wang, Huixiang Joskowicz, Leo Chen, Xiaojun Institute of Biomedical Manufacturing and Life Quality Engineering State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Department of Orthopedics National Center for Orthopedics Shanghai Sixth People’s Hospital Shanghai Jiao Tong University School of Medicine Shanghai China School of Computer Science and Engineering Edmond and Lily Safra Center for Brain Sciences Hebrew University of Jerusalem Jerusalem Israel Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Pelvic fracture is a complex and severe injury. Accurate diagnosis and treatment planning require the segmentation of the pelvic structure and the fractured fragments from preoperative CT scans. However, this segmentation is a challenging task, as the fragments from a pelvic fracture typically exhibit considerable variability and irregularity in the morphologies, locations, and quantities. In this study, a novel dual-stream learning framework is proposed for the automatic segmentation and category labeling of pelvic fractures. First, we develop a dual-branch architecture leveraging distance learning from bone fragments for enhanced spatial information, aiding in fracture segmentation and improving the identification of bone fragments with variable positioning. Second, we implement a multi-size feature fusion module that adaptively aggregates features from diverse receptive fields tailored to targets of different sizes and shapes, thus boosting segmentation performance. Extensive experiments on two pelvic fracture datasets from different medical centers demonstrated the accuracy and generalizability of the proposed method. It achieves a mean Dice coefficient and mean F1-score of 0.935[[EQUATION]]0.068 and 0.930[[EQUATION]]0.057 in the dataset FracCLINIC, and 0.955[[EQUATION]]0.072 and 0.912[[EQUATION]]0.129 in the dataset FracSegData, which are superior than other comparing methods. Our method optimizes the process of pelvic fracture segmentation, potentially serving as an effective tool for preoperative planning in the clinical management of pelvic fractures. © 2024, The Authors. All rights reserved.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Time-Optimal Trajectory Planning Based on Dynamics for Industrial Robot 5

Time-Optimal Trajectory Planning Based on Dynamics for Indus...

引用

5th International Conference on Automation, Control and robotics engineering, CACRE 2020

作者： Wang, Rundong Kong, Minxiu Cheng, Yanchun Castellani, Marco Harbin Institute of Technology State Key Laboratory of Robotics and System School of Mechatronics Engineering Harbin China University of Birmingham Department of Mechanical Engineering Birmingham United Kingdom

ISBN: (纸本)9781728198880

Given the trajectory of the industrial robot in Cartesian space, the existing methods only consider the kinematic constraints when optimizing the time trajectory planning, and ignore the maximum driving ability of the motor, which is likely to cause an overrun alarm and greatly reduce the trajectory accuracy. Therefore, this paper studies the time-optimal trajectory planning algorithm based on dynamics. Firstly, the algorithm discretizes the path, calculates the Cartesian coordinates of each discrete point and the differential about the path length. Then, this algorithm considers the constraints of dynamics and kinematics, uses the principle of linear programming, recursively calculates the upper limit value of speed and the maximum acceleration value at each discrete point, and calculates the speed value at each discrete point and keeps it within its allowable ranges. Finally, this algorithm uses the speed to calculate the corresponding time of each discrete point, and according to the interpolation period, outputs the path position of each period, the position and orientation in the Cartesian space and joint parameters. The MATLAB program is written to verify the feasibility and efficiency of the algorithm. © 2020 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Provably Convergent Federated Trilevel Learning

arXiv

引用

arXiv 2023年

作者： Jiao, Yang Yang, Kai Wu, Tiancheng Jian, Chengtao Huang, Jianwei Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach;2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes µ-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed µ-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the µ-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain ϵ-stationary point is upper bounded by (Formula Presented). Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80%. Copyright © 2023, 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

Filter algorithm based on cochlear mechanics and neuron filter mechanism and application on enhancement of audio signals

引用

Journal of Central South University 2021年第6期28卷 1813-1828页

作者： GAO Wa KAN Yue ZHA Fu-sheng College of Furnishings and Industrial Design Nanjing Forestry UniversityNanjing 210037China School of Mechanical and Power Engineering Henan Polytechnic UniversityJiaozuo 454003China The State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

A filter algorithm based on cochlear mechanics and neuron filter mechanism is proposed from the view point of *** helps to solve the problem that the non-linear amplification is rarely considered in studying the auditory filters.A cochlear mechanical transduction model is built to illustrate the audio signals processing procedure in cochlea,and then the neuron filter mechanism is modeled to indirectly obtain the outputs with the cochlear properties of frequency tuning and non-linear *** mathematic description of the proposed algorithm is derived by the two *** parameter space,the parameter selection rules and the error correction of the proposed algorithm are *** unit impulse responses in the time domain and the frequency domain are simulated and compared to probe into the characteristics of the proposed *** a 24-channel filter bank is built based on the proposed algorithm and applied to the enhancements of the audio *** experiments and comparisons verify that,the proposed algorithm can effectively divide the audio signals into different frequencies,significantly enhance the high frequency parts,and provide positive impacts on the performance of speech enhancement in different noise environments,especially for the babble noise and the volvo noise.

关键词： cochlea neuron filter audio signal processing speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Damage evolution mechanism and low-damage grinding technology of silicon carbide ceramics

引用

International Journal of Extreme Manufacturing 2025年第2期 555-591页

作者： Chen Li Kechong Wang Oleg Zakharov Hailong Cui Mingtao Wu Tianchen Zhao Yongda Yan Yanquan Geng State Key Laboratory of Robotics and System (HIT) Harbin Institute of Technology School of Mechatronics Engineering Harbin Institute of Technology Hunan Provincial Key Laboratory of High Efficiency and Precision Machining of Difficult-to-cut Material Hunan University of Science and Technology Moscow State University of Technology Sichuan Precision and Ultra-Precision Machining Engineering Technology Center College of Mechanical Engineering Quzhou University

Silicon carbide(SiC) ceramics are extensively utilized in aerospace, national defense, and petrochemical industries due to their superior physical and chemical properties. The processing of bulk SiC ceramics necessitates precise and efficient grinding techniques to produce components with satisfactory functionality. However, the inherent high hardness and brittleness of SiC ceramics present significant challenges during grinding, leading to severe brittle fracture and tool wear that compromise both surface integrity and production efficiency. Although ductile-regime grinding of SiC ceramics can be achieved by enhancing machine tool accuracy and stiffness while optimizing wheel performance alongside appropriate selection of process parameters, a comprehensive summary of the mechanisms underlying damage evolution during grinding is lacking, and a mature grinding process for SiC ceramics has yet to be developed. To bridge this gap, the sintering technologies, mechanical properties, and microstructures of SiC ceramics were briefly covered. The grinding-induced damage mechanism and low-damage grinding technologies of SiC ceramics were summarized. The fundamental science underlying the ductile deformation and removal mechanisms of brittle solids was emphasized. Additionally,attention was directed towards the critical role of hybrid energy field grinding in minimizing brittle damages and promoting removal efficiency. This review not only elucidates the intrinsic interactions between the work material and abrasives, but also offers valuable insights for optimizing the grinding processes of brittle solids.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and Design of Periodic Polygonal Lattices Constructed from Microstructures with Varying Curvatures

引用

Physical Review Applied 2022年第4期17卷 044032-044032页

作者： Le Dong Dong Wang Jinqiang Wang Chengru Jiang Hui Wang Biao Zhang Mao See Wu Guoying Gu Robotics Institute and State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai 200240 China Frontiers Science Center for Flexible Electronics (FSCFE) Xi’an Institute of Flexible Electronics (IFE) and Xi’an Institute of Biomedical Materials & Engineering (IBME) Northwestern Polytechnical University 127 West Youyi Road Xi’an 710072 China School of Mechanical and Aerospace Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore

Lattice structures can exhibit unusual mechanical properties by appropriate design and arrangement of the microstructures, and have already found applications in areas such as tissue engineering, stretchable electronics, and soft robotics. However, the designed microstructures generally follow simple geometric patterns with constant curvatures and theoretical models are developed for each geometry particularly. It lacks a universal method to model and design the periodic lattice constructed from microstructures with varying curvatures. In this paper, we develop a universal approach to design polygonal lattices with a wide range of microstructures with varying curvatures using instant curvature and parametric functions. A finite deformation model is proposed for the microstructures and the corresponding lattices, which considers the wavy or curled microstructure, hierarchical geometry, and large deformation. Experiments and finite-element simulations are conducted to validate the theoretical model. All of Young’s modulus, stretchability, and Poisson’s ratio can be inversely designed using the developed theoretical model. Results show that the stretchability of the highly stretchable lattice can be further increased by more than 4 times using densely curled microstructure. The signs of Poisson’s ratio can also change with the axial strain by rationally designing the microstructures. By combining curve fitting and curvature and parametric functions, the mechanical behaviors of lattices constructed by bioinspired microstructures can also be predicted. The lattice structures are then demonstrated to reinforce a hydrogel with modulus increased by around 2 orders and act as a biomimetic soft-strain sensor. This work could aid the design of a hierarchical lattice and have potential applications in tissue engineering, stretchable electronics, and soft robotics.

关键词： Biomimetic & bio-inspired materials Devices Elastic deformation Flexible electronics Mechanical metamaterials Origami & Kirigami Strain Smart materials

来源：评论

学校读者我要写书评

暂无评论

Admittance Control Based Gait Intervention Strategy of Knee Exoskeleton for Stance Phase Support

Admittance Control Based Gait Intervention Strategy of Knee ...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Xiaolin Dai Zhihao Zhou Zilu Wang Xuewen Rong Qining Wang School of Control Science and Engineering Shandong University Jinan China University of Health and Rehabilitation Sciences Qingdao China Institute for Artificial Intelligence Peking University Beijing China Beijing Engineering Research Center of Intelligent Rehabilitation Engineering Beijing China College of Engineering Peking University Beijing China School of Control Science and Engineering Shandong University and Engineering Research Center of Intelligent Un-manned System of Ministry of Education Jinan China Department of Advanced Manufacturing and Robotics College of Engineering with the Institute for Artificial Intelligence Peking University Beijing China Peking University Third Hospital Beijing China Fifth Affiliated Hospital of Zhengzhou University Henan China

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

Knee exoskeletons have been utilized for gait rehabilitation in patients after total knee arthroplasty. During the early and middle stance phases of walking gaits, the knee joint activity of these patients is either absent or reduced, which is not conducive to the rehabilitation of normal gaits. Currently, most exoskeletons used for the rehabilitation of patients after TKA correct gait by pre-setting the movement trajectory of the knee joint. However, this method faces challenges in terms of human-machine interaction and safety. This paper proposes a strategy that combines admittance control during the early and middle stance phases with position control during the late stance and swing phases to improve compliance and safety between the wearer and the knee exoskeleton. The exoskeleton can provide support to the knee joint during the early and middle stance phases according to the wearer’s actual movement requirements. The performance and safety of the admittance control were verified through test bench and squat-to-stand experiments, while the gait intervention strategy was validated through a downhill walking experiment.

关键词： Knee Legged locomotion Torque Mechatronics Exoskeletons Position control Safety

来源：评论

学校读者我要写书评

暂无评论

TRUNK-BRANCH CONTRASTIVE NETWORK WITH MULTI-VIEW DEFORMABLE AGGREGATION FOR MULTI-VIEW ACTION RECOGNITION

arXiv

引用

arXiv 2025年

作者： Yang, Yingyuan Liang, Guoyuan Wang, Can Wu, Xiaojun Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing10049 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Mechanical Engineering and Automation Harbin Institute of Technology at Shenzhen Shenzhen518055 China

Multi-view action recognition aims to identify actions in a given multi-view scene. Traditional studies initially extracted refined features from each view, followed by implemented paired interaction and integration, but they potentially overlooked the critical local features in each view. When observing objects from multiple perspectives, individuals typically form a comprehensive impression and subsequently fill in specific details. Drawing inspiration from this cognitive process, we propose a novel trunk-branch contrastive network (TBCNet) for RGB-based multi-view action recognition. Distinctively, TBCNet first obtains fused features in the trunk block and then implicitly supplements vital details provided by the branch block via contrastive learning, generating a more informative and comprehensive action representation. Within this framework, we construct two core components: the multi-view deformable aggregation (MVDA) and the trunk-branch contrastive learning. MVDA employed in the trunk block effectively facilitates multi-view feature fusion and adaptive cross-view spatio-temporal correlation, where a global aggregation module (GAM) is utilized to emphasize significant spatial information and a composite relative position bias (CRPB) is designed to capture the intra- and cross-view relative positions. Moreover, a trunk-branch contrastive loss is constructed between aggregated features and refined details from each view. By incorporating two distinct weights for positive and negative samples, a weighted trunk-branch contrastive loss is proposed to extract valuable information and emphasize subtle inter-class differences. The effectiveness of TBCNet is verified by extensive experiments on four datasets including NTU-RGB+D 60, NTU-RGB+D 120, PKU-MMD, and N-UCLA dataset. Compared to other RGB-based methods, our approach achieves state-of-the-art performance in cross-subject and cross-setting protocols. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

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：