检索结果-内蒙古大学图书馆

Knee osteoarthritis severity detection using deep inception transfer learning

Computers in Biology and Medicine 2025年 186卷 109641-109641页

作者： Sohail, Muhammad Azad, Muhammad Muzammil Kim, Heung Soo Department of Mechanical Robotics and Energy Engineering Dongguk University-Seoul 30 Pildong-ro 1-gil Jung-gu Seoul04620 Korea Republic of

Osteoarthritis (OA) is a prevalent condition resulting in physical limitations. Early detection of OA is critical to effectively manage this condition. However, the diagnosis of early-stage arthritis remains challenging. The Kellgren and Lawrence (KL) grading system is a common method that is accepted worldwide, uses five grades to classify the severity of OA, and relies on the ability of the orthopedist to accurately interpret radiograph images. To improve the accuracy of radiograph image interpretation, artificial intelligence-assisted models have been developed that include shallow or deep learning approaches and multi-step techniques;however, their accuracy remains variable. This work proposes a transfer learning approach using an InceptionV3-based model fine-tuned on the Osteoarthritis Initiative dataset, and aims to enhance the identification of OA severity levels through dual-stage preprocessing and convolutional neural networks for feature extraction. The fine-tuned IV3 (FT−IV3) model outperformed the IV3 model with training, validation, and testing accuracies of (96.33, 93.82, and 92.25) %, compared to IV3 accuracies of (91.64, 82.04, and 86.20) %, respectively. Additionally, Cohen's Kappa value for the FT−IV3 model (90.69 %) exceeds that of the IV3 model (83.15 %), indicating a better diagnosis of OA severity. This improvement allows the FT−IV3 model to effectively classify moderate and severe-grade OA. © 2024 Elsevier Ltd

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Human-in-the-loop Optimization of Hip Exoskeleton Assistance During Stair Climbing

引用

IEEE Transactions on Biomedical engineering 2025年 PP卷 PP页

作者： Park, Dongho An, Jimin Lee, Dawit Kang, Inseung Young, Aaron J. Woodruff School of Mechanical Engineering the Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA30332-0405 United States the Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30332-0405 United States the Department of Mechanical Engineering Carnegie Mellon University PittsburghPA15213 United States the Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30332 United States the Department of Bioengineering Stanford University StanfordCA94305 United States the Woodruff School of Mechanical Engineering the Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA30332-0405 United States

—This study applies human-in-the-loop optimization to identify optimal hip exoskeleton assistance patterns for stair climbing. Ten participants underwent optimization to individualize hip flexion and extension assistance, followed by a validation comparing optimized assistance (OPT) to biological hip moment-based assistance (BIO), no assistance (No-Assist), and no exoskeleton (No-Exo) conditions. OPT reduced metabolic cost by 4.5% compared to No-Exo, 11.44% compared to No-Assist, and 5.02% compared to BIO, demonstrating the effectiveness of the optimization approach. Statistical analysis revealed distinct characteristics in optimal assistance timing and magnitude that deviated systematically from biological hip moment patterns. Compared to BIO, OPT exhibited later peak flexion timing (76.4 ± 3.7% vs 65.0%), shorter flexion duration (29.2 ± 3.6% vs 40.0%), later peak extension timing (26.7 ± 3.8% vs 20.0% of gait cycle), and higher peak flexion magnitude (11.1 ± 1.5 Nm vs 10.0 Nm). While individual optimal assistance profiles varied across participants, comparison between individually optimized parameters and the best subject-independent parameters identified through post-hoc analysis showed consistency. On average, metabolic rate convergence was achieved after 18 iterations, while most exoskeleton control parameters did not reach our convergence criteria within 20 iterations. These findings demonstrate that human-in-the-loop optimization can effectively identify task-specific assistance patterns for stair climbing, while the consistency between individual and subject-independent parameters suggests the potential for developing generalized assistance strategies. The systematic differences between optimized and biological moment-based assistance underscore the fundamental distinctions between biological torque-based control and optimal control for exoskeleton assistance. © 2025 IEEE Computer Society. All rights reserved.

关键词： Exoskeleton (robotics)

来源：评论

学校读者我要写书评

暂无评论

Improving mechanical Durability of SLA-Printed Components for Load-Bearing 154th

Improving Mechanical Durability of SLA-Printed Components fo...

引用

154th Annual Meeting and Exhibition of The Minerals, Metals and Materials Society, TMS 2025

作者： Fani, Niloofar Monfared, Armaghan Hashemi Sadeghzade, Sorour Tavangarian, Fariborz Mechanical Engineering Program School of Science Engineering and Technology Pennsylvania State University Harrisburg MiddletownPA17057 United States Department of Biomedical Engineering Pennsylvania State University State College University ParkPA16802 United States School of Engineering Westlake University Hangzhou310024 China

ISBN: (纸本)9783031807473

This study explored the impact of post-printing parameters in stereolithography (SLA) technology, particularly focusing on how photopolymerization affected the mechanical properties of samples. Building on previous research, the investigation revealed that different curing temperatures significantly influenced the rigidity and stiffness of the printed samples. The mechanical properties of the samples were evaluated through three-point bending tests. Curing at 60 °C left some polymer chains uncured, resulting in less rigid samples but increased load capacity (up to 30 ± 2.4 N) and deflection (2.9 ± 0.6 mm). On the other hand, curing at 70 °C enhanced the rigidity and stiffness, especially for larger samples. The results demonstrated that photopolymerization and the resulting polymer chain cross-linking are crucial for achieving the desired mechanical properties. Notably, as the diameter of the samples decreased, the difference in stiffness between the 60 and 70 °C cured samples also reduced. The findings highlight the importance of optimizing curing temperatures to tailor the mechanical performance of SLA-printed components for specific applications. © The Minerals, Metals & Materials Society 2025.

关键词： Bending tests

来源：评论

学校读者我要写书评

暂无评论

Minimization of heat accumulation and shrinkage defects via locally induced forced convection in 316L stainless steel investment casting of vortex flow meters

引用

Journal of Materials Science 2025年第18期60卷 7732-7753页

作者： Wang, Yung-Chun Kao, Chia-Yu Mardiono, Intan Saputro, Imang Eko Huang, Cheng-Fu Liu, Yu-Chen Lee, Sheng-Chan Chan, Chien-Wei Fuh, Yiin-Kuen Department of Mechanical Engineering National Central University No. 300 Zhongda Rd. Zhongli District Taoyuan City320317 Taiwan GlobalTek Fabrication Co. Ltd. Xinwu Factory Taoyuan City327001 Taiwan Industrial Engineering Study Program Institut Teknologi Sumatera Terusan Ryacudu Street South Lampung35365 Indonesia

Investment casting is widely used for precision manufacturing of complex parts, such as vortex flow meters (VFM), where shrinkage defects are unavoidable but controllable. X-ray examinations revealed defects in the gating area, with the longest defect measuring 16.7 mm, exceeding the standard upper control limit (UCL) of 10 mm. This study investigated the causes of these defects and proposed solutions to mitigate them. Thermal imaging and finite element method (FEM) simulations identified heat accumulation as the primary cause of shrinkage defects. To address this, we introduced forced convection, which reduced the temperature in the heat accumulation area by up to 550 °C and increased the heat transfer coefficient (HTC) to a maximum of 1930 W/m2 K. Temperature-dependent HTC data were incorporated into the simulation software, and the results confirmed that forced convection effectively eliminated hot spots, which was subsequently validated experimentally. This solution also reduced the secondary dendrite arm spacing (SDAS) length from 57.77 ± 1.2 to 38.64 ± 0.82 μm, marking a 33% reduction, thereby enhancing the product’s mechanical properties. In actual production, forced convection reduced defects in the gating area to 0%, with the maximum defect length decreasing from 16.7 to 9.7 mm, demonstrating a significant improvement. While effective, this solution requires manual operation and additional equipment, highlighting the need for future research to develop automated and more sustainable solutions for mass production. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Forced convection

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in Artificial Intelligence-Driven Prognostics and Health Management of Mobility Batteries

引用

Multiscale Science and engineering 2025年 1-16页

作者： Kumar, Prashant Kim, Heung Soo Kim, Sungjun Kim, Hyun-Seok Moon, Janghyuk Department of AI and Big Data Woosong University Daejeon Republic of Korea Department of Mechanical Robotics and Energy Engineering Dongguk University Seoul Republic of Korea Division of Electronics and Electrical Engineering Dongguk University Seoul Republic of Korea Department of Energy Systems Engineering Chung-Ang University Seoul Republic of Korea

The rise in demand for sustainable transportation solutions in recent years has resulted in Electric vehicles (EVs) attracting substantial interest. The rapid rise in EV adoption has led to the need for efficient prognostics and health management (PHM) solutions. To ensure reliable and safe operation, the batteries that power EVs require maintenance. This paper reviews the detailed artificial intelligence (AI)-driven PHM framework for mobility batteries. Different mobility batteries have different chemistries owing to the different battery materials used for their development. AI-driven PHM uses machine learning, deep learning, and data-driven techniques to accurately estimate key battery parameters that include state of health and remaining useful life. We review data collection strategies, data processing approaches, feature development, and battery health assessment techniques based on AI, reviewing various AI methodologies that include artificial neural networks, Gaussian process regression, convolutional neural networks, and many more. This inclusive review of the recent trends and methodologies of AI-based mobility battery PHM provides a framework to develop a future efficient PHM solution for safer, efficient, and reliable battery systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion of Indirect Methods and Iterative Learning for Persistent Velocity Trajectory Optimization of a Sustainably Powered Autonomous Surface Vessel

arXiv

引用

arXiv 2025年

作者： Govindarajan, Kavin M. Agrawal, Devansh R. Panagou, Dimitra Vermillion, Chris The Department of Robotics University of Michigan Ann ArborMI48109 United States The Department of Aerospace Engineering University of Michigan United States The Department of Robotics The Department of Aerospace Engineering University of Michigan Ann-ArborMI48109 United States The Department of Mechanical Engineering University of Michigan Ann-ArborMI48109 United States

In this paper, we present the methodology and results for a real-time velocity trajectory optimization for a solar-powered autonomous surface vessel (ASV), where we combine indirect optimal control techniques with iterative learning. The ASV exhibits cyclic operation due to the nature of the solar profile, but weather patterns create inevitable disturbances in this profile. The nature of the problem results in a formulation where the satisfaction of pointwise-in-time state of charge constraints does not generally guarantee persistent feasibility, and the goal is to maximize information gathered over a very long (ultimately persistent) time duration. To address these challenges, we first use barrier functions to tighten pointwise-in-time state of charge constraints by the minimal amount necessary to achieve persistent feasibility. We then use indirect methods to derive a simple switching control law, where the optimal velocity is shown to be an undetermined constant value during each constraint-inactive time segment. To identify this optimal constant velocity (which can vary from one segment to the next), we employ an iterative learning approach. The result is a simple closed-form control law that does not require a solar forecast. We present simulation-based validation results, based on a model of the SeaTrac SP-48 ASV and solar data from the North Carolina coast. These simulation results show that the proposed methodology, which amounts to a closed-form controller and simple iterative learning update law, performs nearly as well as a model predictive control approach that requires an accurate future solar forecast and significantly greater computational capability. © 2025, CC BY.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Learning to Hop for a Single-Legged Robot with Parallel Mechanism

arXiv

引用

arXiv 2025年

作者： Zhang, Hongbo Chu, Xiangyu Chen, Yanlin Tang, Yunxi Yue, Linzhu Liu, Yun-Hui Au, Kwok Wai Samuel Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Multiscale Medical Robotics Centre Hong Kong

This work presents the application of reinforcement learning to improve the performance of a highly dynamic hopping system with a parallel mechanism. Unlike serial mechanisms, parallel mechanisms can not be accurately simulated due to the complexity of their kinematic constraints and closed-loop structures. Besides, learning to hop suffers from prolonged aerial phase and the sparse nature of the rewards. To address them, we propose a learning framework to encode long-history feedback to account for the under-actuation brought by the prolonged aerial phase. In the proposed framework, we also introduce a simplified serial configuration for the parallel design to avoid directly simulating parallel structure during the training. A torque-level conversion is designed to deal with the parallel-serial conversion to handle the sim-to-real issue. Simulation and hardware experiments have been conducted to validate this framework. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Acoustic Properties of Stretchable Liquid Metal-Elastomer Composites for Matching Layers in Wearable Ultrasonic Transducer Arrays 41

Acoustic Properties of Stretchable Liquid Metal-Elastomer Co...

引用

41st Annual Semiconductor Thermal Measurement, Modeling and Management Symposium, SEMI-THERM 2025

作者： Krings, Ethan Markvicka, Eric University of Nebraska-Lincoln Smart Materials and Robotics Laboratory Department of Mechanical & Materials Engineering Lincoln 68588 NE United States

ISBN: (纸本)9781735532554

Ultrasound is a safe, noninvasive diagnostic technique used to measure internal structures such as tissues, organs, and arterial and venous blood flow. Skin-mounted wearable ultrasound devices can enable long-term continuous monitoring of patients to provide solutions to critical healthcare needs. However, stretchable ultrasound devices that are composed of ultrasonic transducers embedded in an elastomer matrix are incompatible with existing rigid acoustic matching layers, leading to reduced energy transmission and reduced imaging resolution. Here, a systematic study of soft composites with liquid metal (LM) fillers dispersed in elastomers reveals key strategies to tune the acoustic impedance of soft materials. Experiments supported by theoretical models demonstrate that the increase in acoustic impedance is primarily driven by the increase in density with negligible changes to the speed of sound through the material. By controlling the volume loading and particle size of the LM fillers, we create a material that achieves a high acoustic impedance 4.8 Mrayl, (> 440% increase over the polymer matrix) with low modulus (< 1 MPa) and high stretchability (> 100% strain). When the device was mechanically strained, we observed a small decrease in acoustic impedance (< 15%) with negligible decrease in sound transmittance and impact on attenuation for all droplet sizes. The stretchable acoustic matching layer was then integrated with a wearable ultrasound device and the ability to measure motion was demonstrated using a phantom model as is performed in Doppler ultrasound. © 2025 SEMI-THERM Educational Foundation.

关键词： Ultrasonic transducers

来源：评论

学校读者我要写书评

暂无评论

Multiplexing B5G/6G Services Over Aerial VLC Networks: A Comprehensive Radio Resource Management Framework

引用

IEEE Internet of Things Journal 2025年第9期12卷 11600-11621页

作者： Zarini, Hosein Gholipoor, Narges Mili, Mohammad Robat Rasti, Mehdi Movaghar, Ali Choi, Jinho Chae, Chan-Byoung Sharif University of Technology Department of Computer Engineering Tehran11365-8639 Iran University of Oulu Center for Wireless Communications Oulu90570 Finland Pasargad Institute for Advanced Innovative Solutions Tehran1111111 Iran The University of Adelaide School of Electrical and Mechanical Engineering North Terrace AdelaideSA5005 Australia Yonsei University School of Integrated Technology BK21 Graduate Program in Intelligent Semiconductor Technology Seoul03722 Korea Republic of

Downlink transmission of a nonorthogonal visible light communication (VLC) system, empowered by autonomous aerial vehicles (AAVs), is studied for coexisting enhanced mobile broadband (eMBB), ultrareliable low-latency communication (URLLC), and massive machine-type communication (mMTC) services. A joint resource allocation problem involving user association, transmit power, and flight trajectory of AAVs is formulated, with the goal of characterizing a multiobjective tradeoff as a weighted sum of the power consumption of each AAV and the perceived Quality of Experience (QoE) of its associated eMBB users, while ensuring the service-specific requirements for eMBB, mMTC, and URLLC are met. Assuming the imperfection of channel state information (CSI), we invoke a generalized Benders decomposition (GBD) methodology, leveraging tools from convex optimization and multiagent deep reinforcement learning to address this problem. We further analytically derive the upper and lower bounds on the reward function for each AAV as a learning agent. Extensive simulations confirm that our proposed method outperforms the single-agent counterpart in the literature, with up to a 22% reduction in power consumption and a 13% gain in perceived QoE. Additionally, compared to the globally optimal brute-force method for AAV-user association, our proposed method experiences only a trivial performance loss in a small-scale scenario. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

MPPI-DBaS: Safe Trajectory Optimization with Adaptive Exploration

arXiv

引用

arXiv 2025年

作者： Wang, Fanxin Cheng, Yikun Tao, Chuyuan Department of Mechatronics and Robotics Xi’an Jiaotong-Liverpool University China Department of Mechanical Science and Engineering University of Illinois at Urbana-Champaign United States

In trajectory optimization, Model Predictive Path Integral (MPPI) control is a sampling-based Model Predictive Control (MPC) framework that generates optimal inputs by efficiently simulating numerous trajectories. In practice, however, MPPI often struggles to guarantee safety assurance and balance efficient sampling in open spaces with the need for more extensive exploration under tight constraints. To address this challenge, we incorporate discrete barrier states (DBaS) into MPPI and propose a novel MPPI-DBaS algorithm that ensures system safety and enables adaptive exploration across diverse scenarios. We evaluate our method in simulation experiments where the vehicle navigates through closely placed obstacles. The results demonstrate that the proposed algorithm significantly outperforms standard MPPI, achieving a higher success rate and lower tracking errors. © 2025, CC BY.

关键词： Stochastic systems

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：