检索结果-内蒙古大学图书馆

Skill-Based Edge-Brain Smart Manufacturing: A Case of Grasp Pose Selection Skill

Procedia computer science 2025年 253卷 2776-2790页

作者： Sukhan Lee Byungwoo Jang Seokjong Hyeon Soojin Lee Jaesun Lee Department of Electrical and Computer Engineering Sungkyunkwan University Suwon 16419 Republic of Korea Department of Artificial Intelligence Sungkyunkwan University Suwon 16419 Republic of Korea Department of Computer Science and Engineering Sungkyunkwan University Suwon 16419 Republic of Korea Department of AI System Engineering Sungkyunkwan University Suwon 16419 Republic of Korea Department of Regional Industry Innovation Korea Institute of Industrial Technology Ulsan 44413 Republic of Korea

The edge-brain framework (EBF) is a S/W framework that allows manufacturers to easily integrate AI-empowered robot work skills into a legacy production system in an edge computing environment with minimal time and effort. For EBF-based smart manufacturing, is a skill-based task-level robot programming environment that plays a key role. In this paper, we present the grasp pose selection skill as a case study to demonstrate the proposed skill-based edge-brain smart manufacturing. The proposed grasp-pose selection skill determines the optimal 6D grasp pose associated with the target object in a cluttered workspace by taking into consideration grasp stability, object manipulability, and collision-free path efficacy. To achieve a real-time operation of optimal grasp pose selection skill, deep learning networks are designed to compute, in particular, the manipulability and collision-free path efficacy indices. Experiments demonstrate the effectiveness of the proposed real-time grasp pose selection skill developed for EBF-based smart manufacturing.

关键词： Grasp Pose Selection Skill Edge Brain Framework Grasp Stability Object Manipulability Collision-Free Path Efficacy

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multi-Agent system Swarm Performance Through Explainable AI

Optimizing Multi-Agent System Swarm Performance Through Expl...

引用

Mechatronics and Robotics engineering (ICMRE), International Conference on

作者： Shekhar Mahmud Mustafa Kutlu Alper Turan Alan System Engineering Department Military Technological College Muscat Oman Mechatronics Engineering Department Sakarya University of Applied Sciences Sakarya Turkey Computer Science & Cybersecurity Department International University of Kuwait Kuwait City Kuwait

ISBN: (数字)9798331509293

ISBN: (纸本)9798331509309

Advancements in multi-agent systems (MAS) have enabled swarm-based systems to perform decentralized decision-making and autonomous tasks. However, optimizing their performance while ensuring transparency and interpretability remains a challenge. This paper introduces a framework that combines Bayesian optimization with Explainable Artificial Intelligence (XAI) techniques to enhance both the efficiency and transparency of MAS swarms. The Bayesian optimization framework fine-tunes agent parameters to improve swarm metrics such as energy efficiency, task completion time, and coordination success. The experimental results show significant improvements: a 25% increase in the coordination success rate, a 15% increase in energy efficiency, and a 20 % reduction in task completion time. XAI techniques, including SHAP values, provide interpretable explanations for optimization decisions, improving user trust and understanding. This study demonstrates the efficacy of integrating Bayesian optimization with XAI to create transparent, efficient, and reliable MAS swarms. Future work should address scalability and implications in dynamic environments.

关键词： Measurement Mechatronics Explainable AI Scalability Robot kinematics Energy efficiency Bayes methods Reliability Optimization Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Modified Kelvin-Voigt fractional derivative model for viscoelasticity measurement in optical coherence elastography

引用

Chinese Optics Letters 2025年第1期23卷 93-101页

作者： Chenming Yang Zhongliang Li Nan Nan Teng Liu Yaoli Luo Xiangzhao Wang Advanced Light Source and System R&D Center Department of Advanced Optical and Microelectronic EquipmentShanghai Institute of Optics and Fine MechanicsChinese Academy of SciencesShanghai 201800China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and EngineeringZhejiang UniversityHangzhou 310027China

Optical coherence elastography(OCE)can quantitatively obtain the viscoelasticity of tissues using rheological models and is widely applied to the clinical diagnosis of ***,commonly used rheological models in OCE do not account for the distinctive dependence of high-frequency storage and loss moduli on frequency in tissues,which results in the rheological models failing to accurately measure the viscoelastic properties of *** this paper,a modified Kelvin-Voigt fractional derivative model is presented based on the power-law behavior of soft tissues and the dependence of high-frequency complex shear modulus on frequency in living *** the rheometer and OCE tests,the modified model can provide the prediction of the power-law relationship between the low-frequency shear viscosity and frequency;compared with the Kelvin-Voigt and Kelvin-Voigt fractional derivative models,the modified model has a higher goodness-of-fit(accuracy>96%)for the high-frequency storage moduli of gelatin ***,the proposed model can reduce the root mean square error of fit by approximately 83%for the high-frequency(1–128 kHz)storage modulus of the polydimethylsiloxane phantoms obtained from publicly available ***,the modified model accurately predicts the mechanical properties of biomimetic materials over a wide frequency range,with the potential to more accurately reflect pathological changes in tissues.

关键词： optical coherence tomography optical coherence elastography viscoelasticity rheological model

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multi-Agent system Swarm Performance Through Explainable AI 11

Optimizing Multi-Agent System Swarm Performance Through Expl...

引用

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Mahmud, Shekhar Kutlu, Mustafa Alan, Alper Turan Military Technological College System Engineering Department Muscat Oman Sakarya University of Applied Sciences Mechatronics Engineering Department Sakarya Turkey International University of Kuwait Computer Science & Cybersecurity Department Kuwait City Kuwait

ISBN: (纸本)9798331509293

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining 23

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China and Zhejiang-HUST Joint Research Center for Graph Processing Zhejiang Lab China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798350323481

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and Privacy-preserving Edge Intelligence for 6G-Empowered Intelligent Transportation systems

引用

IEEE Network 2025年

作者： Zhu, Chenlu Fan, Xiaoxuan Deng, Xianjun Xiao, Ziheng Guo, Tingting Liu, Shenghao Sun, Jiaqi Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Kedao Geographic Information Engineering Co. Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of

6G-empowered Intelligent Transportation systems (ITS) generate large amounts of data through millions of devices and sensors at the terminal and network edge. Edge intelligence advances the frontier of data-driven artificial intelligence (AI) to the network edge, which enables AI applications to better utilize edge data. Broader connectivity, higher device density, and stronger data exchange present challenges for reliable device communication and privacy data protection in 6G-empowered ITS. To address these challenges, this paper proposes an energy-efficient and privacy-preserving edge intelligence framework named EP-EI. EP-EI deploys a deep reinforcement learning-based cluster head selection model at the edge to ensure energy-efficient communication for terminal devices. Meanwhile, EP-EI designs a privacy-aware hierarchical computing framework for terminal-edge-cloud to prevent privacy leakage. Furthermore, the application scenarios, challenges, and future directions of EP-EI are discussed. Finally, simulation experiments in a specific intelligent transportation case study demonstrate that EP-EI can provide energy-efficient and privacy-protecting services. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Enabling Quadruple-D Compensation Coil Integration for Efficient Power Transfer to Receiver in Wireless Power Transfer systems for EV Charging

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Erel, Mehmet Zahid Imtiaz, Tabish Elsanabary, Ahmed Mubin, Marizan Soon, Tey Kok Mekhilef, Saad Ankara Yildirim Beyazit University Department of Energy Systems Engineering Ankara Turkey Universiti Malaya Faculty of Engineering Department of Electrical Engineering Kuala Lumpur Malaysia Port Said University Faculty of Engineering Department of Electrical Engineering Port Said Egypt Universiti Malaya Department of Computer System and Technology Faculty of Computer Science and Information Technology Kuala Lumpur Malaysia Swinburne University of Technology School of Science Computing and Engineering Technologies Hawthorn Australia Presidency University Department of Electrical and Electronics Engineering Karnataka Bengaluru India

Wireless power transfer (WPT) presents a promising approach for charging electric vehicles (EVs), offering increased convenience, reliability, and safety for EV customers. Recently, the incorporation of multiple coil structures in wireless charging systems has addressed various operational challenges, enhanced power transfer, and provided a scalable solution for EVs. However, cross-coupling issues and space limitation problems arise when multiple coils are introduced to the WPT system. In this paper, a novel integrated compact coupler is proposed, including two naturally decoupled coils on the transmitter side, while both are coupled with the receiver coil to improve the power transfer capability of the system. ANSYS Maxwell is employed to simulate the proposed coupler and evaluate its performance under misalignment operations. The proposed wireless charging system inherently detects misalignment direction based on the variation of output voltage with respect to x-misalignment. As a result, the experimental prototype of the designed wireless WPT system presents a peak efficiency of 97.08% at 1.147-kW output power for an air gap of 120 mm under fully-aligned condition. Additionally, the designed compensation coil can transfer power of 243.76-W under fully-aligned condition and increases reliability in power transfer during misalignment operations. © 2013 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Battery Capacity and State of Charge Estimation with the NASA B0005 Dataset

引用

computers, Materials and Continua 2025年第3期83卷 4795-4813页

作者： Zeyang Zhou Zachary James Ryan Utkarsh Sharma Tran Tien Anh Shashi Mehrotra Angelo Greco Jason West Mukesh Prasad School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney Ultimo NSW 2007 Australia School of Data Science and Engineering Indian Institute of Science Education and Research Bhopal 462066 India Research Institute of Marine Systems Engineering Seoul National University Seoul 08826 Republic of Korea Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Delhi NCR Campus Ghaziabad 201204 India Battery System Modelling Department CLARIOS VARTA Hannover GmbH Hanover 30419 Germany Science and Innovation Group Bureau of Meteorology Brisbane 4000 Australia

Accurate capacity and State of Charge (SOC) estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric vehicles. This study examines ten machine learning architectures, Including Deep Belief Network (DBN), Bidirectional Recurrent Neural Network (BiDirRNN), Gated Recurrent Unit (GRU), and others using the NASA B0005 dataset of 591,458 instances. Results indicate that DBN excels in capacity estimation, achieving orders-of-magnitude lower error values and explaining over 99.97% of the predicted variable’s variance. When computational efficiency is paramount, the Deep Neural Network (DNN) offers a strong alternative, delivering near-competitive accuracy with significantly reduced prediction times. The GRU achieves the best overall performance for SOC estimation, attaining an R 2 of 0.9999, while the BiDirRNN provides a marginally lower error at a slightly higher computational speed. In contrast, Convolutional Neural Networks (CNN) and Radial Basis Function Networks (RBFN) exhibit relatively high error rates, making them less viable for real-world battery management. Analyses of error distributions reveal that the top-performing models cluster most predictions within tight bounds, limiting the risk of overcharging or deep discharging. These findings highlight the trade-off between accuracy and computational overhead, offering valuable guidance for battery management system (BMS) designers seeking optimal performance under constrained resources. Future work may further explore advanced data augmentation and domain adaptation techniques to enhance these models’ robustness in diverse operating conditions.

关键词： Battery capacity estimation state of charge deep learning prediction efficiency energy storage systems

来源：评论

学校读者我要写书评

暂无评论

Marching Page Walks: Batching and Concurrent Page Table Walks for Enhancing GPU Throughput

Marching Page Walks: Batching and Concurrent Page Table Walk...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Jiwon Lee Gun Ko Myung Kuk Yoon Ipoom Jeong Yunho Oh Won Woo Ro Department of Electrical and Electronic Engineering Yonsei University Seoul Korea Department of Computer Science and Engineering Ewha Womans University Seoul Korea Department of System Semiconductor Engineering Yonsei University Seoul Korea School of Electrical Engineering Korea University Seoul Korea

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Virtual memory, with the support of address translation hardware, is a key technique in expanding programmability and memory management in GPUs. However, the nature of the GPU execution model heavily pressures its translation hardware, particularly due to a discrepancy in the behavior of page table walkers and thousands of concurrently running threads. In GPU workloads, multiple threads simultaneously access a number of pages necessitating a substantial number of translations whereas each walker handles only a single walk request at a time. Such a limitation significantly increases the queueing latency of walk requests, which we observe as a major bottleneck for servicing page table walks in GPUs. To tackle this challenge, we investigate a design of page walkers that facilitates multiple walk requests to be handled together in batches. Then, we make the following observations: 1) allowing a page walker to issue beyond a single memory request significantly improves the throughput of walkers, and 2) GPU applications tend to concurrently access pages in wide address ranges. By leveraging the above implications, we propose Marching Page Walks (MPW) that effectively mitigate the contention in GPU page table walkers. MPW scans pending walk requests to identify ones that can be grouped together. Then, MPW batches these requests and concurrently handles them by issuing multiple memory instructions. Experiments show that MPW reduces the queueing latency of page walks by 86.7% and improves GPU performance by 55.6% over the baseline design.

关键词： Translation Filters Instruction sets Memory management Graphics processing units Throughput Hardware Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Learning Models Revolutionize Doctor’s Training for Point-of-Care Ultrasound

引用

IEEE Access 2025年 13卷 76038-76046页

作者： Chou, Hsin-Hung Chang, Yi-Chung Lien, Wan-Ching Lin, Lung-Chun Lin, Xing-Zheng Hsu, Ting-En Liu, Yueh-Ping Liu, Li Chan, Yen-Ting Kuan, Feng-Sen National Chi Nan University Department of Computer Science and Engineering Nantou545301 Taiwan National Taiwan University College of Medicine Department of Emergency Medicine Taipei106319 Taiwan National Taiwan University Hospital Department of Emergency Medicine Taipei100225 Taiwan National Taiwan University Hospital Department of Internal Medicine Taipei100225 Taiwan Ministry of Health and Welfare Department of Medical Affairs Taipei115204 Taiwan Show Chwan Health Care System Taipei100225 Taiwan OmniHealth Group Inc. Department of Research Planning Taipei106409 Taiwan Huasin H. T. Ltd. Department of Business Development Taipei106409 Taiwan

Point-of-care ultrasound (PoCUS) is a valuable diagnostic tool for pericardial effusion (PCE). However, the time constraints for trainees and experts pose significant barriers to PoCUS learning. This study aims to develop a deep learning (DL) model for detecting and localizing PCE and to investigate the learning efficacy of using this model as an adjunct in PoCUS training. A total of 101 patients with moderate/large PCE and 104 controls without PCE were included, and the images were extracted from the ultrasound (US) clips. We applied preprocessing techniques, including standardized image sizes and background removal, to reduce interference, and post-processing techniques, including adding filters to refine small effusion regions. We developed three DL models based on U-Net, Res-UNet, and UNet++ and compared their performance. Additionally, 14 emergency medicine residents were recruited to complete classification and segmentation tasks on 10% of randomly selected US images. Personalized feedback from the best-performing DL model was provided. Three months later, the residents annotated another set of images. Their learning performance was also evaluated. The UNet++ algorithm surpassed the other two, attaining an impressive sensitivity of 96%, specificity of 97%, area under the curve (AUC) of 98%, intersection over union (IOU) of 81%, and minimal latency. The overall sensitivity increased by 4% in the classification task after training with the UNet++ model, although there were no statistically significant differences in all evaluation metrics. The UNet++ model achieved a balance between high accuracy, IOU, and latency. Although there were no significant differences in the evaluation metrics after UNet++-assisted learning, the overall sensitivity increased by 4%, indicating an improved ability to recognize true positives and reduce false negatives. Our results demonstrated that AI could enhance the interpretation of rare PoCUS conditions and reduce the time demands o

关键词： Personnel training

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：