检索结果-内蒙古大学图书馆

Advancing PCB Quality Control:Harnessing YOLOv8 Deep Learning for Real-Time Fault Detection

computers, Materials & Continua 2024年第10期81卷 345-367页

作者： Rehman Ullah Khan Fazal Shah Ahmad Ali Khan Hamza Tahir Faculty of Cognitive Sciences and Human Development Universiti Malaysia SarawakKota Samarahan94300Malaysia School of Computer Science and Engineering Anhui University of Science and TechnologyHuainan232001China Department Electronic Quaid-i-Azam UniversityIslamabad45320Pakistan

Printed Circuit Boards(PCBs)are materials used to connect components to one another to form a working *** play a crucial role in modern electronics by connecting various *** trend of integrating more components onto PCBs is becoming increasingly common,which presents significant challenges for quality control *** the potential impact that even minute defects can have on signal traces,the surface inspection of PCB remains pivotal in ensuring the overall system *** address the limitations associated with manual inspection,this research endeavors to automate the inspection process using the YOLOv8 deep learning algorithm for real-time fault detection in ***,we explore the effectiveness of two variants of the YOLOv8 architecture:YOLOv8 Small and YOLOv8 *** rigorous experimentation and evaluation of our dataset which was acquired from Peking University’s human-Robot interaction Lab,we aim to assess the suitability of these models for improving fault detection accuracy within the PCB manufacturing *** results reveal the remarkable capabilities of YOLOv8 Small models in accurately identifying and classifying PCB *** model achieved a precision of 98.7%,a recall of 99%,an accuracy of 98.6%,and an F1 score of *** findings highlight the potential of the YOLOv8 Small model to significantly improve the quality control processes in PCB manufacturing by providing a reliable and efficient solution for fault detection.

关键词： Printed circuit boards(PCB) YOLOv8 YOLOv8 Nano YOLOv8 Small deep learning object detection

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Task Scheduling Strategy Based on Improved Fireworks Algorithm in Heterogeneous Cloud 23

An Energy-Efficient Task Scheduling Strategy Based on Improv...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Zhao, Hui Meng, Fanxin Feng, Nanzhi Wang, Quan Wan, Bo Wang, Jing School of Computer Science and Technology Xidian University Xi'an China Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province Xi'an China

ISBN: (纸本)9781665494571

With the development of cloud computing, energy consumption is getting bigger and bigger, and energy optimization has become one of the research focuses. Task scheduling is an efficient way to reduce the energy consumption of cloud. Most previous works ignored the heterogeneity of physical machines (PMs) configured with different CPUs and GPUs, which may result in high energy consumption in heterogeneous cloud. In this paper, an energy-efficient Task Scheduling Strategy based on Improved Fireworks Algorithm (TSS-IFWA) is proposed to reduce the energy consumption of the CPU/GPU heterogeneous cloud. First, a task scheduling model is constructed, in which the energy consumption of CPUs and GPUs are separately consid-ered. Then we obtain the task scheduling optimization problem of minimizing the energy consumption of heterogeneous cloud. Second, as traditional fireworks algorithm consumes massive computing resource and has a poor convergence performance, we improve a new calculation method of explosion amplitude of the fireworks algorithm. We also optimize the mutation strategy. Third, we utilize the improved fireworks algorithm to solve the task scheduling optimization problem. Specifically, the corre-sponding coding and decoding schemes of the fireworks algorithm are designed to initialize the fireworks individuals. We then obtain task scheduling results. Finally, TSS- IFWA is compared with traditional fireworks algorithm (FWA), round-robin algorithm (RR), and genetic algorithm (GA). The experimental results show that TSS- IFWA has a good performance in reducing energy consumption of heterogeneous cloud. © 2021 IEEE.

关键词： Cloud computing Fireworks algorithm Energy consumption Processor scheduling Scheduling Energy efficiency Explosions

来源：评论

学校读者我要写书评

暂无评论

Bioderived Hygromorphic Twisted Actuator for Untethered Sustainable Systems 12th

Bioderived Hygromorphic Twisted Actuator for Untethered Sust...

引用

Proceedings of the 12th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2023

作者： Whatmore, Reece Keely, Emelia Lee, Zoe Minori, Adriane Yao, Lining Department of Materials Science and Engineering Carnegie Mellon University PittsburghPA15218 United States Industrial Design Department Rhode Island School of Design ProvidenceRI02903 United States Human-Computer Interaction Institute School of Computer Science Carnegie Mellon University PittsburghPA15218 United States

ISBN: (纸本)9783031388569

Environmentally friendly and hygromorphic actuators have gained increasing attention for energy harvesting, field robotics, seeding and biodegradable active structures and sensors. While recent works have used hygromorphic seeds as sources of bio-inspiration, it is challenging to engineer synthetic hygromorphic actuators with comparable stiffness, energy density, and reaction speed, and the processing of synthetic materials or need for external power sources inevitably increases fossil fuel consumption and waste production. In this paper, we harness an alternative bioderived design approach, utilizing the natural twisted body of the seed, Hesperostipa Spartea, itself as a sustainable and biodegradable hygromorphic twisting actuator that converts atmospheric water concentration into mechanical energy. Our self-powered twisted actuator is capable of providing twisting actuation with a load over 11,000 times its body mass. We further demonstrate the potential of modular biohybrid design to create untethered self-locking and crawling systems, powered solely by environmental stimuli. The ability to create biodegradable self-actuating systems with modular bioderived design presents opportunities to create biocompatible systems, improving sustainability in the field of soft robotics and beyond. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Exploring the Embodied Experience of Walking Meetings through Bodystorming - Implications for Design 23

Exploring the Embodied Experience of Walking Meetings throug...

引用

17th International Conference on Tangible, Embedded, and Embodied interaction, TEI 2023

作者： Jacob, Mélodie Damen, Ida Lallemand, Carine Human-Computer Interaction Group University of Luxembourg Luxembourg Sporthogeschool Fontys University of Applied Sciences Netherlands Department of Industrial Design Eindhoven University of Technology Netherlands

ISBN: (纸本)9781450399777

Walking meetings are a promising way to reduce unhealthy sedentary behavior at the office. Some aspects of walking meetings are however hard to assess using traditional research approaches that do not account well for the embodied experience of walking meetings. We conducted a series of 16 bodystorming sessions, featuring unusual walking meeting situations to engage participants (N=45) in a reflective experience. After each bodystorming, participants completed three tasks: a body map, an empathy map, and a rating of workload using the NASA-TLX scale. These embodied explorations provide insights on key themes related to walking meetings: material and tools, physical and mental demand, connection with the environment, social dynamics, and privacy. We discuss the role of technology and opportunities for technology-mediated walking meetings. We draw implications for the design of walking meeting technologies or services to account for embodied experiences, and the individual, social, and environmental factors at play. © 2023 Owner/Author.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

Special Issue of Selected Papers from the 29th International Symposium on Graph Drawing and Network Visualization (GD 2021) Guest Editors’ Foreword

引用

Journal of Graph Algorithms and Applications 2023年第2期27卷 45-47页

作者： Rutter, Ignaz Purchase, Helen Faculty of Computer Science and Mathematics University of Passau Passau Germany Department of Human Centred Computing Monash University Melbourne Australia

来源：评论

学校读者我要写书评

暂无评论

VTA-NAc neural pathways involved in the mechanism of depression-like behavior induced by chronic sleep deprivation in mice 24

VTA-NAc neural pathways involved in the mechanism of depress...

引用

11th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2024

作者： Li, Yaqing Mo, Weiyi Ren, Jing Sun, Tianyi Zheng, Chengguaang Wang, Ling Yang, Jiajia Ming, Dong Medical School Tianjin University Tianjin China ZhejiangLab Zhejiang Hangzhou China Tianjin Key Laboratory of Brain Science and Neuroengineering Tianjin China Haihe Laboratory of Brian-Computer Interaction and Human-Machine Integration Tianjin China

ISBN: (纸本)9798400718274

Sleep plays a crucial role in individual physical and mental health. Insufficient sleep leads to inattention, memory loss, cognitive dysfunction and emotional disorders. The mesolimbic pathway, ventral tegmental area (VTA) to nucleus accumbens (NAc) dopaminergic neural pathway has been shown to be associated with sleep-wake behavior and depression-like behavior. In this study, we investigated the relation between chronic sleep deprivation (CSD)-induced depression-like behaviors and the activity of VTA-NAc dopaminergic pathway. CSD caused weight loss and depression-like behaviors in the mice, including anhedonia and helplessness. CSD prominently reduced the change of mice' s DA signal when moving freely. Additionally, NAc DA release became less noticeable in rewarding event and retreat behavior after exposing to CSD. In conclusion, our findings indicated that VTA-NAc dopaminergic neural pathway is directly related to depressive-like behavior caused by chronic sleep deprivation. This study provides a theoretical basis for the in-depth understanding of the physiological function of sleep, and provides a potential target for clinical research on improving or treating sleep disorder-related depression. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

A Mapping-based Dynamic Semi-Online Task Scheduling Method for Minimizing Energy in Edge Computing 23

A Mapping-based Dynamic Semi-Online Task Scheduling Method f...

引用

作者： Zhao, Hui Feng, Nanzhi Meng, Fanxin Wang, Quan Wan, Bo Wang, Jing School of Computer Science and Technology Xidian University Xi'an China Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province Xi'an China

ISBN: (纸本)9781665494571

Semi-online task scheduling in the edge computing platform refers to a scheduling scenario where there exists unknown performance computing nodes in the system. Existing online and offline task scheduling methods may lead to long makespan or transmission time due to the influence of unknown nodes, and existing semi-online methods are not fully applicable to the scenario discussed in this paper, which aggravates the problem of high energy consumption in edge computing plat-form. To solve this problem, this paper proposes a Mapping-based Dynamic Semi-online Scheduling(MDSS) strategy for edge computing platform. Firstly, we consider three main factors that affect the energy consumption in edge computing platform, that is, the energy consumption of task execution, task transmission and idle state. Then an energy consumption optimization problem is established from the perspectives of the processing speed, routing delay and queuing delay of the edge nodes, which correspond to those three factors. Secondly, for the unknown node, this paper introduces a mapping mechanism, which maps the performance of unknown nodes to a certain given node. Then the mapping relations are dynamically adjusted by continuously checking the task queue lengths of the mapped two-sides. Therefore, the prior knowledge of known nodes can be fully used. Thirdly, an im-proved Power-of- D algorithm based on the mapping mechanism is proposed to solving the formulated problem. It utilizes the prior knowledge of known node performance, which reduces task processing time and transmission time, so that the energy consumption can be reduced. Finally, some experiments are conducted to evaluate MDSS. Results show that the dynamic mapping mechanism is effective in the semi-online scenario and MDSS can greatly reduce the energy consumption in the edge computing platform. © 2021 IEEE.

关键词： Energy consumption Processor scheduling Heuristic algorithms Dynamic scheduling Routing Delays Task analysis

来源：评论

学校读者我要写书评

暂无评论

Recommendations in Visual Analytics - An Analytical Approach for Elaboration in science

Recommendations in Visual Analytics - An Analytical Approach...

引用

International Conference on Information Visualisation (IV)

作者： Midhad Blazevic Lennart B. Sina Cristian A. Secco Kawa Nazemi Department of Media & Department of Computer Science Human-Computer Interaction and Visual Analytics Darmstadt University of Applied Sciences Darmstadt Germany

The huge amount of scientific content increases the workload for evaluating state-of-the-art research and the complexity of creating novel and innovative methods and approaches. Although many approaches exist using recommendations in various application domains, the full potential of recommendation systems is not yet fully utilized. Particularly, there are missing approaches that combine interactive visualizations with recommendation systems to enable an analytical investigation of the current state of technology and science. We, therefore, propose in this work a novel Visual Analytics approach that integrates recommendation methods as the model and provides a seamless integration of both interactive visualizations and recommendation systems. We utilize MAE and RMSE metrics and human validation to identify the best approach out of eight approaches that differ in vectorization and similarity algorithms to recommend scientific items. We contribute novel approaches for recommending scientific publications, venues, and projects, based on comparing traditional and deep-learning-based recommendation approaches. Furthermore, we propose a Visual Analytics approach that uses recommendation methods for analytical elaboration. This work shows the potential of integrating recommendation systems into scientific research and identifies potential future directions for improving the proposed model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Enabled Sustainability: The Collective Work of Turning Data into Actions for Environmental Care 26

Data-Enabled Sustainability: The Collective Work of Turning ...

引用

26th ACM Conference on computer-Supported Cooperative Work and Social Computing, CSCW 2023

作者： Rossitto, Chiara Lindrup, Martin Valdemar Anker Comber, Rob Tholander, Jakob Jacobsson, Mattias Cabral, Alex Hagensby Jensen, Rikke Department of Computer and Systems Sciences Stockholm University Stockholm Sweden Department of Computer Science Aalborg University Aalborg Denmark Department of Media Technology and Interaction Design Kth Royal Institute of Technology Stockholm Sweden Department of Media Technology Södertörn University Stockholm Sweden Department of Computer Science Harvard University Boston United States

ISBN: (纸本)9798400701290

This one-day workshop invites discussions on the role of data and data-enabled practices in addressing challenges of environmental sustainability. Fostering acts of care for the environment is a complex endeavor entailing multi-lifespan relations to people and institutions, to the environment and other non-human actors, and to existing infrastructures and processes. The workshop addresses such challenges by exploring the role of data, and the work of making them actionable for the many actors involved in protecting the environment. It will bring together interdisciplinary scholars, representatives of public institutions, activists, environmental collectives, and IT practitioners interested in the design of more sustainable futures. The workshop will discuss analytical and design issues of data-enabled sustainability, along with the practical opportunities of using data to infrastructure acts of care for the environment. The workshop will accommodate up to twenty participants and will be mainly run on-site. © 2023 Owner/Author.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Workload Pattern Learning-Based Cloud Resource Management Models: Concepts and Meta-Analysis

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年第3期10卷 418-438页

作者： Saxena, Deepika Singh, Ashutosh Kumar University of Aizu Department of Computer Science and Engineering Aizuwakamatsu965-0006 Japan Indian Institute of Information Technology Madhya Pradesh Bhopal462003 India University of Economics and Human Sciences Warsaw01-043 Poland

Workload pattern learning-based resource management is crucial for cloud computing environments for achieving higher performance, sustainability, fault-tolerance, and quality of service. The existing literature lacks a comprehensive discussion and meta-analysis of workload pattern learning centered cloud resource management. In this context, this paper presents a first comprehensive study about five pattern learning and analysis-driven techniques applied for achieving higher efficiency and performance during multi-constrained cloud resource management. The paper manifests utility and significance of workload pattern learning-based resource management as compared with traditional resource management. The five principle techniques are thoroughly discussed with coherent depiction of intended concept alongwith numerical illustration. The most prominent state-of-the-art models belonging to each technique are further distinguished based on distinct objectives conferring an extensive survey and comparison. Besides, conceptual and theoretical analysis, the leading models underlying the major resource management techniques are implemented on a common platform and thoroughly examined using real-world Google Cluster workload traces. Based on the all-inclusive study and performance evaluation, trade-off discussion among these techniques are capsuled to put forward imperative concluding remarks with concrete open issues and insightful future research directions. © 2016 IEEE.

关键词： Quality of service

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：