检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer electronics-Taiwan (ICCE-TW)

作者： Ming-An Chung Jia-Wei Lin Department of Electronic Engineering Master Program in Smart Railway National Taipei University of Technology Taipei Taiwan College of Mechanical & Electrical Engineering Master Program in Smart Railway National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

Railway track inspection and maintenance is a significant topic. This research introduces a track inspection method based on image recognition to attain a rapid and effective track inspection methodology. The approach employs image enhancement technology to augment the dataset’s content, thereby improving the detection accuracy of the track detection model. The experiment indicates an improvement of substantial accuracy when employing image enhancement technology to augment the dataset, irrespective of the YOLOv5n or YOLOv5s model. The model’s average accuracy (mAP50) in detecting sleeper breaks reached the highest score of 99.5%. The datasets are publicly available at https://***/softteacherrail-xxepi/l10_ul_50_2.

关键词： Rails YOLO Training Accuracy Noise Inspection Predictive models

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Grey Wolf Optimizer for the Identification Process of a real MIMO System

Multi-Objective Grey Wolf Optimizer for the Identification P...

引用

IEEE/IAS International Conference on Industry Applications (INDUSCON)

作者： Allan Christian Krainski Ferrari Gideon Villar Leandro Leandro dos Santos Coelho Eletrical Engineering Department Federal University of Paraná UFPR Curitiba Brazil Electrical Engineering Graduate Program (PPGEE) Federal University of Paraná (UFPR) and Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná (PUCPR)

This article implements the multi-objective grey wolf optimizer (MOGWO) in the identification process of a multivariable system. For a sequence of 100 runs, MOGWO approach had compared and analyzed with the grey wolf optimizer (GWO), the single-objective version. In the computational simulation, the determination coefficient values and mean square error had used to analyze the quality of the models obtained. In the results, MOGWO showed superior to GWO to the differences between the order of magnitude of the system outputs. The implementation shows that MOGWO and other multi-objective metaheuristics can be an alternative method to solve problems of identification processes of multivariable systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Track Fasteners and Rails Surface Detection using Image Recognition and Data Management System Technology

Research on Track Fasteners and Rails Surface Detection usin...

引用

IEEE International Conference on Consumer electronics-Taiwan (ICCE-TW)

作者： Ming-An Chung Chun-Chia Lin Department of Electronic Engineering Master Program in Smart Railway National Taipei University of Technology Taipei Taiwan College of Mechanical and Electrical Engineering Master Program in Smart Railway National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

This research uses image recognition to conduct track fastener and rail surface defect detection. To counteract the dataset imbalance, design an image manager system to change the image's size, brightness, flip, and rotation. Comparing original and enhanced datasets by the precision of three different image recognition, results indicate the improvement of YOLO V8 Nano and optimized YOLO V4. However, the YOLO V7 model has a lower precision rate but a more promising recall rate.

关键词： YOLO Rails Training Image recognition Accuracy Force Fasteners

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Beamforming and Anti -Jamming with Intelligent Omni-Surfaces

Simultaneous Beamforming and Anti -Jamming with Intelligent ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yuhan Wang Shuhao Zeng Qingyu Liu Boya Di Hongliang Zhang School of Electronic and Computer Engineering Peking University Shenzhen Graduate School China Pengcheng Laboratory China Department of Electrical and Computer Engineering Princeton University USA School of Electronics Peking University China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Wireless transmission is vulnerable to malicious jamming attacks due to the openness of wireless channels, posing a severe threat to wireless communications. Current anti-jamming studies primarily focus on either enhancing desired signals or mitigating jamming, resulting in limited performance. To address this issue, intelligent omni-surface (lOS) is a promising solution. By jointly designing its reflective and refractive properties, the lOS can simultaneously nullify jamming and enhance desired signals. In this paper, we consider an lOS-aided multi-user anti-jamming communication system, aiming to improve desired signals and nullify jamming by optimizing lOS phase shifts and transmit beamforming. However, this is challenging due to the coupled and discrete lOS reflection and refraction phase shifts, the unknown jammer's beamformer, and imperfect jammer-related channel state information. To tackle this, we relax lOS phase shifts to continuous states and optimize with a coupling-aware algorithm using the Cauchy-Schwarz inequality and S-procedure, followed by a local search to recover discrete states. Simulation results show that the proposed scheme significantly improves the sum rate amid jamming attacks.

关键词： Wireless communication Array signal processing Simulation Reflection Jamming Channel state information

来源：评论

学校读者我要写书评

暂无评论

Mobile robot's navigation based on road segmentation and route evaluation. 48

Mobile robot's navigation based on road segmentation and rou...

引用

48th Annual Conference of the IEEE Industrial electronics Society, IECON 2022

作者： Tanimoto, Shinji Muramatsu, Satoshi Inagaki, Katsuhiko Chugo, Daisuke Yokota, Sho Hashimoto, Hiroshi Tokai Univ. Graduate School of Engineering Department of Electrical and Electronic Engineering Kanagawa Japan Kwansei Gakuin Univ. School of Engineering Hyogo Japan Toyo Univ. Department of Mechanical Enginering Saitama Japan Advanced Institute of Industrial Tech. Master Progaram of Innovation for Design and Engineering Tokyo Japan

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

In recent years, development of robots that can run independently in the same space as humans has been progressing. Most of the current navigation methods for autonomous robots use geometric information. While this method is easy to implement, it has some drawbacks, such as the need for accurate self-positioning and vulnerability to errors in sensor information. Humans do not have an exact self-position, but rather, they recognize an approximate location based on surrounding information and envision the path to the goal to reach the destination. Therefore, this study examines a navigation method that plans a route based on an abstract map, such as a hand-drawn map, and then travels independently to the destination. © 2022 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Modification of Deeplab V3+ for Detecting Cracks on Steel Rail Surfaces

Modification of Deeplab V3+ for Detecting Cracks on Steel Ra...

引用

IEEE International Conference on Consumer electronics-Taiwan (ICCE-TW)

作者： Ming-An Chung Yi-Xuan Ma Department of Electronic Engineering Master Program in Smart Railway National Taipei University of Technology Taipei Taiwan College of Mechanical and Electrical Engineering Master Program in Smart Railway National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

This study proposes an improved deep learning model for detecting surface cracks on railway steel tracks, addressing the urgent safety needs in the growth of railway construction. The improved Deeplab V3+ model architecture can improve feature extraction efficiency and reduce computational costs. Based on experimental results, the model outperforms others in pixel accuracy and processing speed. This study provides an effective approach for improving railway crack detection, and future work will focus on further optimizing the model for practical applications in railway inspections.

关键词： Accuracy Computational modeling Semantic segmentation Refining Computer architecture Rail transportation Safety

来源：评论

学校读者我要写书评

暂无评论

A Zero Harmonic Distortion Master Converter for Medium Voltage Microgrids

A Zero Harmonic Distortion Master Converter for Medium Volta...

引用

Annual IEEE Conference on Applied Power electronics Conference and Exposition (APEC)

作者： Gabriel V. Ramos Dener A. de L. Brandão Thiago M. Parreiras Danilo I. Brandao Braz de J. C. Filho Graduate Program in Electrical Engineering - Universidade Federal de Minas Gerais Belo Horizonte MG Brazil Department of Electrical Engineering Centro Federal de Educação Tecnológica de Minas Gerais Belo Horizonte Brazil Department of Electrical Engineering Universidade Federal de Minas Gerais Belo Horizonte Brazil

ISBN: (数字)9798331516116

ISBN: (纸本)9798331516123

This paper proposes the Zero Harmonic Distortion Converter (ZHD) as a master converter (MC) for medium voltage microgrids, delivering sinusoidal waveforms in both grid-connected and islanded mode without sinusoidal capacitive filtering elements. The ZHD MC ensures seamless transitions between modes using a simple control approach that eliminates the need off a voltage closed-loop control for grid-connected, islanded, and transition modes, using only a current closed-loop control for grid-connected operation. Simulation and hardware-in-the-loop results show the performance of the ZHD MC converter.

关键词： Electric potential Filtering Microgrids Medium voltage Power electronics Harmonic distortion Distributed power generation Reliability Voltage control

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Grey Wolf Optimizer for the Tuning Process of the FOPID Controller

Multi-Objective Grey Wolf Optimizer for the Tuning Process o...

引用

IEEE/IAS International Conference on Industry Applications (INDUSCON)

作者： Allan Christian Krainski Ferrari Gideon Villar Leandro Leandro Dos Santos Coelho Gilberto Reynoso Meza Eletrical Engineering Department Federal University of Paraná UFPR Curitiba Brazil Electrical Engineering Graduate Program (PPGEE) Federal University of Paraná (UFPR) Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná (PUCPR) Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná Curitiba Brazil

This article implements the multi-objective grey wolf optimizer (MOGWO) in the tuning process of the gains of the Fractional-Order Proportional-Integral-Derivative (FOPID) controller applied in the control of a boiler system. For a sequence of 100 runs, this application had compared and analyzed with other implementation that uses MOGWO to optimize the gains of the classical Proportional-Integral-Derivative (PID) controller. In the computational simulation, the value hypervolume metric had used to analyze the performance of the controllers. In the results, the implementation of the FOPID showed superior to PID, where the comparison had validated by a hypothesis test. Despite the higher computational cost concerning the tuning process of the PID controller, this study proved that the FOPID controller can be advantageous for industrial applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Metaheuristics with Machine Learning Enabled Medical Decision Support System

引用

Computers, Materials & Continua 2022年第11期73卷 2423-2439页

作者： Sara A.Althubiti JoséEscorcia-Gutierrez Margarita Gamarra Roosvel Soto-Diaz Romany F.Mansour Fayadh Alenezi Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Research Center-CIENS Escuela Naval de Suboficiales A.R.C.“Barranquilla”BarranquillaColombia Electronics and Telecommunications Engineering Program Universidad Autónoma del CaribeBarranquilla080001Colombia Departament of Computational Science and Electronic Universidad de la CostaCUCBarranquilla080001Colombia Biomedical Engineering Program Universidad Simón BolívarBarranquilla080001Colombia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga 72511Egypt Department of Electrical Engineering College of EngineeringJouf UniversitySaudi Arabia

Smart healthcare has become a hot research topic due to the contemporary developments of Internet of Things(IoT),sensor technologies,cloud computing,and ***,the latest advances of Artificial Intelligence(AI)tools find helpful for decision-making in innovative healthcare to diagnose several *** Cancer(OC)is a kind of cancer that affects women’s ovaries,and it is tedious to identify OC at the primary stages with a high mortality *** OC data produced by the Internet of Medical Things(IoMT)devices can be utilized to differentiate *** this aspect,this paper introduces a new quantum black widow optimization with a machine learningenabled decision support system(QBWO-MLDSS)for smart *** primary intention of the QBWO-MLDSS technique is to detect and categorize the OC rapidly and ***,the QBWO-MLDSS model involves a Z-score normalization approach to pre-process the *** addition,the QBWO-MLDSS technique derives a QBWO algorithm as a feature selection to derive optimum feature ***,symbiotic organisms search(SOS)with extreme learning machine(ELM)model is applied as a classifier for the detection and classification of ELM model,thereby improving the overall classification *** design of QBWO and SOS for OC detection and classification in the smart healthcare environment shows the study’s *** experimental result analysis of the QBWO-MLDSS model is conducted using a benchmark dataset,and the comparative results reported the enhanced outcomes of the QBWO-MLDSS model over the recent approaches.

关键词： Ovarian cancer decision support system smart healthcare IoMT deep learning feature selection

来源：评论

学校读者我要写书评

暂无评论

Green Hydrogen Facilities Based on Carbon Pricing Consideration of Introduction Possibility

Green Hydrogen Facilities Based on Carbon Pricing Considerat...

引用

International Conference on Systems and Control (ICSC)

作者： Daiki Takayama Toru Amau Takao Maeda Satoshi Miyake Itaru Kawakami Department of Electrical and Chemical Engineering Graduate School of Integrative Science and Engineering Tokyo City University Setagaya Tokyo Japan The Department of Electrical and Electronic Engineering Faculty of Science and Engineering Tokyo City University Setagaya Tokyo Japan Japan Construction Industry Co. Ltd. Chuo Tokyo Japan

ISBN: (数字)9798331531812

ISBN: (纸本)9798331531829

The purpose of this study is to explore how the use of renewable energy, particularly solar power, in combination with green hydrogen can achieve a decarbonized society at the lowest possible cost. To investigate this, we conducted a one-year simulation focusing on the introduction of solar power generation and hydrogen production facilities. Through the simulation, we aimed to determine the optimal capacities of these facilities. The results of the study revealed that it is possible to introduce hydrogen facilities at minimal operational costs while still achieving Japan's carbon dioxide (CO2) reduction targets. Furthermore, the study highlighted the impact of carbon pricing on facility adoption, demonstrating that an increase in carbon pricing encourages the more widespread introduction of hydrogen facilities. This research provides insights for the national government, local governments, and companies in their efforts to meet CO2 reduction goals through the strategic adoption of renewable energy and hydrogen technologies.

关键词： Costs Electricity Carbon dioxide Pricing Green hydrogen Production facilities Mathematical models Fuels Solar power generation Carbon

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：