检索结果-内蒙古大学图书馆

15th International Conference on Computer and Automation Engineering, ICCAE 2023

作者： Rahim, Umme Fawzia Utsumi, Tomoyoshi Iwaki, Yohei Mineno, Hiroshi Shizuoka University Graduate School of Science and Technology 3-5-1 Johoku Naka-ku Shizuoka Hamamatsu432-8011 Japan Yamaha Motor Co. Ltd Technical Research & Development Center 3001-10 kuno Shizuoka Fukuroi437-0061 Japan

ISBN: (纸本)9798350396225

To adjust management practices and improve wine marketing strategies, accurate vineyard yield estimation early in the growing season is essential. Conventional methods for yield forecasting rely on phenotypic features' manual assessment, which is time- and labor-intensive and often destructive. We combined a deep object segmentation method, mask region-based convolutional neural network (Mask R-CNN), with two potential multi-object tracking algorithms, simple online and real-time tracking (SORT) and intersection-over-union (IOU) trackers to develop a complete visual system that can automatically detect and track individual inflorescences, enabling the assessment of the number of inflorescences per vineyard row from vineyard video footage. The performance of the two tracking algorithms was evaluated using our vineyard dataset, which is more challenging than conventional tracking benchmark datasets owing to environmental factors. Our evaluation dataset consists of videos of four vineyard rows, including 221 vines that were automatically acquired under unprepared field conditions. We tracked individual inflorescences across video image frames with a 92.1% multi-object tracking accuracy (MOTA) and an 89.6% identity F1 score (IDF1). This allowed us to estimate inflorescence count per vineyard row with a 0.91 coefficient of determination (R2) between the estimated count and manual-annotated ground truth count. The impact of leaf occlusions on inflorescence visibility was lessened by processing multiple successive image frames with minimal displacements to construct multiple camera views. This study demonstrates the use of deep learning and multi-object tracking in creating a low-cost (requiring only an RGB camera), high-throughput phenotyping system for precision viticulture. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improved ADRC Based Speed Control for Dynamic Performance Improvement of Micro-Turbine System 7

Improved ADRC Based Speed Control for Dynamic Performance Im...

引用

7th IEEE International Electrical and Energy Conference, CIEEC 2024

作者： Luo, Ziyi Li, Yong Zhang, Mingmin Liu, Fang Xu, Yong Wang, Bing College of Electrical and Information Engineering Hunan University Changsha China School of Electronic Information and Electrical Engineering Changsha University Changsha China School of Information Science and Engineering Central South University Changsha China Technology Research and Development Center State Grid Hunan Integrated Energy Service Company Limited Changsha China

ISBN: (纸本)9798350359558

The micro-turbine (MT) system plays an important role in the gas-electricity combined system. For an isolated gas-electricity combined system, effective speed-tracking control is critical for a stable power supply. This study employs a linear active disturbance rejection control (LADRC) technique to achieve precise speed-tracking for the MT system with a permanent magnet synchronous generator (PMSG). Beginning with looking into the MT system's internal structure, the mathematical model of the speed control loop is derived. A third-order extended state observer (ESO) is established to manage lumped model disturbances. Leveraging the ESO, the proposed LADRC-based speed controller facilitates accurate speed tracking. Recognizing the limited observer bandwidth in extensive time-lag systems, an enhanced version of the regular ESO is introduced, leading to an improved LADRC with a smaller control input gain, bigger bandwidth, and enhanced disturbance rejection capabilities for speed control. Simulation results demonstrate the improved control performance of the LADRC-based speed controller for the MT system. © 2024 IEEE.

关键词： Speed control

来源：评论

学校读者我要写书评

暂无评论

Wireless Power Transmission Using Acoustic-to-Inductive Relayed Transfer 21

Wireless Power Transmission Using Acoustic-to-Inductive Rela...

引用

21st International Conference on Micro and Nanotechnology for Power Generation and Energy Conversion Applications, PowerMEMS 2022

作者： Tseng, Victor Farm-Guoo Kiebala, Tobias Bruno, Dylan Novick, Benjamin Lazarus, Nathan Bedair, Sarah S. Army Research Laboratory Us Army Combat Capabilities Development Command United States Rochester Institute of Technology Oak Ridge Associated Universities Fellowship United States University of Delaware United States

ISBN: (纸本)9781665493062

This paper presents, for the first time, a wireless power transfer technology that uses acoustic power transfer to transfer through/along a metal structure, then relays to conventional inductive power transfer to charge receivers not in contact with the metal structure. Acoustic waves have the unique ability to transfer directly through/along metal structures without experiencing electromagnetic shielding, which is useful for powering wireless sensors for infrastructure monitoring (e.g., within metal pipelines). For powering receivers detached from the metal structure, acoustic and inductive can be combined, and in this work, we demonstrate 28% power efficiency at 28 kHz by transferring through a metal tube. Higher efficiencies can be achieved by improving the inductive coil coupling. © 2022 IEEE.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

research progress of superhydrophobic coatings based on silicone rubber surface 11

Research progress of superhydrophobic coatings based on sili...

引用

11th Global Conference on Materials Science and Engineering, CMSE 2022

作者： Xie, X.W. Zhao, Y.J. Shi, J.B. Beijing Guo Dian Futong Science and Technology Development Co. Ltd Beijing100070 China NARI Group Corporation State Grid Electric Power Research Institute Nanjing211106 China

Silicone rubber has excellent insulation properties such as good hydrophobic mobility and anti pollution flashover performance. It plays an important role in the power system and provides an important guarantee for the reliability of power supply. However, due to the erosion of various harsh environments, especially in wet environments such as rain and snow, a large amount of dirt and water are easily attached to the surface of insulating parts. It not only reduces its surface hydrophobicity and hydrophobic mobility, but also greatly shortens its service life. There are even serious leakage current problems. Especially in the low temperature environment, a lot of snow and flashover will occur at the accessories of the insulation parts. In order to solve this problem, super hydrophobic self-cleaning coating based on silicone rubber surface came into being. The preparation principle and model of superhydrophobic self-cleaning coating on silicone rubber surface are reviewed in this paper. By comparing different preparation methods, the advantages, disadvantages and application prospects are analyzed, and the existing problems and challenges are put forward according to the existing preparation technologies, so as to lay a theoretical foundation for preparing self-cleaning coatings with excellent performance in the future. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

Analysis of Near-Field Probing Techniques for Immunity Tests

Analysis of Near-Field Probing Techniques for Immunity Tests

引用

2022 ESA Workshop on Aerospace EMC, Aerospace EMC 2022

作者： Wu, Xinglong Grassi, Flavia Spadacini, Giordano Pignari, Sergio A. Paoletti, Umberto Hoda, Isao Politecnico di Milano Dept. Electronics Information and Bioengineering Milan20133 Italy Center for Technology Innovation Production Engineerin Research Development Group Hitachi Ltd Yokohama244-0817 Japan

ISBN: (纸本)9789082684742

This work experimentally investigates the performance of near-field probes as injection devices for wideband immunity tests. To this end, the coupling effectiveness and resolution of different kinds of magnetic and electric near-field probes are firstly investigated in terms of S-parameters measured with the probes placed on microstrip traces. Different test benches are set up and experimentally characterized in order to investigate the characteristics and determine the frequency response of the transfer function of a typical measurement chain for immunity verification. Finally, time-domain near-field tests employing arbitrary waveform generators are introduced, showing the feasibility of injecting customized wideband noise waveforms at specific pins. © 2022 ESA ESTEC.

关键词： Scattering parameters

来源：评论

学校读者我要写书评

暂无评论

Surface Anomaly Detection Using Machine Learning Technique 4

Surface Anomaly Detection Using Machine Learning Technique

引用

4th International Conference on Emerging Trends in Networks and Computer Communications, ETNCC 2024

作者： Weiqi, Xiao Chee Hooi, Steve Teoh Sindiramutty, Siva Raja A L Asirvatham, David A L Kumar, Devender Verma, Sahil School of Computer Science Taylor's University Subang Jaya Malaysia Lovely Professional University Division of Research and Development Punjab Phagwara144411 India KKR and KSR Institute of Technology and Sciences Andhra Pradesh Guntur India Chandigarh Group of Colleges Department of Computer Science and Engineering PunjabJhanjeri Mohali140307 India

ISBN: (纸本)9798350353266

The world is developing rapidly, and the industrial field is gradually reducing labor work and moving to a state of smart work. Machine intelligence operations can often help humans reduce stress in many aspects. Here, we will use related technologies of machine learning. At present, convolutional neural network algorithms are mainly used to apply image-related application scenarios. On this basis, using YOLO technology can achieve faster and more accurate target detection and improve accuracy of detection. Through this improvement, production efficiency can be greatly improved and the stability of the production rhythm can be enhanced. The stability of production rhythm is an extremely important part. It can minimize unnecessary losses and expenditures of enterprises and at the same time obtain greater profits. The improvement of detection accuracy can better protect the health, safety and rights of consumers from a social perspective. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Scene Text Recognition using Deep Learning Techniques 4

Scene Text Recognition using Deep Learning Techniques

引用

4th International Conference on Emerging Trends in Networks and Computer Communications, ETNCC 2024

作者： Ying, Xin Murugesan, Raja Kumar Raja Sindiramutty, Siva Wei, Goh Wei Balakrishnan, Sumathi Kumar, Devender Verma, Sahil School of Computer Science Taylor's University Subang Jaya Malaysia Lovely Professional University Division of Research and Development Punjab Phagwara144411 India KKR and KSR Institute of Technology and Sciences Andhra Pradesh Guntur India Chandigarh Group of Colleges Jhanjeri Department of Computer Science and Engineering Punjab Mohali140307 India

ISBN: (纸本)9798350353266

In the discipline of computer vision, which aims to automatically identify text regions from photos and transform them into editable text data, text recognition in natural contexts presents a difficult task. Deep learning-based methods for text recognition in natural settings have advanced significantly in recent years. The feature extraction-based CRNN technique, which was tested in this paper, performed better. It is possible to accurately portray text properties in real-world environments by using the local entropy property, which is used to describe the information distribution and texture of images. In the CRNN approach based on local entropy feature extraction, the local entropy features from the picture are first extracted using the convolutional neural network. When these features are fed into the recurrent neural network for sequence modeling, the text output is subsequently generated. The CRNN technique based on feature extraction from local entropy may be able to recognize text in real-world situations because local entropy can correctly characterize the texture and information distribution in images. The SCUT-FORU dataset experiment results demonstrate the efficacy of the local entropy feature extraction based CRNN technique for text recognition in realistic settings. There are several fonts, sizes, colors, lighting, backdrops, and other elements in the SCUT-FORU data collection. The CRNN technique based on local entropy feature extraction provides improved accuracy and can perform the text recognition task more quickly, according to experiments on this dataset. In conclusion, the local feature extraction-based CRNN method is a potent text recognition method that may be applied in a range of real-world application scenarios. The continued improvement of deep learning technology will enable future developments and innovations in the field of character recognition in natural settings. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

State-of-the-art evolution of g-C3N4-based photocatalytic applications:A critical review

引用

结构化学 2024年第12期43卷 113-129页

作者： Yanghanbin Zhang Dongxiao Wen Wei Sun Jiahe Peng Dezhong Yu Xin Li Yang Qu Jizhou Jiang School of Environmental Ecology and Biological Engineering School of Chemistry and Environmental EngineeringKey Laboratory of Green Chemical Engineering Process of Ministry of EducationEngineering Research Center of Phosphorus Resources Development and Utilization of Ministry of EducationNovel Catalytic Materials of Hubei Engineering Research CenterWuhan Institute of TechnologyWuhan430205PR China Key Laboratory of Material Chemistry for Energy Conversion and Storage Ministry of EducationSchool of Chemistry and Chemical EngineeringHuazhong University of Science and TechnologyWuhan430074PR China College of Forestry and Landscape Architecture South China Agricultural UniversityGuangzhou510642PR China Key Laboratory of Functional Inorganic Materials Chemistry(Ministry of Education) School of Chemistry and Materials ScienceInternational Joint Research Center for Catalytic TechnologyHeilongjiang UniversityHarbin 150080PR China

g-C3N4 is a promising non-metallic photocatalyst recognized for its unique structural and physicochemical *** reviews have addressed g-C3N4-based photocatalysis;however,the rapid progress in big data and artificial intelligence has significantly accelerated the design,synthesis,and optimization of these *** learning,theoretical simulations,and advanced in-situ characterization techniques have deepened our understanding of their photocatalytic *** review critically evaluates advancements in g-C3N4-based photocatalysts over the last two to three years,focusing on strategies to improve photogenerated charge sepa-ration,expand light absorption,and enhance stability and catalytic *** discusses cutting-edge in-situ characterization methods alongside machine learning approaches for predicting and optimizing applications in photocatalytic H2 evolution,CO2 reduction,pollutant degradation,H2O2 production,and nitrogen ***,it proposes prospective strategies for further enhancing the performance of g-C3N4-based photocatalysts,aiming to guide the design of high-performance two-dimensional carbon-based photocatalysts.

关键词： g-C3N4 Photocatalysis Enhancement strategies In-situ characterization Theoretical simulations

来源：评论

学校读者我要写书评

暂无评论

Comparative study of VOF, LS, and VOSET on pore-scale immiscible waterflooding modeling

引用

Petroleum 2021年第3期7卷 314-324页

作者： Jiajun Peng Rui Song Yao Wang Hanmin Xiao School of Geoscience and Technology Southwest Petroleum UniversityChengdu610500China School of Civil Engineering and Architecture Southwest University of Science and TechnologyMianyang621010China Research Institute of Petroleum Exploration&Development PetroChina Company LimitedBeijing100083China

The pore-scale mechanism of the waterflooding contributes to enhancing oil recovery,which has been widely emphasized in the petroleum *** this paper,the performances and accuracy of three tracking interface algorithms,including VOF,LS,and VOSET,are compared and analyzed through twophase flow in the conceptual model of *** results show that the VOSET method combines the advantages of the other two methods,which not only satisfies the mass conservation but also improves the continuity of the physical quantities near the ***,based on the binary image of the pore,the two-dimensional micro pore model is reconstructed by extracting image *** grid independence of the reconstructed pore model is verified by the single-phase flow *** waterflooding process in the reconstructed pore model is simulated using the VOSET method,and the effects of displacement speed and wettability on the oil recovery are *** morphologies of residual oil under different conditions of wettability are investigated and *** study provides a basic theory for modeling the pore-scale oil-water flow and optimizing the scheme of the water injection.

关键词： Waterflooding Oil recovery VOSET Displacement speed Wettability

来源：评论

学校读者我要写书评

暂无评论

3D-printed manganese dioxide incorporated scaffold promotes osteogenic-angiogenic coupling for refractory bone defect by remodeling osteo-regenerative microenvironment

引用

Bioactive Materials 2025年第2期44卷 354-370页

作者： Yipei Yang Zhenyu Yao Yuanyi Sun Yangyi Nie Yuanchi Zhang Ziyue Li Zhiheng Luo Wenjing Zhang Xiao Wang Yuhan Du Wei Zhang Ling Qin Hongxun Sang Yuxiao Lai Department of Orthopedic Surgery Shenzhen HospitalSouthern Medical UniversityShenzhen518000China Centre for Translational Medicine Research&Development Institute of Biomedical and Health EngineeringShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen518055China Department of Medicine Ultrasonics Nanfang HospitalSouthern Medical UniversityGuangzhou510500China Musculoskeletal Research Laboratory Department of Orthopaedics&TraumatologyThe Chinese University of Hong KongHong Kong SAR999077China CAS-HK Joint Lab of Biomaterials Shenzhen518055China The Third School of Clinical Medicine Southern Medical UniversityGuangzhou510500China

The treatment of refractory bone defects is a major clinical challenge,especially in steroid-associated osteonecrosis(SAON),which is characterized by insufficient osteogenesis and ***,a microenvironment responsiveness scaffold composed of poly-L-lactide(PLLA),and manganese dioxide(MnO_(2))nanoparticles is designed to enhance bone regeneration by scavenging endogenous reactive oxygen species(ROS)and modulating immune microenvironment in situ.A catalase-like catalytic reaction between MnO_(2)and endogenous hydrogen peroxide(H_(2)O_(2))generated at the bone defect area,which typically becomes acidic and ROS-rich,triggers on-demand release of oxygen and M^(n2+),significantly ameliorating inflammatory response by promoting M2-type polarization of macrophages,reprograming osteoimmune microenvironment conducive to angiogenesis and ***,the fundamental mechanisms were explored through transcriptome sequencing analysis,revealing that PLLA/MnO_(2)scaffolds(PMns)promote osteogenic differentiation by upre-gulating the TGF-β/Smad signaling pathway in human bone marrow mesenchymal stem cells(hBMSCs).Overall,the PMns exhibit superior immunomodulatory,excellent osteogenic-angiogenic properties and promising can-didates as bone graft substitutes for therapy clinical refractory bone defects.

关键词： Osteogenic-angiogenic coupling Steroid-associated osteonecrosis Manganese dioxide Refractory bone defect

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：