检索结果-内蒙古大学图书馆

Wheat yellow rust monitoring method based on Sentinel-2 image and BPNN model

Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural engineering 2019年第17期35卷 178-185页

作者： Huang, Linsheng Jiang, Jing Huang, Wenjiang Ye, Huichun Zhao, Jinling Ma, Huiqin Ruan, Chao National Engineering Research Center for Agro-Ecological Big Data Analysis & Application Anhui University 230601 China Sanya Institute of Remote Sensing Sanya572029 China Key Laboratory of Digital Earth Science Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences Beijing100094 China

Wheat yellow rust is a deadly disease of winter wheat and its timely and accurate detection at regional scale is critical to ameliorate infectious yield loss and safeguard wheat production. With the development in remote sensing technology, satellite imagery with high spatial resolution and high revisiting frequency has become increasingly accessible. Remote sensing data has a unique advantage over traditional method in detecting crop diseases and controlling their spreading, including simple operation, real-time detection, high spatiotemporal resolution and targeting specific-disease, especially the multispectral satellite imagery which covers a wide range of wave bands and provides rich information related to crop diseases at regional scale. Compared to conventional broad band satellite imagery, the Sentinel-2 is a sensor with three wave bands within the edge of the red light which are sensitive to crop diseases. In this study, a Sentinel-2 image acquired in May 12, 2018 was used to extract 26 characteristic variables related to wheat yellow rust, including 3 visible bands (blue, green and red) reflectance variables, one near infrared band, 3 red-edge bands, 14 broad-bands and 5 red-edge vegetation indices. An approach combining K-means and ReliefF algorithm is proposed to filter these features. We first used the RelieF algorithm to calculate the weight of each feature and filter out 10 features most relevant to the disease. The feature with maximum weight was then taken as the initial center of the K-Means algorithm, and other features were added to form a cluster in descending order of their weight. The combination of features with the highest clustering accuracy was taken as the final input variable to the model. The optimal features, including enhanced vegetation index (EVI), structure intensive pigment index (SIPI), simple ratio index (SR), normalized red-edge2 index(NREDI2), normalized red-edge3 index (NREDI3), three wide-band vegetation indices and 2 red ed

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

MIM: Lightweight Multi-Modal Interaction Model for Joint Video Moment Retrieval and Highlight Detection

MIM: Lightweight Multi-Modal Interaction Model for Joint Vid...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jinyu Li Fuwei Zhang Shujin Lin Fan Zhou Ruomei Wang School of Computer Science and Engineering National Engineering Research Center of Digital Life Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion School of Communication and Design Sun Yat-sen University Guangzhou China

Joint video moment retrieval and highlight detection aims to find the relevant moments and highlight clips in a video with natural language. It is an emerging task though its individual problems have been studied for a while. The current methods utilize transformer to interact between modals, which leads to a huge cost of parameters and computation in spite of great performance. To address this problem, we present a cross-modal attention mechanism to capture related features from different modalities in a few-parameter way. Furthermore, a lightweight multi-modal interaction model (MIM) is proposed to solve video moment retrieval and highlight detection jointly. In the case of greatly reducing the number of parameters, we achieve competitive performance and faster convergence speed compared to previous method. Extensive experiments on four datasets demonstrate the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiphysics-Coupled Stress analysis of Hydrogen Storage Filling Using Diverse Composite Layer Winding Patterns

Multiphysics-Coupled Stress Analysis of Hydrogen Storage Fil...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Yi Chen Zuoqin Qian Jianxiao Wang Jie Song College of Engineering Peking University Beijing China School of Naval Architecture Ocean and Energy Power Engineering Wuhan University Of Technology Wuhan China National Engineering Laboratory for Big Data Analysis and Applications Peking University Ordos Research Institute of Energy Beijing China College of Engineering Peking University Ordos Research Institute of Energy Beijing China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

Hydrogen storage technology, as one of the core technologies in the hydrogen energy industry chain, is directly related to the efficient utilization and safe transportation of hydrogen energy. Currently, existing literature overlooks the impact of the wrapping patterns of composite layers, which can cause hydrogen storage containers to exhibit different stress characteristics. In this paper, a Type III hydrogen storage tank model is established to analyze the flow field during the filling process, obtaining the internal pressure load distribution. Subsequently, three different wrapping patterns are modeled to comparatively analyze the stress conditions of the hydrogen storage tank under these patterns. Case studies based on ANSYS reveal that when the wrapping angle tends more towards 90° or 0°, the stress conditions on the composite layers tend to be more extreme, while the stress conditions on the inner liner improve, resulting in a higher maximum stress. This trend gradually diminishes from the inner layers to the outer layers. Moreover, the stress distribution in each layer is related to the wrapping direction of that layer, i.e., the fiber direction, and the position of the layer within the stack, and is almost unaffected by other layers.

关键词： Analytical models Hydrogen storage Hydrogen Windings Transportation Filling Finite element analysis Wrapping Stress Load modeling

来源：评论

学校读者我要写书评

暂无评论

Image-Guided Point Cloud Completion with Multi-modal Fusion Transformers

Image-Guided Point Cloud Completion with Multi-modal Fusion ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： ZhaoWen Li Shujin Lin Fan Zhou School of Computer Science and Engineering National Engineering Research Center of Digital Life Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion School of Communication and Design Sun Yat-sen University Guangzhou China

The task of image-guided point cloud completion aims to leverage information from images to address uncertainty issues in the completion inference of point clouds. The key challenge in this setting lies in how to effectively combine features extracted from both modalities. Due to the large domain discrepancy between the image and point cloud, existing methods that use cross-modal attention to directly fuse features have increased attention on redundant information and noise from different modalities, resulting in poor feature fusion performance. Hence, by introducing multi-modal fusion transformers that use bottleneck tokens, we enabled point cloud feature to learn image feature through information bridges, leading to improved point cloud completion performance. Our method can not only benefit from RGB images, but also from sketches with less feature information but more emphasis on edge information. Extensive experiments demonstrate that our proposed method enhances the quality of point cloud completion and outperforms other state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study of Smart Lifting 3D Garage Design Based on the Low-Cost PLC Control System 6th

Study of Smart Lifting 3D Garage Design Based on the Low-Cos...

引用

6th International Conference on Advanced Machine Learning Technologies and applications, AMLTA 2021

作者： Zhang, Rongsheng Chang, Kuo-Chi Chu, Kai-Chun Chang, Fu-Hsiang Wang, Hsiao-Chuan Hsu, Tsui-Lien Lin, Yuh-Chung Sung, Tien-Wen Trong-The, Nguyen Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China School of Information Science and Engineering Fujian University of Technology Fuzhou China School of Management Fujian University of Technology Fuzhou China Department of Tourism Shih-Hsin University Taipei Taiwan Institute of Environmental Engineering National Taiwan University Taipei Taiwan Institute of Construction Engineering and Management National Central University Taoyuan Taiwan College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (纸本)9783030697167

As the current computer design level continues to improve, the process equipment and production line management levels are relatively stable. The intelligent and automatic 3D garage-type has shown a diversified development trend. Several garage types are currently in everyday use, including vertical lifting type, vertical lifting type, simple lifting type, horizontal shifting circulation type, channel stacking type, etc. The 3D lifting garage has a simple structure, small floor space, low operating cost, and the most extensive application requirements. However, this study summarizes the application status and development prospects of smart lifting 3D garages first. Then the system analyzes the working principle and mechanical structure characteristics of the smart lifting 3D garage, analyzes the control requirements, and designs the semi-automatic control system of the 3D garage S7–1200—it including the PLC control program and the man-machine interface. Finally, the overall system control effect is verified through simulation. This study meter has superficial operation characteristics, a high degree of automation, fast operation speed, high stability, and has deep development value and application prospects in specific markets. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels

arXiv

引用

arXiv 2022年

作者： Ma, Zhongchen Li, Lisha Mao, Qirong Chen, Songcan The School of Computer Science and Communications Engineering Jiangsu University Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Nanjing211106 China

Contrastive learning (CL) has shown impressive advances in image representation learning in whichever supervised multi-class classification or unsupervised learning. However, these CL methods fail to be directly adapted to multi-label image classification due to the difficulty in defining the positive and negative instances to contrast a given anchor image in multi-label scenario, let the label missing one alone, implying that borrowing a commonly-used way from contrastive multi-class learning to define them will incur a lot of false negative instances unfavorable for learning. In this paper, with the introduction of a label correction mechanism to identify missing labels, we first elegantly generate positives and negatives for individual semantic labels of an anchor image, then define a unique contrastive loss for multilabel image classification with missing labels (CLML), the loss is able to accurately bring images close to their true positive images and false negative images, far away from their true negative images. Different from existing multi-label CL losses, CLML also preserves low-rank global and local label dependencies in the latent representation space where such dependencies have been shown to be helpful in dealing with missing labels. To the best of our knowledge, this is the first general multi-label CL loss in the missing-label scenario and thus can seamlessly be paired with those losses of any existing multi-label learning methods just via a single hyperparameter. The proposed strategy has been shown to improve the classification performance of the Resnet101 model by margins of 1.2%, 1.6%, and 1.3% respectively on three standard datasets, MSCOCO, VOC, and NUS-WIDE. Code is available at https://***/chuangua/ContrastiveLossMLML. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Study of data Repetitive Record Cleaning Technology of MES System in High-Tech Process 6th

Study of Data Repetitive Record Cleaning Technology of MES S...

引用

6th International Conference on Advanced Machine Learning Technologies and applications, AMLTA 2021

作者： Chang, Kuo-Chi Chu, Kai-Chun Lin, Yuh-Chung Chang, Fu-Hsiang Wang, Hsiao-Chuan Hsu, Tsui-Lien Nguyen, Trong-The Sung, Tien-Wen Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China School of Information Science and Engineering Fujian University of Technology Fuzhou China School of Management Fujian University of Technology Fuzhou China Department of Tourism Shih-Hsin University Taipei Taiwan Institute of Environmental Engineering National Taiwan University Taipei Taiwan Institute of Construction Engineering and Management National Central University Taoyuan Taiwan College of Mechanical & Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (纸本)9783030697167

High-tech industries such as semiconductors have become important pillars of Taiwan’s economy under the raging COVID-19 epidemic. The MES system actively collects and monitors the production materials generated in the manufacturing process and integrates the core business required by the company’s production such as orders, suppliers, property management, production, equipment maintenance, quality control, and other processes to improve the company’s manufacturing process and production efficiency. big data of the process is the foundation of information. Good data quality is the basic condition for effective data analysis applications such as OLAP and data mining. The recursive field matching algorithm uses the recursive structure of the text field. The Sorted-Neighborhood Method (SNM) algorithm cannot solve all the matching records detected by a single keyword. data cleaning is a relatively mature field that expects more breakthroughs and innovations. There is still a lot of room for technological development, but there is still a lot of work to be done, the specific recommendations already provided. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cleaning

来源：评论

学校读者我要写书评

暂无评论

Study of 2D SubMarine Tracking with Complete Worked Out Example Based on Kalman Filter 16th

Study of 2D SubMarine Tracking with Complete Worked Out Exam...

引用

16th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information Technology, applications and Tools, FITAT 2020

作者： Chang, Kuo-Chi Gakiza, Joram Chu, Kai-Chun Wang, Hsiao-Chuan Hsu, Tsui-Lien Amesimenu, Governor David Kwabena Chang, Fu-Hsiang Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China School of Information Science and Engineering Fujian University of Technology Fuzhou China Department of Business Management Fujian University of Technology Fuzhou China Institute of Environmental Engineering National Taiwan University Taipei Taiwan Institute of Construction Engineering and Management National Central University Taoyuan Taiwan Department of Tourism Shih-Hsin University Taipei Taiwan College of Mechanical & Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (纸本)9789813364196

In many applications such as maritime surveillance and autonomous derivation, specific target tracking has become extremely important, and the characteristics of the research target will come from various distributed sources in different spaces and their noise measurements. We provide a new idea based on mobile submarine prediction data and ion pair measurement in this study, using Kalman filter based on accurate two-dimensional to approximate the results. However, we proposed to minimize the error covariance to calculate the total uncertainty measurement using the gain matrix K of Kalman filter. The actual measurement ix(k) of Kalman filter will be incorporated into each previously estimated sampling time. According to the correction equation to further improves the estimated value. The research results can be ground, the method can quickly converge to the true value, and its accuracy is better than the current passive omnidirectional sonar buoy submarine. This is an important result of the research. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Based on Smart Trash Can Bag Changing System 6th

Low-Cost Based on Smart Trash Can Bag Changing System

引用

6th International Conference on Advanced Machine Learning Technologies and applications, AMLTA 2021

作者： Xiao, Weihao Chang, Kuo-Chi Chu, Kai-Chun Chang, Fu-Hsiang Wang, Hsiao-Chuan Hsu, Tsui-Lien Lin, Yuh-Chung Sung, Tien-Wen Trong-The, Nguyen Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China School of Information Science and Engineering Fujian University of Technology Fuzhou China School of Management Fujian University of Technology Fuzhou China Department of Tourism Shih-Hsin University Taipei Taiwan Institute of Environmental Engineering National Taiwan University Taipei Taiwan Institute of Construction Engineering and Management National Central University Taoyuan Taiwan College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (纸本)9783030697167

The smart and automatic bag-changing trash can is controlled by a circuit chip and consists of an infrared detection device and a mechanical, electronic drive system. As long as an object approaches the sensing area, the lid will automatically open, and the lid will automatically close after a few seconds after the object or hand leaves the sensing area. It does not require an external power source. It is powered by a battery and has low power consumption. The exquisite streamlined appearance sensor flip design, which combines infrared sensors and microcomputers, is flexible and convenient, and it can easily throw away garbage without manual or foot stepping. It is also convenient and hygienic and has reliable performance, which helps you effectively prevent contact infections. It comprises functional modules such as ultrasonic distance measurement, photoelectric sensor modules, motor drive modules, and voice alarm modules. It takes an ultrasonic sensor, RPR220 photoelectric sensor, and single-chip computer as the core. Distance information is collected through the sensor, and then the single-chip computer sends instructions through AD conversion. When the ultrasonic sensor detects that the distance between the person and the trash can is less than the set distance, the trash can automatically flip the lid. If the RPR220 photoelectric detects the full trash can, the system will give a voice prompt. This system has a simple structure, stable performance, convenient operation, and low cost. This paper designs multifunctional trash can control system based on STC89C52RC. This system has found a feasible solution to further isolate people from garbage and prevent people from infecting bacteria. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Ultrasonic sensors

来源：评论

学校读者我要写书评

暂无评论

A Simulation Method to Play with Porosity and Particle Size Distribution for Characterizing Porous Media

arXiv

引用

arXiv 2024年

作者： Wang, Yuhe National & Local Joint Engineering Laboratory for Big Data Analysis and Computing Technology Beijing100190 China Institute for Scientific Computation Texas A&M University College StationTX77843 United States

This note presents a simulation method for investigating the relationship between porosity and particle size distribution in porous media characterization. The method simulates particle packing based on particle size distributions, incorporating descent and collision rules to mimic the natural deposition process while minimizing boundary-induced porosity distortions. By systematically varying the mean particle size and standard deviation, multiple packed structures are generated, and their corresponding porosities are calculated. This approach offers a flexible and scalable tool for exploring the impact of particle size distribution on porosity, providing both qualitative and quantitative insights into porous media properties. © 2024, CC BY.

关键词： Porosity

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：