检索结果-内蒙古大学图书馆

Progressive Motion Boosting for Video Frame Interpolation

IEEE Transactions on Multimedia 2023年 25卷 8076-8090页

作者： Xiao, Jing Xu, Kangmin Hu, Mengshun Liao, Liang Wang, Zheng Lin, Chia-Wen Wang, Mi Satoh, Shin'Ichi The School of Computer Science Wuhan University Wuhan430072 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The Department of Electrical Engineering the Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430072 China The Digital Content and Media Sciences Research Division National Institute of Informatics Tokyo101-8430 Japan

Video frame interpolation has made great progress in estimating advanced optical flow and synthesizing in-between frames sequentially. However, frame interpolation involving various resolutions and motions remains challenging due to limited or fixed pre-trained networks. Inspired by the success of the coarse-to-fine scheme for video frame interpolation, i.e., gradually interpolating frames of different resolutions, we propose a progressive boosting network (ProBoost-Net) based on a multi-scale framework to achieve flexible recurrent scales and then gradually optimize optical flow estimation and frame interpolation. Specifically, we designed a dense motion boosting (DMB) module to transfer features close to real motion to the decoded features from the later scales, which provides complementary information to refine the motion further. Furthermore, to ensure the accuracy of the estimated motion features at each scale, we propose a motion adaptive fusion (MAF) module that adaptively deals with motions with different receptive fields according to the motion conditions. Thanks to the framework’s flexible recurrent scales, we can customize the number of scales and make trade-offs between computation and quality depending on the application scenario. Extensive experiments with various datasets demonstrated the superiority of our proposed method over state-of-the-art approaches in various scenarios. © 2023 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge Computing Environment

引用

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection of Medium and Thick Plates Based on Yolov8 Network 5

Surface Defect Detection of Medium and Thick Plates Based on...

引用

5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023

作者： Luo, Yutian Li, Jinze Chen, Jie Liu, Jian University at Buffalo The State University of New York School of Engineering and Applied Sciences Department of Computer Science and Engineering United States University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798350357950

Steel is one of the important basic industrial raw materials, and the development of steel production technology directly affects the infrastructure construction, the development of manufacturing industry and the prosperity of the national economy. The identification of surface defects on steel plates has garnered increasing attention. Such defects not only impede the ability of medium and heavy plates to meet user production specifications but also pose the risk of significant production accidents. These challenges can have an immeasurable adverse impact on the production enterprise. Due to the swift advancements in computer vision, vision-based steel plate surface inspection technology has reached a high level of maturity. We collected images of steel plate surface defects, this encompasses the detection of various defects such as overburning, pits, compressed rust skin, and other irregularities originating from the production line of a domestic medium and heavy steel plate factory, and used five models (yolov8, yolov5, Faster-RCNN, RCNN, and DETR) for training and detection after pre-processing techniques such as labelling and data enhancement. Upon evaluating the detection outcomes, it becomes evident that the Yolov8 model exhibits robust accuracy and rapid computational speed when applied to the task of detecting defects on steel surfaces. This proficiency lends dependable technical support for various applications, including industrial quality inspection and the analysis of surface defects. Furthermore, the performance of Yolov8 under different sets of loss functions are evaluated, and the optimal setting is selected for surface defect detection. © 2023 IEEE.

关键词： data pre-processin defect detection Yolov8

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Data Visualization Techniques for Real-Time Information

A Comprehensive Review on Data Visualization Techniques for ...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Vishal Kumar Choudhary Gulshan Kumar Saurabh Suman Abhishek Kumar Department of Computer Science and Medical Engineering Faculty of Engineering and Technology Wardha Maharashtra India Department of Computer Science and Design Faculty of Engineering and Technology Wardha Maharashtra India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

Research on real-time data visualization methods is necessary to achieve the most accurate and clear representation of information. Creating specific boards and modifying current platforms are two key tasks in performing an appropriate information visualization. An overview of the studies on dashboard platforms, data visualization methods, and accessible strategies is given in this article. To evaluate the effects of the various data visualization approaches on the finished dashboard, a generic and dynamic dashboard based on real-time data was created. Consequently, a preliminary collection of cues, charts, tables, and reports will allow users to interact with the data. produced by the Dashboard itself. Making informed decisions across a variety of businesses requires the capacity to acquire and comprehend real-time information in today’s data-driven environment. Real-time data visualization techniques are now essential for turning complex data into insights that can be put to use. This study examines the value of real-time data visualization and offers a summary of strategies and equipment that enable businesses to efficiently use real-time data.

关键词： Reviews Data visualization Turning Real-time systems Task analysis Business

来源：评论

学校读者我要写书评

暂无评论

Asthma Disease Risk Prediction Using Machine Learning Techniques

Asthma Disease Risk Prediction Using Machine Learning Techni...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Pyingkodi, M. Thenmozhi, K. Wilfred Blessing, N.R. Selvaraj, P.A. Kumar, Kamdev Aadarsh, V. Mariya Arockiya Akash, A. Kongu Engineering College Department of Computer Applications Erode India Kristu Jayanti College Department of Computer Science Bengaluru India University of Technology and Applied Sciences-Ibri College of Computing and Information Sciences IT Department Oman

ISBN: (纸本)9798350348217

The signs of asthma, a long-term inflammatory condition of the airways, include wheezing, throat tightness, coughing, and breathing difficulties. The attack of an asthma, which can be fatal, is the fast worsening of these symptoms. Another severe, irreversible airflow restriction in the lungs is caused by respiratory COPD, which encompasses emphysema and chronic bronchitis. In this project, a machine learning-based algorithm is for predicting asthma risk is presented (ML). PEFR, which are widely used external tools like peak flow meters and recognized asthma risk predictors, are frequently monitored. This study shows a relationship between the ambient particle matter(PM) and the weather outdoors. According to the best peak flow value each person was able to acquire, the results are divided into two groups: Safe and Risk circumstances. The link between indoor PM and weather data is mapped to the found values using a convolutional neural network (CNN) architecture. The suggested method's root mean square and mean absolute error accuracy metrics are contrasted with those of current deep neural network (DNN)-based methods. Additionally, the accuracy of the classification methods KNN and SVM are carried out. The new data set's asthma category may be predicted more accurately thanks to the application of SVM, KNN, and CNN classification. Python 3.7 is the coding language employed. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Publication performance and trends in virtual reality research in education fields: a bibliometric analysis

引用

Multimedia Tools and Applications 2025年第10期84卷 6999-7026页

作者： Elaish, Monther M. Yadegaridehkordi, Elaheh Ho, Yuh-Shan Computer Science Department Information Technology Faculty University of Benghazi Benghazi Libya College of Information and Communications Technology School of Engineering and Technology CQUniversity Sydney Australia Trend Research Centre Asia University No. 500 Lioufeng Road Taichung41354 Taiwan

Virtual Reality (VR) technology has the potential to enhance education by providing immersive and engaging learning experiences that can improve teaching and learning outcomes. While there is a growing interest in utilizing VR in education settings, further research is needed to understand its pedagogical effectiveness and address associated considerations and challenges. This bibliometric study comprehensively analyzes 1,157 relevant articles from the Social science Citation Index (SSCI) and the science Citation Index Expanded (SCI-EPANDED) to gain insights into the current state of VR integration in education. The analysis revealed variation in VR adoption and research output across countries and institutions, underscoring the importance of collaboration and knowledge-sharing in the field. Key research areas and trends, such as the use of VR for skill development and training, were identified. Additionally, the study highlighted the need for more research on the pedagogical effectiveness of VR. The findings carry practical implications for guiding future research shaping policy decisions and advocating for a concerted effort to harness VR’s capabilities in education. This study serves as a practical roadmap, promoting the implementation and improvement of VR technology and fostering equitable and inclusive educational practices. © The Author(s) 2024.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Design of Cattle Feed Measuring System Using Loadcell and MySQL Database

Design of Cattle Feed Measuring System Using Loadcell and My...

引用

2023 International Conference on Networking, Electrical engineering, computer science, and Technology, IConNECT 2023

作者： Samsugi, Selamet Warsito, Warsito Junaidi Styawati Afrisa, Firli Suryono, Ryan Randy Universitas Teknokrat Indonesia Faculty of Computer Science and Engineering Bandarlampung Indonesia Universitas Lampung Department of Physics Fmipa Bandarlampung Indonesia

ISBN: (纸本)9798350331172

In relation to cattle farming, many researchers conduct research to find solutions to problems that arise, especially with cows in the barn. Early research on the importance of clean and strong cowsheds was conducted in the early 20th century. In increasing the productivity of cattle development, another important thing is to pay attention to the food intake or feed of cows. Delays or waiting times in feeding cows can affect their growth. The information obtained indicates that each cow is expected to increase its weight by 1.5 kg. To achieve this goal, each cow is given 15 kg of feed per day, which is divided into three feedings. In each feeding, each cow will be given a ration of 5 kg, but from the observations obtained, it appears that the feed given is not really measured because no weighing is done before it is given to the cow and only uses estimates. With the creation of an automatic cow feed measurement system using an internet of things-based load cell, it can make it easier for cattle farmers to feed cows in a scheduled, measured, and monitored manner. The results of load cell calibration with standard scales give an error value of 0.5%, so the load cell scales are feasible to use as an automatic feed weight measuring tool. © 2023 IEEE.

关键词： Feeding

来源：评论

学校读者我要写书评

暂无评论

A Miniaturized Wideband Floret - Monopole Antenna for C Band Applications 12

A Miniaturized Wideband Floret - Monopole Antenna for C Band...

引用

12th IEEE International Conference on Advanced Computing, ICoAC 2023

作者： Vasudevan, Ramya Nagaraju, V. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Department of Electronics and Communication Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350318210

Due to its low power consumption, the ultra wideband floret monopole antenna discussed in this article is intended for short-range communication. Three florets were arranged symmetrically on the top substrate surface to increase gain and efficiency. Simulation software (HFSS) was used to analyse the florets' features. To increase the impedance bandwidth, the substrate's bottom is provided with a partial ground. Broadband applications are served by the proposed antenna's simulated impedance bandwidth, which ranges from 4 to 9 GHz. It is built on a low-profile, inexpensive FR4 substrate. The antenna's total measurements are 20 x20x0.8mm3. The antenna has a maximum gain of 2.74 dB and emits omnidirectionally at a frequency of 6 GHz. The suggested miniaturized antenna supports 5G LTE (4,S-5 GHz), WiFi 7, and C band (4-8 GHz). Applications involving many frequencies can use the antenna. © 2023 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Fractional-order binary bat algorithm for feature selection on high-dimensional microarray data

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第6期14卷 7453-7467页

作者： Esfandiari, Ahmad Farivar, Faezeh Khaloozadeh, Hamid Department of Computer and Mechatronics Engineering Science and Research Branch Islamic Azad University Tehran Iran Department of Systems and Control Faculty of Electrical Engineering K. N. Toosi University of Technology Seyed-Khandan Shariati Ave. Tehran16317-14191 Iran

High-dimensional microarray data suffer from the confounding effects of irrelevant, redundant and noisy genes on the scalability and efficiency of classification algorithms. In order for an effective dimensionality reduction and the selection of informative genes, this paper introduces a novel approach using fractional calculus concepts. This study proposes a modified version of binary the bat algorithm named fractional-order binary bat algorithm (FBBA) able to control the convergence process using more historical memory of bat behaviors. The gene selection technique contains a two-stage hybrid filter/wrapper method which employs a new correlation-based feature clustering (CFC) algorithm in the filter stage and the FBBA in the wrapper stage. The CFC-FBBA is evaluated on ten microarray gene expression datasets by employing the support vector machine classifier with a k-fold Monte Carlo cross validation data partitioning model. Furthermore, the results show that the CFC-FBBA, while minimizing the size of the gene subset, achieves the highest classification accuracy in most cases compared to several state-of-art hybrid techniques. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Novel Method For Traffic Sign Detection Using Advanced Image Processing Techniques 8

A Novel Method For Traffic Sign Detection Using Advanced Ima...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Jenifer, A. Mary Balamanigandan, R. Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Electronics and Communication Engineering Tamil Nadu Chennai602105 India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350367904

The accurate detection of traffic signs is vital for the development of intelligent transportation systems and autonomous driving technologies. This paper focuses on traffic sign detection utilizing advanced image processing techniques. Our approach combines several state-of-the-art image processing methods, including Preprocessing, color segmentation, shape analysis, and feature extraction, to robustly identify and classify traffic signs in various environments. The proposed system is implemented using powerful image processing libraries such as OpenCV and scikit-image. Extensive experiments conducted on a comprehensive traffic sign dataset demonstrate the high accuracy and reliability of our method, even under challenging conditions such as partial occlusions, varying illumination, and diverse weather scenarios. The results reveal that our image processing-based approach significantly improves detection performance, providing a robust and efficient solution for real-time traffic sign recognition. This research contributes to enhancing road safety and advancing the capabilities of autonomous vehicles. © 2024 IEEE.

关键词： Traffic signs

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：