检索结果-内蒙古大学图书馆

Enhancing Human Pose Estimation in Internet of Things via Diffusion Generative Models

ieee INTERNET OF THINGS JOURNAL 2025年第10期12卷 13556-13567页

作者： Wu, Sifan Zhang, Hongzhe Liu, Zhenguang Chen, Haipeng Jiao, Yingying Jilin Univ Coll Comp Sci & Technol Minist Educ Changchun Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun Peoples R China China Univ Polit Sci & Law Sch Discipline Inspect & Supervis Beijing 100088 Peoples R China Zhejiang Univ State Key Lab Blockchain & Data Secur Hangzhou 310027 Peoples R China Inst Blockchain & DataSecur Hangzhou High Tech Zone Binjiang Hangzhou 310059 Peoples R China Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310014 Peoples R China

With the ongoing development of public video surveillance technology, accurate human pose estimation is becoming increasingly important in urban administration and law enforcement. However, existing methods rely on large-scale dense annotations, which are labor-intensive and time-consuming. To tackle this, we propose SparsePose which leverages training videos with sparse annotations (labeled every k frames) to learn to propagate temporal poses that help to estimate the poses in unlabeled frames. Technically, we engage in a novel dual-branch architecture that combines 1) pose forecasting of the consecutive neighboring frames with 2) visual clues of the current frame and the nearest labeled frames. We theoretically derive the intrabranch and interbranch mutual information loss to supervise that maximized pose-relevant features are extracted from the current frame and different branches complement each other to approach precise pose estimation. Additionally, we propose a diffusion generative enhancement, which improves the robustness of the model to challenging scenes from the perspective of diversity. Empirical results show that our method significantly outperforms the state-of-the-art methods in sparsely labeled pose estimation on three benchmark datasets.

关键词： Pose estimation Internet of Things Heating systems Annotations Mutual information Cameras visualization Streaming media Behavioral sciences Accuracy Human pose estimation mutual information (MI) multiperson sparsely labeled

来源：评论

学校读者我要写书评

暂无评论

A Content-Based Study and Tweet Analysis of the Russia-Ukraine Conflict 1

A Content-Based Study and Tweet Analysis of the Russia-Ukrai...

引用

1st ieee International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Ingole, Rohit V. Katrojwar, Himanshu R. Bhoge, Harsh N. Giradkar, Aditya M. Kalbande, Kamlesh Morris, Nekita Chavan G H Raisoni College of Engineering Department of Data Science Nagpur440016 India Nagpur440016 India

ISBN: (纸本)9798350323795

Twitter analysis has emerged as a fascinating field of inquiry, and the recent Russia-Ukraine conflict has garnered significant international interest. Twitter users, particularly those from Ukraine, have turned to the platform to share their experiences, seek support, and more. Existing research has predominantly concentrated on sentiment analysis, but there is a rising enthusiasm for exploring social media analysis in greater depth. Thus, this research aims to present a holistic perspective on the situation by employing advanced methodologies such as text cleaning, preprocessing, and visualization. The research findings encompass a comprehensive analysis of the text, including aspects such as word distribution, word length distribution, counting stopwords, analyzing hashtags, examining mentioned users, and visualizing text word clouds. These various techniques were employed to thoroughly investigate and gain insights from the text under study. © 2023 ieee.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Touch the Collections: A 3D UI Prototype in DSpace-7

Touch the Collections: A 3D UI Prototype in DSpace-7

引用

23rd ACM/ieee Joint Conference on Digital Libraries (JCDL)

作者： Yang, Le Zhang, Zhongda Univ Oregon Eugene OR 97403 USA Univ Oklahoma Norman OK 73019 USA

ISBN: (纸本)9798350399318

Institutions have focused on the digitization process, metadata workflow, and digital infrastructure development for digital librarianship in recent decades. The undergoing digital shift that is accelerated by the pandemic crisis has signified the importance of visualizing digital collections because digital presence is no longer a preview of the physical collection;instead, the digital presence has become the primary access point. Replacing the heavily text-based browsing features, visualization and interactive design in digital repositories are used to facilitate communication, presentation, discovery, and comprehension of digital and digitized heritage. This project explores and demos the first 3D user interface that visually outlines and interactively exhibits communities and collections in DSpace-7 and discusses the applicable scenarios. The integration of the developed modules will be released as open sources on GitHub once completed.

关键词： Open Repository DSpace-7 data visualization 3D Prototype

来源：评论

学校读者我要写书评

暂无评论

Manhole Cover Monitoring System

Manhole Cover Monitoring System

引用

2023 China Automation Congress, CAC 2023

作者： Hu, ZhiJie Gui, XiaoLin Huang, RunYan School of Computer Science Xi'an Jiaotong University Xi'an China School of Information Engineering Xi'an Eurasia University Xi'an China

ISBN: (纸本)9798350303759

Statistics show that there are 3000 4000 manhole covers per square kilometer of the city. So many manhole covers are often stolen. In addition, if the maintenance of the manhole covers is not timely, it can easily cause vehicle traffic accidents, and even the occurrence of 'manhole covers eat people' incidents. They pose a serious threat to the safety of vehicles and pedestrians. In view of the above problems, this system designed the intelligent manhole cover monitoring system. This system collects the environmental data of the manhole cover in real time through the Angle inclination sensor, position sensor, water level sensor, and combustible gas sensor, respectively. STM32F103C8T6 processes the data collected by the sensors and displays the processed data on the display module. When the processed data exceeds the threshold value, the alarm module alarms. At the same time, the processed data will also be uploaded to the upper computer through the Wi-Fi module, so that the administrator can view the data remotely. After testing, the system has the characteristics of fast response speed, high collection accuracy, good stability, and so on. It provides a theoretical basis for the management of urban manhole cover and has a certain reference value. © 2023 ieee.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

Cell Tour: Learning About the Cellular Membrane Using Virtual Reality 53

Cell Tour: Learning About the Cellular Membrane Using Virtua...

引用

53rd ieee ASEE Frontiers in Education International Conference, FIE 2023

作者： Poulter, Hope Diebold, Logan Kelly, Sean Pakalapati, Samuel Rao, Asha Rojas-Muñoz, Edgar School of Performance Visualization & Fine Arts Texas A&m University College StationTX United States Texas A&m University Department of Computer Science and Engineering College StationTX United States Texas A&m University Department of Electrical and Computer Engineering College StationTX United States Texas A&m University Department of Biology College StationTX United States

ISBN: (纸本)9798350336429

Virtual reality (VR) technology has emerged as a promising tool in education, offering new possibilities for learning in immersive environments. This paper explores the application of VR in biology education, specifically focusing on teaching the functionality of the cell membrane. The traditional methods of textbook reading and microscopic observation lack interactivity and engagement, motivating the development of a VR-based learning approach designed as a game-like experience. The study compares the knowledge gain of participants who played the VR game with a control group who watched instructional videos. Surprisingly, the control group exhibited a higher knowledge gain compared to the VR group. Analysis suggests that the VR participants were more distracted by the immersive nature of the VR environment and focused less on the instructional content. Future research involving larger and more motivated participant groups, such as freshmen or high school students, may yield different results. Despite the observed limitations, this study highlights the importance of balancing immersive experiences with focused instructional content for better learning outcomes. © 2023 ieee.

关键词： data visualization Human-Computer Interaction Student Engagement Virtual Reality

来源：评论

学校读者我要写书评

暂无评论

Internet Financial data Mining and Analysis Based on Internet data 12

Internet Financial Data Mining and Analysis Based on Interne...

引用

12th International Conference of Information and Communication Technology, ICTech 2023

作者： Wang, Xinyu Xing, Wenbin School of International Education Wuhan University-of Technology Wuhan China School of Computer Science and Artificial Intelligence Wuhan University-of Technology Wuhan China

ISBN: (纸本)9798350332919

Based on the financial data in the Internet, the system uses data mining technology to collect and mine the specified target financial data from the financial website page, provide corresponding financial information according to the needs of different groups, and create a financial business operation law and financial business information for today's college students and financial practitioners. The statistical analysis system of financial risk dynamics and other information completes the real-time collection of financial data with time series in Internet financial websites, so that those in need can know the real-time information and data analysis of the financial industry at any time. The system also provides personalized customized services for practitioners, complete financial screening plans, and realize the dynamic visualization of financial information. A service platform for online communication and information sharing between employees and social people. In most cases, financial data is expressed in the form of time series. This project proposes the relevant financial data mining and analysis system platform, which can efficiently mine the potential high-value data in the massive financial time series data, and is also conducive to the research of financial data analysis system in data mining. The research of this project has a certain degree of theoretical and practical significance. © 2023 ieee.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Poultry Farms from Aerial Images for Actionable AI System toward Biosecurity Applications

Automated Detection of Poultry Farms from Aerial Images for ...

引用

2023 ieee Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Li, Yu Das, Rana Duong, Cuong Lim, Teng-Teeh Haithcoat, Timothy Ersoy, Ilker Shyu, Chi-Ren University of Missouri Department of Electrical Engineering and Computer Science ColumbiaMO United States University of Missouri Biological Engineering ColumbiaMO United States University of Missouri Plant Science and Technology Extension ColumbiaMO United States University of Missouri Institute for Data Science and Informatics Columbia United States University of Missouri Institute for Data Science and Informatics Electrical Eng. and Computer Science Dept. ColumbiaMO United States

ISBN: (纸本)9798350359527

Poultry productions have shifted towards larger farms and often cluster in certain regions. However, many of the smaller farms with a considerable amount of production are not considered concentrated animal feeding operation under regulation in many regions, and therefore are not required to obtain a permit. As a result, information of these operations is not being recorded and monitored, contributing to an increased risk for biosecurity issues. The development in computer vision and availability of high-resolution remote sensing imagery allows the possibility for automatic localization and operation estimation of the unregistered farms, filling in the missing information needed for biosecurity risk management. The farm information extracted from images can be incorporated with other available geospatial data, such as road networks, watersheds, etc., to build a comprehensive knowledge base for actionable plans. In the current study, we present a framework for automated localization, analysis, and visualization of poultry farms from remote sensing images. A robust machine learning method was developed to computationally link the visual features from remote sensing imagery to Missouri Department of Natural Resources Concentrated Animal Feeding Operation data, to identify the animal farm type, location, and potential capacity in the region. The developed process can be performed automatically on images of different timestamps to analyze temporal and spatial development of poultry production facilities of a region. This research contributes to the effective management and regulation of poultry and potentially other animal farms, providing insights into farm characteristics and capacities while facilitating informed decision-making. © 2023 ieee.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

UnStressMe: Explainable Stress Analytics and Self-tracking data visualizations

UnStressMe: Explainable Stress Analytics and Self-tracking D...

引用

2023 ieee International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

作者： Paraschou, Eva Yfantidou, Sofia Vakali, Athena Aristotle University of Thessaloniki Thessaloniki Greece

ISBN: (纸本)9781665453813

Self-tracking technology for behavior monitoring is prevalent in various aspects of human life. It enables users' activities tracking with data produced 'in the wild', namely capturing real-world physical activity, sleep patterns, and stress levels, among others. Advanced new sensors integrated into commercial self-tracking devices have empowered a new era of sensing data exploration and self-improvement recommendations, aiming to enhance physical and mental well-being. However, the collected data and related inferred knowledge are not always well-explained or well-presented and discourage users' commitment leading to sensing devices' abandonment. To sustain user engagement with self-tracking technology for well-being, this paper introduces a comprehensive framework and respective full-stack web service called 'UnStressMe' for the analysis of diverse data modalities tracked in the wild, the prediction of future stress behavior and the production and provision of personalized, model-agnostic explanations and interactive visualizations. We showcase the utility of our framework through a mental health use case, paving the way for explainable, transparent, and human-centric self-tracking technology. © 2023 ieee.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Real-time Monitoring of Two-phase Flow Using Electrical Impedance Tomography with Convolutional Neural Network

Real-time Monitoring of Two-phase Flow Using Electrical Impe...

引用

2023 ieee International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Yang, Xuanxuan Chen, Haofeng Xu, Gengchen Ma, Gang Wang, Xiaojie Chinese Academy of Sciences Institute of Intelligent Machines Hefei Institutes of Physical Science Hefei230031 China The University of Science and Technology of China Hefei Anhui230026 China

ISBN: (纸本)9798350327182

Two-phase flow is common in industrial systems, and monitoring the state of two-phase flow is important for production and manufacturing. Electrical impedance tomography (EIT) is a promising non-invasive visualization technique for monitoring two-phase flows. However, in stratified flow, traditional algorithms have low imaging accuracy and can produce artifacts, making it difficult to accurately determine the interface between the two phases. In this paper, we propose a real-time monitoring method for stratified two-phase flow using EIT with a convolutional neural network (CNN). We use the Impedance Matrix (IM) to train the CNN model to reconstruct stratified two-phase flow images. The proposed method is evaluated on a series of simulated data sets with different noise levels and compared with traditional image reconstruction methods such as the NOSER algorithm. Furthermore, the effectiveness of the method for real-time monitoring of multiphase flows in pipes is verified. The results show that the proposed CNN-based method is superior to traditional methods in terms of imaging reconstruction accuracy and noise robustness and can be used for real-time monitoring of stratified two-phase flow. This study provides a promising method for real-time monitoring of stratified two-phase flow. © 2023 ieee.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification using G-XGB

Human Activity Classification using G-XGB

引用

2023 International Conference on data science and Network Security, ICDSNS 2023

作者： Kataria, Aman Puri, Vikram Pareek, Piyush Kumar Rani, Sita Amity Institute of Defence Technology Amity University Noida Campus Sector-125 Noida India Duy Tan University Center of Visualization and Simulation Da Nang Viet Nam Cell Nitte Meenakshi Institute of Technology Dept. of Artificial Intelligence and Machine Learning and Ipr Bengaluru India Guru Nanak Dev Engineering College Department of Computer Science and Engineering Ludhiana India

ISBN: (纸本)9798350301595

Wearable body sensors have recently gained popularity because they monitor user behaviors and vital indicators. These sensors are designed to monitor various physiological factors, such as motion, temperature, and heart rate, among others. Making sense of the data gathered by these sensors requires separating the dependent and independent features. The dependent parameters are those that body-worn sensors can read in this scenario. Examples of such elements include blood oxygen levels, heart rate, temperature, mobility, and airflow. These sensors capture data about a person's activity and health. The independent parameters in wearable body sensors are related to the dependent parameters, whereas the dependent parameters are those that the sensors can measure directly. Such characteristics include age, sex, weight, and environmental influences. For example, humidity and airflow might impair a temperature sensor's accuracy. The user's age or level of physical fitness may also influence the accuracy of a heart rate monitor. Activity monitors are used in this study to capture the actions of various people. Static and dynamic properties are derived from the activity monitor recording. The performance evaluations of the eight distinct machine-learning models that were created using the retrieved features are discussed in this paper. The Grid Search method is used to enhance the performance of the XGB model. © 2023 ieee.

关键词： Heart

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：