检索结果-内蒙古大学图书馆

ieee JOURNAL OF EMERGING AND SELECTED TOPICS IN INDUSTRIAL ELECTRONICS 2024年第2期5卷 779-789页

作者： Li, Ting Wang, Shiyong Luo, Yongchao Wan, Jiafu Luo, Ziren Chen, Minghao South China Univ Technol Sch Mech & Automot Engn Guangzhou 510640 Peoples R China Guangdong Engn Polytech Guangzhou 510000 Peoples R China South China Univ Technol Guangdong Prov Key Lab Precis Equipment & Mfg Tec Guangzhou 510640 Peoples R China

With the rapid advancements in surface mount technology (SMT), microelectronic packaging products are becoming smaller, denser, and defect-free. This has led to stricter requirements for surface quality inspection. In the realm of industrial visual inspection, there is a growing demand for three-dimensional imaging technology to achieve high-precision and fast image acquisition, as well as for AI-based online inspection models to enhance real-time defect detection. This article primarily focuses on first- and second-level package products for SMT microelectronics and discusses the main optical imaging technologies, analyzing the principles and limitations. Next, this article analyzes the current research status of intelligent detection models based on deep learning in industrial environments and discusses current technical issues in data augmentation, small object learning, and model lightweight. The article also summarizes the characteristics and applications of the latest representative products, comparatively analyzes the gap between developed and developing countries. Finally, this article outlines four major challenges and future research trends in this field, aiming to promote the intelligent evolution of related visual inspection equipment.

关键词： Inspection Three-dimensional displays Microelectronics Packaging Imaging Soldering visualization data augmentation model lightweight small object learning three-dimensional (3-D) defect detection 3-D imaging

来源：评论

学校读者我要写书评

暂无评论

Outlining the Open Digital Twin Platform 9

Outlining the Open Digital Twin Platform

引用

9th ieee Smart World Congress, SWC 2023

作者： Grubel, Jascha Rios, Carlos Vivar Zuo, Chenyu Ossey, Sabrina Franken, Robin M. Balac, Milos Xin, Yanan Axhausen, Kay W. Raubal, Martin Riba-Grognuz, Oksana Eth Zurich Center for Sustainable Future Mobility Zurich Switzerland Epfl Swiss Data Science Center Lausanne Switzerland Eth Zurich Transport Planning Group Zurich Switzerland Eth Zurich Geoinformation Engineering Group Zurich Switzerland

ISBN: (纸本)9798350319804

Complex simulations and machine-learning models increase in application in research, industry, and governance. However, applying these systems with reasonable accuracy and efficiency requires large-scale efforts of data collection, data transformation, data analysis, and data visualization. At the same time, maintaining the required infrastructure, software, and personnel skyrockets making these tools unavailable to many potential users. The paradigm of the digital twin offers a novel perspective on how to manage the data efficiently and make these systems available more steadily at a lower cost. We introduce the first prototype of the Open Digital Twin Platform (ODTP) that is designed to be openly available to all interested parties to enable a common framework and baseline for digital twin based research. ODTP uses containerization, loose coupling, and micro-services to provide dynamically composable digital twins. ODTP also provides tools for licensing resolution, privacy and access control, and reproducibility. In its first iteration presented here, ODTP implements a common mobility research pipeline of the eqasim pipeline for MATSim. These kind of programs are usually difficult to assemble and use, thus leading to dangerous versions of 'never change a running system'. ODTP converts them into an easy-to-use version making it possible to initiate mobility simulations with one click. ODTP enables the quick adding of relevant data sources and analytical pipelines related to any topic and make them easily usable, accessible and shareable to research, industry, and governance. Thus, ODTP expands the FAIR principle from data to the complete data life cycle. © 2023 ieee.

关键词： Containerization data Semantics Digital Twin Mobility Open Research data

来源：评论

学校读者我要写书评

暂无评论

Web Scraping for data Analytics: A BeautifulSoup Implementation 6

Web Scraping for Data Analytics: A BeautifulSoup Implementat...

引用

6th International Conference of Women in data science at Prince Sultan University, WiDS-PSU 2023

作者： Abodayeh, Ayat Hejazi, Reem Najjar, Ward Shihadeh, Leena Latif, Rabia Prince Sultan University College of Computer and Information Sciences Riyadh Saudi Arabia

ISBN: (纸本)9781665477239

Web scraping is an essential tool for automating the data-gathering process for big data applications. There are many implementations for web scraping, but barely any of them is based on Python's BeautifulSoup library. Therefore, this paper aims at creating a web scraper that gathers data from any website and then analyzes the data accordingly. For results and analysis, the web scraper has been implemented on the Amazon website which collects a product's name, price, number of reviews, rate, and link. We further highlighted the web scraper's capabilities by assimilating the results into an interface that integrates data visualization techniques to analyze the results gathered. The web scraper proved to be efficient upon execution, in which it scraped five pages and analyzed them, and visualized the information in approximately ten seconds. The limitations as a result of this implementation mainly revolved around applying it to specific product names rather than generic ones and extracting specific information that we wanted from the resulting products. Moreover, BeautifulSoup cannot extract all the data available to not compromise on speed. Further studies can be done by researchers who wish to reuse this implementation and modify it according to the data they want to extract, the analysis they wish to perform, and the website they wish to scrape. The implementation can be helpful, thus, to developers who are novices in the web scraping field or to researchers that wish to reuse the code for small data analytics projects. © 2023 ieee.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Wi-Fitness: Improving Wi-Fi Sensing With Video Perception for Smart Fitness

引用

ieee INTERNET OF THINGS JOURNAL 2025年第3期12卷 2876-2889页

作者： Wei, Mengli Zhao, Daguo Zhang, Lei Wang, Cheng Zhang, Yonggang Wang, Qi Fan, Xiaochen Zhong, Yaping Mao, Shiwen Wuhan Sports Univ Sports Big Data Res Ctr Wuhan 430079 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300050 Peoples R China Tianjin Univ Tianjin Key Lab Adv Network Technol & Applicat Tianjin 300050 Peoples R China Qilu Univ Technol Shandong Acad Sci Key Lab Comp Power Network & Informat Secur Minist Educ Jinan Peoples R China Tongji Univ Minist Educ Key Lab Embedded Syst & Serv Comp Shanghai 200092 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engineer Minist Educ Changchun 130012 Peoples R China Tiangong Univ Sch Elect & Informat Engn Tianjin 300387 Peoples R China Tiangong Univ Tianjin Key Lab Optoelect Detect Technol & Syst Tianjin 300387 Peoples R China Tsinghua Univ Inst Elect & Informat Technol Tianjin Tianjin 300467 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Auburn Univ Dept Elect & Comp Engn Auburn AL 36849 USA

With advancements in AI, smart home gyms are becoming increasingly popular for providing fitness assistance in indoor environments. In this research, we propose a layer-by-layer framework, called Wi-Fitness, which bridges video perception with Wi-Fi sensing for smart fitness. At the data preprocessing layer, the singular value decomposition-based channel state information denoising mechanism is leveraged to do the Wi-Fi data calibration. Diverse and high-quality training samples are generated by a random quantization-based data augmentation method. At the bimodal fusion layer, the heterogeneity between the Wi-Fi and video is mitigated by the local attention mechanism and the bimodal feature integration mechanism. For the video modality, the attention-based spatio-temporal graph convolutional network (AST-GCN Net) is proposed to refine spatial information. The spatio-temporal semantic alignment module is proposed to transfer spatial information from video to Wi-Fi and maintain temporal consistency across modalities. The fitness assessment layer provides exercise visualization. The generalization of Wi-Fitness is enhanced by layer-by-layer collaboration. Wi-Fitness demonstrates its effectiveness by achieving an average F1-Score of 92.68% in three typical indoor environments.

关键词： Wireless fidelity Sensors Feature extraction Sports Semantics Behavioral sciences Skeleton Privacy Wireless sensor networks Training Action recognition channel state information (CSI) multimodal skeleton Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

In-depth Analysis of Information Overflows and its Role in Shaping Future Knowledge Structures 3

In-depth Analysis of Information Overflows and its Role in S...

引用

3rd ieee International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Paranthaman, V. Kamal, M.D. Raj Balaji, V. Sunil, G. Adhi College of Engineering and Technology Dept. of Mechanical Engineering TN Chennai India Velammal Institute of Technology Department of Mechanical Engineering TN Chennai India Loyola Institute of Technology Department of Mechanical Engineering TN Chennai India School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India

ISBN: (纸本)9798350343274

This study provides a thorough evaluation of data deluges and how they will play a significant role in the development of future knowledge architectures. The suggested methodology is adaptable and interdisciplinary since it combines cutting-edge data mining, NLP, and network analysis methods. data mining, NLP, network analysis, content analysis, big data analytics, cognitive mapping, SNA, MNA, QR, and IV are all compared to the proposed method, as are machine learning algorithms, qualitative research methods, and data visualization. Accuracy, relevance, depth of analysis, innovation, practical consequences, and clarity are only a few of the areas where the suggested technique shines. Its greater analytical skills are shown by its persistent outperformance of conventional approaches. Additionally, the suggested approach better accords with ethical norms and responsible research procedures, thus they are all considered as well. In summary, this study demonstrates the value of looking at information floods from several angles of study. The suggested technique not only provides cutting-edge analytic instruments for negotiating the intricacies of the digital information ecosystem, but also gives a forward-looking viewpoint by anticipating new patterns and developments. It demonstrates how crucial it is to use cutting-edge methods and evolve with the information age. © 2023 ieee.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Exploration and Design of Intelligent Connected Vehicle Monitoring and Supervision Platform Based on Multi-Source data 11

Exploration and Design of Intelligent Connected Vehicle Moni...

引用

11th Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2023

作者： Dong, Shaoshuai Hu, Jianyao Wang, Xunji School of Automotive and Transportation Engineering Hefei University of Technology Hefei China School of Mechanical Engineering Southwest Jiaotong University Chengdu China The Fifth Electronics Research Institute of Ministry of Industry and Information Technology Guangzhou China Hefei Intelligent and Connected Vehicles Innovation Center Hefei China

ISBN: (纸本)9798350333664

With the rapid advancement of Intelligent Connected Vehicle (ICV), the demand for monitoring and supervision of vehicles has become increasingly urgent. To address this need, this paper presents a design for an ICV monitoring and regulation platform that leverages multi-source data. By gathering information from on-board sensors, traffic surveillance cameras, and road monitoring devices, such as traffic participant data, vehicle information, traffic conditions and surrounding environmental data, this platform can integrate multi-source data to achieve real-time monitoring and analysis of ICV behavior, safety and operational status. It presents a comprehensive view of road conditions and the overall functioning of the ICV, helping managers to monitor ICV operations from a large to a small scale. By engaging with the ICV, this platform enables management and regulation of the ICV, thereby improving operational efficiency and safety. Additionally, it provides precise analysis and optimization suggestions for vehicle operating status, assisting management personnel in understanding vehicle performance and capabilities. The design of this platform offers a comprehensive and efficient solution for ICV monitoring and supervision, providing robust support for the advancement of Intelligent Transport Systems (ITS) and the widespread adoption of ICV. © 2023 ieee.

关键词： artificial intelligence ICV multi-source data visualization module

来源：评论

学校读者我要写书评

暂无评论

Interactive Volume Rendering Module using Two-Dimensional Transfer Function on Cone-Beam Computed Tomography data 10

Interactive Volume Rendering Module using Two-Dimensional Tr...

引用

10th International Conference on Signal Processing and Integrated Networks, SPIN 2023

作者： Bhat, Shreenidhi H Hareesha, K.S. Kamath, Abhay T Kudva, Adarsh Shashank, H. Manipal Institute of Technology Manipal Academy Higher Education Dept. of Data Science and Applications Karnataka Manipal India Kmc Hospitals Balmatta Dept. of Dental Sciences Karntaka Mangalore India Manipal Academy Higher Education Manipal College of Dental Sciences Dept. of Oral Maxillofacial Surgery Karnataka Manipal India Manipal Institute of Technology Manipal Academy Higher Education Dept. Information and Communication Technology Karnataka Manipal India

ISBN: (纸本)9781665490993

The transfer function's design has a direct impact on the outcome of the medical image visualization. A well-designed transfer function can boost both image quality as well as visualization speed. In this paper, a new approach is proposed for developing an interactive ubiquitous volume rendering module using a 2D histogram-based transfer function on medical data. The set of direct manipulation widgets in VTK is used to demonstrate interactive and intuitive 2D transfer functions. Also, the interaction in the histogram was done by adding multiple control points, which act as the boundary-emphasizing function designed to identify regions of the transfer function. The CBCT dataset of the dentofacial images is used to evaluate the outcome of the proposed 2D transfer function by highlighting the required features in the dentofacial volume. By comparing with the 3D Slicer open-source software, the effectiveness and quality were much more accurate, and more detailed clear information can be visualized from the proposed approach. © 2023 ieee.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

Visual Explanations: Activation-based Acute Lymphoblastic Leukemia Cell Classification

Visual Explanations: Activation-based Acute Lymphoblastic Le...

引用

ieee International Conference on Development and Learning (ICDL)

作者： Raza, Muhammad Umair Nawaz, Adil Liu, Xintong Chen, Zhuangzhuang Leung, Victor C. M. Chen, Jie Li, Jianqiang Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen Peoples R China

ISBN: (纸本)9781665470759

The saliency methods are widely used for generating heatmaps that emphasize the important portions of an input image for deep networks on a specific classification task. Interpretability is crucial for deploying deep neural networks in real-world applications. However, the heatmaps produced by current visual explainable methods may contain or visualize particulars differently. To analyze and compare the visualization of different methods, such as Gradient-based, Activation-based, Perturbation-based, and Region-based methods, we empirically evaluated them on the acute lymphoblastic leukemia (cancer cell) classification task using state-of-the-art convolutional neural networks. We also visualized the essential pathological features (salient parts) that are the reasons for the classification results on the classification of normal versus malignant cell (CNMC) dataset.

关键词： Explainable AI Post-hoc Interpretability Visual explanations Cancer cell classification

来源：评论

学校读者我要写书评

暂无评论

Augmenting the Problem Frames Approach with Explicit data Descriptions using ChatGPT 31

Augmenting the Problem Frames Approach with Explicit Data De...

引用

31st ieee International Requirements Engineering Conference (RE)

作者： Xie, Ling Xiao, Hongbin Li, Zhi Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Peoples R China Guangxi Normal Univ Guangxi Key Lab Multi Source Informat Min & Secur Guilin 541004 Peoples R China

ISBN: (纸本)9798350326918

Problem Frames (PF) as a mainstream requirements analysis method has attracted extensive attention and research in the field of requirements engineering. However, the current problem diagram as a PF visualization tool is more abstract and lacks the ability to express data descriptions. In this paper, we propose a method to extend problem diagrams based on ChatGPT. The aim is to detail the requirements to ensure a more accurate and comprehensive representation of the complex requirements of the system. We combine problem diagrams and ChatGPT by letting them interact with each other, and obtain the cause table describing causal relationships that exist within shared phenomena, then we model the cause table and calculate the structural coefficient of each cause and rank the causes from the largest to the smallest. Finally the ranked causes are used as an extension of the shared phenomenon, thus using the property that they can help improve the detailed descriptions of the requirements. A case study of an insulin injection control system demonstrates the applicability and viability of this method.

关键词： ChatGPT Problem Frames Structural Causal Model Requirements Engineering

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Prediction using Deep Learning Techniques

Skin Cancer Prediction using Deep Learning Techniques

引用

2023 International Multi-Disciplinary Conference in Emerging Research Trends, IMCERT 2023

作者： Irfan, Tayyab Rauf, Abid Iqbal, M Javed University of Engineering and Technology Department of Computer Science Taxila Pakistan

ISBN: (纸本)9798350347708

There is a growing need for early diagnosis of skin cancer because of the rapid growth rate of melanoma skin cancer, its high treatment costs and high mortality rate. The detection of skin cancer cells was usually done manually, and most cases require a lengthy cure. Currently the main problem in skin cancer detection is high misclassification rate and low accuracy. This paper provides a technique based on deep learning techniques to detect the cancer from skin images. Convolutional neural network-based model consisting of six layers with hidden layers is used in this work. The problem of low accuracy is addressed with the help of regularization technique and features are selected with the help of convolution method. To improve the accuracy of the model hyper parameter tuning along with model parameter tuning are performed. Publicly available dataset is used in the research which contains images with cancer and normal instances. The major steps in this work includes data collection, preprocessing, data cleaning, visualization, and model development. At the end a comparative analysis is performed with state-of-The-Art techniques. The proposed model achieved good accuracy of 88% on HAM dataset as compared to state of the art techniques. © 2023 ieee.

关键词： Diagnosis

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：