检索结果-内蒙古大学图书馆

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ren, Pengzhen Li, Changlin Wang, Guangrun Xiao, Yun Du, Qing Liang, Xiaodan Chang, Xiaojun Northwest Univ Xian Shaanxi Peoples R China Univ Technol Sydney AAII ReLER Sydney NSW Australia Univ Oxford Oxford England South China Univ Technol Guangzhou Guangdong Peoples R China Sun Yat Sen Univ Guangzhou Guangdong Peoples R China PengCheng Lab Shenzhen Guangdong Peoples R China RMIT Univ Melbourne Vic Australia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window. Most current work uses a fixed single-scale window for modeling by default, ignoring the impact of window size on model performance. However, this may limit the modeling potential of these window-based models for multi-scale information. In this paper, we propose a novel method, named Dynamic Window Vision Transformer (DW-ViT). The dynamic window strategy proposed by DW-ViT goes beyond the model that employs a fixed single window setting. To the best of our knowledge, we are the first to use dynamic multi-scale windows to explore the upper limit of the effect of window settings on model performance. In DW-ViT, multi-scale information is obtained by assigning windows of different sizes to different head groups of window multi-head self-attention. Then, the information is dynamically fused by assigning different weights to the multi-scale window branches. We conducted a detailed performance evaluation on three datasets, ImageNet-1K, ADE20K, and COCO. Compared with related state-of-the-art (SoTA) methods, DW-ViT obtains the best performance. Specifically, compared with the current SoTA Swin Transformers [31], DW-ViT has achieved consistent and substantial improvements on all three datasets with similar parameters and computational costs. In addition, DW-ViT exhibits good scalability and can be easily inserted into any window-based visual transformers.(1)

关键词： Performance evaluation visualization Systematics Computational modeling Scalability Transformers Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning Applications and visualizations Taxonomy of Blockchain Data

Ensemble Learning Applications and Visualizations Taxonomy o...

引用

Data Science and information System (ICDSIS), ieee International conference on

作者： Ramachandra Rao Kurada Y Ramu N. Silpa V.V.R. Maheswara Rao Sunil Pattem L. Pallavi Department of CSE Shri Vishnu Engineering College for Women Bhimavaram India Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur India

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

Trading particularly in blockchains are being hailed as a disruptive force in the finance sector and are instrumental as a monumental task. Ensemble Learning (EL) techniques have an enduring legacy in such aspects, as they combine multiple models to enhance performance and increase accuracy in predictive modeling. This study meticulously unfolds two distinct sections intended to document of the observations the vision of model building to uphold the unprecedented values of blockchains and embark visual indepth understanding of information. From this perspective, this transcript devolves the prime objective into a deeper understanding of blockchain data with EL methods to peruse the concealed knowledge in the blocks. Data visualization of blockchain data objectively stands as a service look at history seemingly with a characteristic of immense and self-restraint value to users. Hence, the subsequent objective bestows to present the epitomization of cryptocurrency websites envies with the economic renaissance pontificated in blockchains.

关键词： visualization Accuracy Biological system modeling Taxonomy Data visualization Predictive models Blockchains

来源：评论

学校读者我要写书评

暂无评论

Comparing Logistic Regression and Tree Models on HR Data

Comparing Logistic Regression and Tree Models on HR Data

引用

2023 International conference on Advanced Computing and Communication Technologies, ICACCTech 2023

作者： Patil, Aaditya Sarda, Tejas Shetye, Snehal Bachchan, Srishti Gutte, Vitthal S. Mit World Peace University Department of Computer Engineering and Technology Pune India

ISBN: (纸本)9798350380880

This research paper offers a thorough analysis carried out within the HR department of a consulting firm with the goal of improving employee satisfaction and retention through data-driven tactics. The research explores a broad range of employee data, including job satisfaction, performance indicators, project participation, working hours, tenure, accidents, promotions, departmental links, and pay information. The HR department and any pertinent parties with an interest in the researcher's results are included as *** study is divided into several sections that cover project design, careful data analysis, and execution tactics. Understanding the business environment, conducting a thorough data exploration, and evaluating prediction models are priorities. The research makes use of tree-based machine learning and logistic regression techniques to provide data-driven suggestions for improving employee satisfaction and retention. The study is noteworthy for the way ethical issues are intertwined throughout, highlighting how crucial it is to process data responsibly and make moral decisions. Resources are actively used to discuss moral conundrums and provide workable answers. The main objective of this study's findings is to enable firms to make well-informed decisions that promote a happy and persistent staff. It does this via a holistic approach to HR data analysis. © 2023 ieee.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Flow visualization Software based on MATLAB 5

Design and Implementation of Flow Visualization Software bas...

引用

5th ieee information Technology, Networking, Electronic and Automation Control conference, ITNEC 2021

作者： Teng, Xianshu Zhang, Mingnan Li, Yilin Qiao, Wensheng Shanghai University The Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai200072 China China Aerospace Science and Industry Corporation The 601st Institute The 6th Academy Hohhot010076 China

ISBN: (纸本)9781665415989

With the continuous development of scientific visualization, visualization has been applied to various fields. Flow field visualization is an important part of the visual field, by using computer graphics, computer vision, and image processing technology, it can use intuitive graphical images to describe the flow field structure of the complex, disorder, which makes the flow field visualization in the field of meteorology, aviation and geography have great application prospect. This paper uses MATLAB App Designer to design a flow field visualization software, which mainly displays the scalar or vector velocity field in two dimensions and three dimensions. The software has a powerful interactive function, can choose different flow field display modes, can choose a specific two-dimensional section for separate display. With this software, flow field data can be clearly, succinctly, and intuitively displayed, and key information such as flow field distribution, movement trend, and velocity change can be understood. In addition, the software uses MATLAB App Designer to encapsulate the form of desktop independent APP, which is simple and convenient to use. © 2021 ieee.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Exploring Explainability and Transparency in Deep Neural Networks: A Comparative Approach 7

Exploring Explainability and Transparency in Deep Neural Net...

引用

7th International conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Bhagya, J. Thomas, Jeena Raj, Ebin Deni Indian Institute of Information Technology Department of Computer Science Kottayam India

ISBN: (纸本)9798350397253

Explainability in Artificial Intelligence (AI) helps define model accuracy, clarity, transparency, and results in decision-making backed by AI. A business needs to establish reliability and trust when implementing AI models. Explainability provides a responsible approach to AI development. This paper's primary objective is to examine the visual explanation property of various interpretability methods. An attempt is made to understand how a convolutional neural network's output can be explained. It was common practice to refer to the deep learning models as black boxes;however, our primary concern is determining precisely what takes place within them. Explainability will give us an understanding of which all elements lead to a prediction. A few techniques for providing visual explanations from Convolutional Neural Network (CNN)-based models are the focus of our investigation. The transparency that can be achieved through visualization receives the most attention. Along with this, attention is given to class discrimination and whether the model takes into account the smallest of details. There have been several proposals for creating deep learning models that are intuitive. In this paper, an attempt is made to determine the effectiveness and drawbacks of Grad-CAM, Ablation-CAM, Score-CAM, and Eigen-CAM. © 2023 ieee.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Novelty Detection of Text Using Spectral Graphs and visualization

Novelty Detection of Text Using Spectral Graphs and Visualiz...

引用

Global conference for Advancement in Technology (GCAT)

作者： Remya R.K. Menon Fawaz-Al-Faizi U.L Sooraj Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

Novelty detection is the process of identifying the presence of new or unknown information in a given text dataset that does not conform to the existing patterns or patterns seen in the past. There have been some studies on the application of spectral graph-based methods for novelty detection in text data. There is still a gap in the literature on the integration of these techniques with visualization methods to enhance the interpretability of the results. Our work aims to fill this gap in the literature by proposing a novel approach that combines spectral graph-based methods with visualization techniques for the task of novelty detection in text data. The proposed approach of combining spectral graph-based methods with visualization techniques can effectively detect novel documents among text data collection while also providing interpretable results. Our contribution is a novel framework that integrates these two methods, which can be applied to various domains that require novelty detection in text data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sales System Efficiency through Process Mining 21

Enhancing Sales System Efficiency through Process Mining

引用

21st International conference on ICT and Knowledge Engineering, ICT and KE 2023

作者： Ratisaksoontorn, Kandit Saguansakdiyotin, Norranut Intarasema, Sarayut Graduate School of Information Technology Siam University Bangkok Thailand

ISBN: (纸本)9798350308716

This research presents a comprehensive analysis of sales systems in quotation preparation, focusing on identifying underlying issues contributing to delays and deviations from predefined targets. This investigation is facilitated by applying process mining techniques, which enable the discovery and visualization of actual bottlenecks within an IT equipment sales company's sales system in Thailand. The study utilizes a three-year dataset from the company's sales system database. The research methodology consists of three essential steps: 1. Event Log Format Presentation, 2. Data Import into Fluxicon Disco Software, and 3. Data Analysis with Process Mining. The outcomes of this investigation underscore the effectiveness of process mining in revealing key insights, including extended waiting times for quotation approvals, frequent requests for quotation modifications, and notable challenges within the system. By analyzing the workload of employees, this research provides a framework for troubleshooting sales system issues, offering a pathway for enhancing quotation approval processes and reducing the frequency of quotation corrections. In today's era of perpetual digital transformation and relentless competition, this research positions itself as a model for effective digital transformation within organizations, seeking to drive essential changes that align with the evolving landscape of the digital age. © 2023 ieee.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Line Weaver: Importance-Driven Order Enhanced Rendering of Dense Line Charts

引用

COMPUTER GRAPHICS FORUM 2021年第3期40卷 399-410页

作者： Trautner, T. Bruckner, S. Univ Bergen Bergen Norway

Line charts are an effective and widely used technique for visualizing series of ordered two-dimensional data points. The relationship between consecutive points is indicated by connecting line segments, revealing potential trends or clusters in the underlying data. However, when dealing with an increasing number of lines, the render order substantially influences the resulting visualization. Rendering transparent lines can help but unfortunately the blending order is currently either ignored or naively used, for example, assuming it is implicitly given by the order in which the data was saved in a file. Due to the non-commutativity of classic alpha blending, this results in contradicting visualizations of the same underlying data set, so-called "hallucinators". In this paper, we therefore present line weaver, a novel visualization technique for dense line charts. Using an importance function, we developed an approach that correctly considers the blending order independently of the render order and without any prior sorting of the data. We allow for importance functions which are either explicitly given or implicitly derived from the geometric properties of the data if no external data is available. The importance can then be applied globally to entire lines, or locally per pixel which simultaneously supports various types of user interaction. Finally, we discuss the potential of our contribution based on different synthetic and real-world data sets where classic or naive approaches would fail.

关键词： CCS Concepts • Human-centered computing → information visualization visualization techniques visualization theory concepts and paradigms

来源：评论

学校读者我要写书评

暂无评论

Investigating the Use of Data Mining for Knowledge Discovery 3

Investigating the Use of Data Mining for Knowledge Discovery

引用

3rd International conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Sunil, M.P. Pandey, Megha Garima Janakiraman, V. Maral, Vikas B. Das, Sidhant Department of Electronics and Communication Engineering Faculty of Engineering and Technology Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350319125

Fact mining has emerged as one of the most promising information discovery strategies in tremendous and complex databases. The tourism quarter advantages highly from records mining, as it can provide specific insights into how customers view and transact with the industry. In recent years, fact mining has grown exponentially within the tourism region, making it vital for researchers to apprehend how it can be implemented to discover meaningful information and inform strategic choice-making. This paper examines the potential of fact mining for know-how discovery in tourism, along with supervised and unsupervised learning techniques, artificial intelligence, predictive modeling, and information visualization. The authors talk about the results of technological improvements in information mining and the ability of tourism organizations to benefit from its use. They then speak of realistic examples of statistics mining programs inside the tourism area, from tracking client reviews to forecasting vacationer trends. An assessment of the prevailing literature is presented to assess knowledge discovery strategies inside the field of tourism. Ultimately, the authors recommend avenues for destiny studies in this location. © 2023 ieee.

关键词： conclusion forecasting knowledge presented technology

来源：评论

学校读者我要写书评

暂无评论

The Research on Security Model Algorithm in Intelligent Connected Vehicles 6

The Research on Security Model Algorithm in Intelligent Conn...

引用

6th ieee International conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2022

作者： Xiong, Shaojun Qi, Xiangtao Wuhan Business University School of Information Engineering Wuhan City China

ISBN: (数字)9781665469869

ISBN: (纸本)9781665469869

With the rapid development of mobile internet technology, the Intelligent Connected Vehicles(ICV), as an important support system for intelligent transportation, has become the future development direction of the intelligent networked industry. The 5G mobile network is characterized by three aspects, ultra-high speed, ultra-large connection, and ultra-low latency. These characteristics realize the digitization and visualization of the perception ability of vehicles in the Internet of Vehicles(IoV), and promote the integration and development of related technologies in the ICV. It is foreseeable that the IoV will generate a large amount of communication data in future application scenarios. However, the application of the IoV frequently involves private information data such as vehicle's location, driving-data, and user-identity. Therefore, the increasing demand in communication volume will aggravate the leakage of communication data in the ICV. The risk maybe lead to safety hazards. Based on the design characteristics of its own interface mode of the Internet in the ICV communication system, the ICV is prone to network attacks, such as malicious network attacks such as illegal intrusion, remote control and anonymous tracking. This paper intends to explore the methods to solve the hidden dangers in communication security through the theoretical research and analysis of the information security model in the ICV. © 2022 ieee.

关键词： Vehicles

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：