检索结果-内蒙古大学图书馆

Checking the Truthfulness of News Channels using NLP Techniques

Checking the Truthfulness of News Channels using NLP Techniq...

2023 International Conference on the Confluence of Advancements in Robotics, Vision and Interdisciplinary Technology Management, IC-RVITM 2023

作者： Vipin, C. Harshit, S. Sailesh Kumar, K.L. Vijay, K. Zaid, Mohamed Vellore Institute of Technology Department of Computer Science and Engineering Vellore India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350306088

data analytics are difficult with unstructured data since it lacks pre-formatting, which makes up a large amount of information on social media. Research has looked into the potential of machine learning and natural language processing to interpret unstructured data and uncover significant information that could have gone unnoticed. We classify social media users using segmentation approaches on the basis of population, relationship status, and other criteria, allowing for the recognition of prominent people within particular categories. Behavior analysis assigns distinct roles to social media participants, such as users, recommenders, prospective users, and detractors, facilitating the tailoring of messages and reactions to address their concerns effectively. The study involves the accumulation of data from three news channels, data cleaning, and exploratory data analysis (EDA) to unearth patterns. Sentiment analysis is performed, and its results are compared for each of the news channels. Topic modeling is used to reveal different themes in the data. This study offers a solid basis for sentiment analysis and visualization, providing insightful information on the sentiment levels across various source kinds and features. It holds the potential to empower government agencies and businesses in harnessing the power of social media analytics for informed decision-making and improved communication strategies. © 2023 ieee.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Reliability analysis of a Low-Cost CCSDS 123 Hyperspectral Image Compressor 37

Reliability Analysis of a Low-Cost CCSDS 123 Hyperspectral I...

引用

37th ieee International symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2024

作者： Grignani, Wesley Santos, Douglas A. Dilillo, Luigi Melo, Douglas R. University of Vale Do Itajaí Leds Itajaí Brazil University of Montpellier Cnrs Ies Montpellier France

ISBN: (纸本)9798350366884

Remote sensing techniques in space applications use images that provide a large volume of information to collect data about the Earth. Hyperspectral images (HSIs) present a high volume of data and affect restrictions on the storage capacity and processing in space systems, highlighting the demand for compression. Systems that operate in space are susceptible to faults due to adverse conditions and require the implementation of protection techniques to mitigate these faults and ensure correct operation. This work implements a fault-tolerant CCSDS 123 HSI compressor using Triple Modular Redundancy (TMR) and Hamming Error Correcting Code (ECC) techniques to protect from Single Event Upsets (SEUs). We present the compressor in a standard version, followed by partially-protected and fully-protected versions, by applying hardening in different circuit components. We performed a reliability analysis through a fault injection campaign considering all implementations. The standard version showed 97.9% of executions with errors, which was reduced in the versions partially hardened, reaching no error propagation in the fully hardened version. In addition, all implementations accelerated the application, achieving a performance increase of up to 24×compared to the software solution. © 2024 ieee.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Information-Theoretic Exploration of Multivariate Time-Varying Image databases

引用

COMPUTING IN SCIENCE & ENGINEERING 2022年第3期24卷 61-70页

作者： Tasnim, Humayra Dutta, Soumya Turton, Terece L. Rogers, David H. Moses, Melanie E. Univ New Mexico Albuquerque NM 87131 USA Los Alamos Natl Lab Los Alamos NM 87545 USA

Modern scientific simulations produce very large datasets, making interactive exploration of such data computationally prohibitive. An increasingly common data reduction technique is to store visualizations and other data extracts in a database. The Cinema project is one such approach, storing visualizations in an image database for post hoc exploration and interactive image-based analysis. This work focuses on developing efficient algorithms that can quantify various types of multivariate dependencies existing within multivariable datasets. It applies specific mutual information measures for the quantification of salient regions from multivariate image data. Using such information measures, the opacity of the images is modulated so that the salient regions are automatically highlighted and the domain scientists can interactively explore the most relevant regions for scientific discovery.

关键词： Mutual information databases Motion pictures data visualization data models Three-dimensional displays Image databases

来源：评论

学校读者我要写书评

暂无评论

Unravelling the Human Perspective and Considerations for Urban data visualization 14

Unravelling the Human Perspective and Considerations for Urb...

引用

14th ieee Pacific visualization symposium (ieee PacificVis)

作者： Goodwin, Sarah Meier, Sebastian Bartram, Lyn Godwin, Alex Nagel, Till Doerk, Marian Monash Univ Clayton Vic Australia HafenCity Univ Hamburg Germany Simon Fraser Univ Burnaby BC Canada Amer Univ Washington DC 20016 USA Mannheim Univ Appl Sci Mannheim Germany Potsdam Univ Appl Sci Potsdam Germany

ISBN: (纸本)9781665439312

Effective use of data is an essential asset to modern cities. visualization as a tool for analysis, exploration, and communication has become a driving force in the task of unravelling our complex urban fabrics. This paper outlines the findings from a series of three workshops from 2018-2020 bringing together experts in urban data visualization with the aim of exploring multidisciplinary perspectives from the human-centric lens. Based on the rich and detailed workshop discussions identifying challenges and opportunities for urban data visualization research, we outline major human-centric themes and considerations fundamental for CityVis design and introduce a framework for an urban visualization design space.

关键词： Human-centered computing Interaction design Interaction design process and methods Human-centered computing visualization visualization design and evaluation methods

来源：评论

学校读者我要写书评

暂无评论

High-Performance visualization for Ocean Modeling

High-Performance Visualization for Ocean Modeling

引用

OCEANS Hampton Roads Conference

作者： Ali, Wael H. Gao, Youran Foucart, Corbin Doshi, Manan Mirabito, Chris Haley, Patrick J. Lermusiaux, Pierre F. J. MIT Dept Mech Engn Cambridge MA 02139 USA MIT Dept Earth Atmospher & Planetary Sci Cambridge MA USA

ISBN: (数字)9781665468091

ISBN: (纸本)9781665468091

Real-time sea experiments often involve large computational costs and software development associated with running numerical ocean simulations. Effective visualization tools that interpret the results of these simulations are therefore a necessity, and must overcome the challenges of plotting large, high-resolution, three-dimensional, time-dependent, and probabilistic ocean fields and associated quantities in real-time. Although disparate visualization tools aimed at ocean forecasting exist, a complete, integrated visualization suite that is efficient, interactive, and has 3D capabilities is still needed. In this work, we present the MSEAS high-performance visualization suite for real-time sea experiments. It processes multidisciplinary oceanographic fields in a computationally efficient manner and creates easy-to-use, portable, and interactive visualizations. The suite includes static visualization tools based on NCAR Graphics and MATLAB;the interactive web-based tool 2DSeaVizKit built using leaflet and *** for interactive 2D visualization on the world map;and 3DSeaVizKit, a browser-based, interactive 3D visualization tool built using Plotly and WebGL for exploratory 3D analysis of ocean forecasts. It can provide standard 2D cross-sections for scalar-valued data;quiver plots, pathlines, and streamtubes for vector-valued data;Lagrangian products (such as trajectories, Lagrangian Coherent Structures, etc.);isosurfaces for 3D data;and an interactive graphical user interface for selecting the quantities, times, and sub-domains of interest. We showcase applications of the visualization suite during three recent exercises that took place in the Gulf of Mexico, the Clarion-Clipperton Fracture Zone in the Pacific Ocean, and the Balearic sea.

关键词： Ocean modeling ocean visualization interactive visualization spatiotemporal data three-dimensional probabilistic forecasting real-time data assimilation

来源：评论

学校读者我要写书评

暂无评论

data analysis Tools Affect Outcomes of Eye-Tracking Studies 24

Data Analysis Tools Affect Outcomes of Eye-Tracking Studies

引用

18th ACM/ieee International symposium on Empirical Software Engineering and Measurement, ESEM 2024

作者： Dörzapf, Timon Peitek, Norman Wyrich, Marvin Apel, Sven Saarland University Saarland Informatics Campus Germany

ISBN: (纸本)9798400710476

Background: Eye-tracking studies in software engineering offer insights into the thought processes of developers and their interaction with visual information. However, the analysis of eye-tracking data lacks established standards. Particularly concerning for the comparability of study findings is the large variety of tools for evaluating eye-tracking data, all of which use different algorithms and preset parameters, often undisclosed. Aims: Our study has three objectives: (1) characterizing the analysis tool landscape for eye-tracking data within software-engineering research;(2) analyzing justifications by study authors for their choice of a particular analysis tool;and (3) investigating whether the choice of the analysis tool affects study results and conclusions. Method: First, we conducted a systematic mapping study to identify reports of eye-tracking studies in software engineering, from which we extracted analysis tools used and authors' justifications. Second, we reproduced the statistical analyses on three publicly available eye-tracking data sets from the original studies using two different analysis tools. Results: We found that the most frequently used analysis tools are Tobii Software, iTrace, and Ogama, although around a third of the papers did not mention the used analysis tool at all. The choice of analysis tool is also rarely justified. Most importantly, our case studies revealed that the choice of analysis tool significantly affects study results. Conclusions: The lack of standardization in analyzing eye-tracking data poses a significant threat to the comparability and reproducibility of eye-tracking studies in software engineering. Greater importance should be attached to this aspect in existing reporting guidelines for eye-tracking studies. © 2024 Owner/Author.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

High-quality Approximation of Scientific data using 3D Gaussian Splatting

High-quality Approximation of Scientific Data using 3D Gauss...

引用

ieee symposium on large data analysis and visualization (LDAV)

作者： Andres Sewell Landon Dyken Victor A. Mateevitsi Will Usher Jefferson Amstutz Thomas Marrinan Khairi Reda Silvio Rizzi Joseph A. lnsley Michael E. Papka Sidharth Kumar Steve Petruzza Utah State university Argonne National Laboratory Universtty of Illinois Chicago Luminary Cloud NVIDIA University of St. Thomas lndiana University Indianapolis Northern Illinois University

ISBN: (数字)9798331516925

ISBN: (纸本)9798331516932

This work explores the application of recent advancements in radi-ance field rendering, specifically 3D Gaussian splatting, to generate high-quality approximations of scientific data. In this technique, a 3D Gaussian splatting model is built from a 3D point cloud gen-erated using structure-from-motion, or a randomly initialized one when using a NeRF as input. This point cloud serves as the basis for initializing a set of Gaussian primitives, which are then refined through machine learning to minimize differences between ground truth and rendered images. We modified this pipeline to train Gaus-sian models directly from scientific data, eliminating the need for structure-from-motion. We test exporting an isosurface as a point cloud, which is then used to train a Gaussian model representing the dataset's isosurface. We also experimented with using a cinema database to produce a 3D Gaussian model; however, this approach yielded less promising results due to sub-optimal point cloud ini-tialization. Our findings highlight the potential of this technique for scientific datasets, suggesting it could enable efficient post-hoc visualization with reduced computational resources.

关键词： Point cloud compression Solid modeling Technological innovation Three-dimensional displays Pipelines Rendering (computer graphics) data models Real-time systems Image reconstruction Isosurfaces

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning for Quality Risk Factor analysis of Electronic Assemblies 24

Application of Machine Learning for Quality Risk Factor Anal...

引用

24th International symposium on Quality Electronic Design (ISQED)

作者： Reidy, Brendan Duggan, David Glasauer, Bernard Su, Peng Zand, Ramtin Univ South Carolina Dept Comp Sci & Engn Columbia SC 29208 USA Juniper Networks Component Engn Sunnyvale CA 94089 USA

ISBN: (纸本)9798350334753

The rapid identification of contributing factors to failures in a high-volume electronic product manufacturing environment is critical to reduce disruption to production and mitigate potential quality and reliability risks. As system complexity and component usage continues to increase, it is becoming more and more challenging to manually process the large volume of data that are continuously generated by production processes. In this paper, we utilize various machine learning (ML) techniques to classify components on the printed circuit board assemblies (PCBAs) as defective or non-defective based on an input feature map including features like the date the component is manufactured, the side of board on which the component is placed, the location of the component on the board, etc. We then implement a feature importance algorithm to detect the underlying cause of the component failure. Three ML models including support vector machine, random forest, and neural network are trained and implemented for feature importance analysis using a dataset obtained from over 10 million components on various PCBA boards. Due to the intrinsic characteristics of the dataset, such as a significant imbalance between defective and non-defective cases, pre-processing techniques such as upsampling and downsampling are necessary to increase the performance of the models. The results show that all the developed ML models can achieve more than 99% accuracy. Finally, we show that our proposed feature importance approach is capable of correctly identifying the main cause of defects for given components.

关键词： Component analysis neural network machine learning printed circuit board random forest support vector machine

来源：评论

学校读者我要写书评

暂无评论

Optimizing Autonomous Vehicle Sensor Setups: A Framework for Coverage analysis

Optimizing Autonomous Vehicle Sensor Setups: A Framework for...

引用

2023 ieee symposium Sensor data Fusion and International Conference on Multisensor Fusion and Integration, SDF-MFI 2023

作者： Hafemann, Philipp Hahn, Simon Enrico Lienkamp, Markus Technical University of Munich Germany Munich Germany

ISBN: (纸本)9798350382587

The performance of environment perception in autonomous vehicles is significantly influenced by the sensor setup, which is determined in the early design phase. The selection of the type and position of sensors in this phase often occurs before the availability of data processing algorithms. Therefore, the evaluation of the sensor setup can only be based on coverage metrics. This paper presents a novel framework for modeling the sensor coverage of autonomous vehicles. By discretizing the environment into grid cells, our framework analyzes each sensor and the whole setup. Our methodology systematically determines the coverage, identifies redundancy and blind spot areas, and obtains quantifiable metrics for evaluating the sensor setup efficiency. Utilizing the PyVista visualization library, we present the individual building blocks of the framework and their open-source implementation. The results from a real-world case study demonstrate our framework's ability to identify weaknesses in sensor setup coverage. Our approach helps to develop a comprehensive understanding of the sensor coverage and, therefore, contributes to designing more effective and reliable sensing systems. © 2023 ieee.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning-Based Synthetic Face Detection 23

CYBORG: Blending Human Saliency Into the Loss Improves Deep ...

引用

23rd ieee/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Boyd, Aidan Tinsley, Patrick Bowyer, Kevin Czajka, Adam Univ Notre Dame Notre Dame IN 46556 USA

ISBN: (纸本)9781665493468

Can deep learning models achieve greater generalization if their training is guided by reference to human perceptual abilities? And how can we implement this in a practical manner? This paper proposes a training strategy to ConveY Brain Oversight to Raise Generalization (CYBORG). This new approach incorporates human-annotated saliency maps into a loss function that guides the model's learning to focus on image regions that humans deem salient for the task. The Class Activation Mapping (CAM) mechanism is used to probe the model's current saliency in each training batch, juxtapose this model saliency with human saliency, and penalize large differences. Results on the task of synthetic face detection, selected to illustrate the effectiveness of the approach, show that CYBORG leads to significant improvement in accuracy on unseen samples consisting of face images generated from six Generative Adversarial Networks across multiple classification network architectures. We also show that scaling to even seven times the training data, or using non-human-saliency auxiliary information, such as segmentation masks, and standard loss cannot beat the performance of CYBORG-trained models. As a side effect of this work, we observe that the addition of explicit region annotation to the task of synthetic face detection increased human classification accuracy. This work opens a new area of research on how to incorporate human visual saliency into loss functions in practice. All data, code and trained models used in this work are offered with this paper.

关键词： Training visualization Training data Brain modeling data models Face detection Task analysis

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：