检索结果-内蒙古大学图书馆

Cognitive Aspects of Virtual Reality (CVR), IEEE International Conference on

作者： István Károly Boda Erzsébet Tóth László T. Nagy Department of Mathematics and Informatics Debrecen Reformed Theological University Debrecen Hungary Department of Data Science and Visualization University of Debrecen Debrecen Hungary

In our paper we introduce the IT technical language learning material focusing on the specialized use of the English language in the context of information technology (IT) and computing. This material has been developed in the framework of the 3D virtual library project started in 2013 as part of the Cognitive Infocommunications (CogInfoCom) research. The current version of the virtual library has a hypertext or 2D implementation which is freely available in the internet. The advanced 3D presentation of the material uses the 3D features of the MaxWhere Seminar System, arranging and displaying the content of the language learning material in the Fly Podium 3D space. First, we provide a short overview on the virtual library project as an introduction to the IT technical language learning material. In the next section we describe the background and aim of the development of the material, then we present in detail the organization and structure of the 2D and 3D implementation of the learning material. Some inventions and ideas may deserve attention such as the topic map of selected terms, concepts, and texts functioning as a navigational tool, the interactive tests (where the first one is for practice, and the second one is actually a memory game), and the mapping mechanism of the hypertext-based material into the 3D virtual space of the MaxWhere system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FUSegNet: A Deep Convolutional Neural Network for Foot Ulcer Segmentation

arXiv

引用

arXiv 2023年

作者： Dhar, Mrinal Kanti Zhang, Taiyu Patel, Yash Gopalakrishnan, Sandeep Yu, Zeyun Big Data Analytics and Visualization Laboratory Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI53201 United States

This paper presents FUSegNet, a new model for foot ulcer segmentation in diabetes patients, which uses the pretrained EfficientNet-b7 as a backbone to address the issue of limited training samples. A modified spatial and channel squeeze-and-excitation (scSE) module called parallel scSE or P-scSE is proposed that combines additive and max-out scSE. A new arrangement is introduced for the module by fusing it in the middle of each decoder stage. As the top decoder stage carries a limited number of feature maps, max-out scSE is bypassed there to form a shorted P-scSE. A set of augmentations, comprising geometric, morphological, and intensity-based augmentations, is applied before feeding the data into the network. The proposed model is first evaluated on a publicly available chronic wound dataset where it achieves a data-based dice score of 92.70%, which is the highest score among the reported approaches. The model outperforms other scSE-based UNet models in terms of Pratt's figure of merits (PFOM) scores in most categories, which evaluates the accuracy of edge localization. The model is then tested in the MICCAI 2021 FUSeg challenge, where a variation of FUSegNet called x-FUSegNet is submitted. The x-FUSegNet model, which takes the average of outputs obtained by FUSegNet using 5-fold cross-validation, achieves a dice score of 89.23%, placing it at the top of the FUSeg Challenge leaderboard. The source code for the model is available on GitHub. © 2023, CC BY-NC-SA.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Development of machine learning models for turbulent wall pressure fluctuations 55

Development of machine learning models for turbulent wall pr...

引用

55th AIAA Aerospace sciences Meeting

作者： Ling, J. Barone, Matthew Davis, Warren Chowdhary, K. Fike, Jeffrey Thermal/Fluids Science and Engineering Department Sandia National Labs LivermoreCA94450 United States Aerosciences Department Sandia National Labs LivermoreCA94450 United States Scalable Analysis and Visualization Department Sandia National Labs LivermoreCA94450 United States Extreme Scale Data Science and Analytics Department Sandia National Labs LivermoreCA94450 United States Thermal/Fluids Science and Engineering Department Sandia National Labs AlbuquerqueNM87123 United States Aerosciences Department Sandia National Labs AlbuquerqueNM87123 United States Scalable Analysis and Visualization Department Sandia National Labs AlbuquerqueNM87123 United States Extreme Scale Data Science and Analytics Department Sandia National Labs AlbuquerqueNM87123 United States

ISBN: (数字)9781624104473

ISBN: (纸本)9781624104473

In many aerospace applications, it is critical to be able to model fluid-structure interactions. In particular, correctly predicting the power spectral density of pressure fluctuations at surfaces can be important for assessing potential resonances and failure modes. Current turbulence modeling methods, such as wall-modeled Large Eddy Simulation and Detached Eddy Simulation, cannot reliably predict these pressure fluctuations for many applications of interest. The focus of this paper is on efforts to use data-driven machine learning methods to learn correction terms for the wall pressure fluctuation spectrum. In particular, the non-locality of the wall pressure fluctuations in a compressible boundary layer is investigated using random forests and neural networks trained and evaluated on Direct Numerical Simulation data. © 2017 by the American Institute of Aeronautics and Astronautics, Inc.

关键词： Machine Learning Power Spectral Density Direct Numerical Simulation Convolutional Neural Network Compressible Boundary Layer Fluid Structure Interaction Turbulence Models Reynolds Averaged Navier Stokes Free Stream Velocity Velocity Profiles

来源：评论

学校读者我要写书评

暂无评论

Utilizing Computer Vision for Beef Cattle Feeding Bunk Score Assessment with a Calan Gate Feeding System 11

Utilizing Computer Vision for Beef Cattle Feeding Bunk Score...

引用

11th European Conference on Precision Livestock Farming

作者： Mendes, Egleu D.M. Wooley, Jack Pi, Yalong Tao, Jian Tedeschi, Luis O. Department of Animal Science Texas A&M University College StationTX United States Institute of Data Science Texas A&M University College StationTX United States School of Performance Visualization & Fine Arts Texas A&M University College StationTX United States

ISBN: (纸本)9791221067361

Our study employed a novel methodology to assess the effectiveness of a CV model in classifying feed leftovers (orts) within a Calan Gate Feeding System. We used six bunk scores: S00 (no feed), S05 (scattered feed), S10 (thin layer), S20 (25-50%), S30 (> 50%), and S40 (untouched). With the use of three RGB (red green blue) cameras, we captured a dataset of 12 156 images, which were then segmented into training (70%), validation (15%), and testing (15%) sets. The analysis with ResNet revealed high initial model performance, with precision, recall, and F1 scores reaching 0.9989 and testing accuracy of 99.89%. However, when applied to an independent dataset of 7 905 images, the performance dropped, notably for precision (0.5868), recall (0.3982), and F1 score (0.3653). These discrepancies likely resulted from varying lighting conditions, the mismatch between typical open-feeding bunk classifications and the Calan Gate's closed design, and model overfit. To optimize the effectiveness of the feeding bunk scoring system, we suggest refining the classification into three tailored categories: C1) empty bunk (S00), C2) scattered or thin layer (S05 + S10), and C3) more than 25% to full (S20, S30, S40). This integration of CV into PLF can automate the feeding scores to estimate individual consumption accurately. Such advancements can improve resource utilization, optimize animal performance, and reduce operational costs, thereby contributing to cost-effective and sustainable production methods. This study underscores the necessity of continuous model training and adaptation, a crucial aspect that ensures reliable CV application in real-world settings and is of utmost importance in your research. © 2024 11th European Conference on Precision Livestock Farming. All rights reserved.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Scalable load balancing for massively parallel distributed Monte Carlo particle transport

Scalable load balancing for massively parallel distributed M...

引用

International Conference on Mathematics and Computational Methods Applied to Nuclear science and Engineering, M and C 2013

作者： O'Brien, Matthew J. Brantley, Patrick S. Joy, Kenneth I. Lawrence Livermore National Laboratory 7000 East Avenue Livermore CA 94550 United States Institute for Data Analysis and Visualization Computer Science Department University of California One Shields Avenue Davis CA 95616 United States

ISBN: (纸本)9781627486439

In order to run computer simulations efficiently on massively parallel computers with hundreds of thousands or millions of processors, care must be taken that the calculation is load balanced across the processors. Examining the workload of every processor leads to an unscalable algorithm, with run time at least as large as O(N), where N is the number of processors. We present a scalable load balancing algorithm, with run time 0(log(N)), that involves iterated processor-pair-wise balancing steps, ultimately leading to a globally balanced workload. We demonstrate scalability of the algorithm up to 2 million processors on the Sequoia supercomputer at Lawrence Livermore National Laboratory.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Compression and occlusion culling for fast isosurface extraction from massive datasets

Compression and occlusion culling for fast isosurface extrac...

引用

Workshop on Mathematical Foundations of Scientific visualization, Computer Graphics, and Massive data Exploration, 2004

作者： Gregorski, Benjamin Senecal, Joshua Duchaineau, Mark Joy, Kenneth I. Center for Applied Scientific Computing Lawrence Livermore National Laboratory 7000 East Avenue LivermoreCA94551 United States Institute for Data Analysis and Visualization Department of Computer Science University of California Davis One Shields Avenue DavisCA95616 United States

ISBN: (纸本)9783642543005

We present two algorithms for data compression and occlusion culling that improve interactive, adaptive isosurface extraction from large volume datasets. Our algorithm, based on hierarchical tetrahedral meshes defined by longest edge bisection, allows arbitrary isosurfaces to be adaptively extracted at interactive rates from losslessly compressed volumes where the region of interest, determined at runtime by user interaction, is decompressed on-the-fly. For interactive applications, we exploit frame-to-frame coherence between consecutive views to simplify the mesh structure in occluded regions and eliminate occluded triangles significantly reducing the complexity of the visualized surface and the underlying multiresolution volume representation. We extend the use of hardware accelerated occlusion queries to adaptive isosurface extraction applications where the surface geometry and topology change with the level-of-detail and view-point and the user can select an arbitrary isovalue for visualization. © 2009 Springer-Verlag Berlin Heidelberg.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Implicit Surface Modeling Suitable for Inside/Outside Tests with Radial Basis Functions

Implicit Surface Modeling Suitable for Inside/Outside Tests ...

引用

2007 10th IEEE International Conferences on Computer Aided Design and Computer Graphics(CAD/Graphics 2007)

作者： Vaclav Skala Centre of Computer Graphics and Data Visualization Department of Computer Science and EngineeringUniversity of West BohemiaPlzenCzech Republic30614

We describe a method for computing an implicit function that represents a surface by its zero level set,given a set of points scattered over the surface and associated with surface normal *** implicit function is defined as a linear combination of compactly supported radial basis *** method is suitable for testing whether a given point is interior or exterior to the surface,previously only associated with globally supported or globally regularized radial basis *** use a two-level interpolation *** the coarse scale interpolation,we set basis function centers by a grid that covers the enlarged bounding box of the given point set and compute their signed distances to the underlying surface using local quadratic approximations of the nearest surface *** a fitting to the residual errors on the surface points and additional off-surface points is performed with fine scale basis *** final function is the sum of the two intermediate functions and is a good approximation of the signed distance field to the surface in the bounding *** of surface reconstruction and set operations between shapes are provided.

关键词： Implicit Surface Modeling Suitable for Inside/Outside Tests with Radial Basis Functions

来源：评论

学校读者我要写书评

暂无评论

Quantitative visualization of ChIP-chip data by using linked views

Quantitative visualization of ChIP-chip data by using linked...

引用

IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)

作者： Min-Yu Huang Gunther H. Weber Xiao-Yong Li Mark D. Biggin Bernd Hamann Institute for Data Analysis and Visualization (IDAV) Department of Computer Science University of California슠Davis Davis CA USA Visualization Group Lawrence Berkeley National Laboratory Berkeley CA USA Genomics Divisions Lawrence Berkeley National Laboratory Berkeley CA USA Institute for Data Analysis and Visualization (IDAV) Department of Computer Science University of California Davis Davis CA USA

Most analyses of ChIP-chip in vivo DNA binding have focused on qualitative descriptions of whether genomic regions are bound or not. There is increasing evidence, however, that factors bind in a highly overlapping manner to the same genomic regions and that it is quantitative differences in occupancy on these commonly bound regions that are the critical determinants of the different biological specificity of factors. As a result, it is critical to have a tool to facilitate the quantitative visualization of differences between transcription factors and the genomic regions they bind to understand each factor's unique roles in the network. We have developed a framework which combines several visualizations via brushing-and-linking to allow the user to interactively analyze and explore in vivo DNA binding data of multiple transcription factors. We describe these visualization types and also provide a discussion of biological examples in this paper.

关键词： Correlation Bioinformatics data visualization Genomics Image color analysis Browsers

来源：评论

学校读者我要写书评

暂无评论

419 Automated individual animal identification and feeding bunk scoring: a computer vision approach for beef cattle at Calan gate feeding system

引用

Journal of Animal science 2024年第SUPPLEMENT_3期102卷 2-3页

作者： Mendes, Egleu D M Wooley, Jack Pi, Yalong Tao, Jian Tedeschi, Luis O Department of Animal Science Texas A&M University Institute of Data Science Texas A&M University School of Performance Visualization & Fine Arts Texas A&M University

Recent developments in computer vision (CV) technology have significantly improved the management of beef cattle feeding systems by enabling precise monitoring and adjustment of feed intake based on individual needs. This study introduces an automated approach for identifying cattle at feeding bunks using CV and evaluates the effectiveness of a feeding bunk scoring system to optimize cattle feeding strategies. Utilizing a high-definition video capture setup, our research focused on the feeding behaviors of 6 heifers in one pen with the Calan Feeding System (American Calan, Northwood, NH). We deployed three Reolink PoE cameras (Model D400) strategically positioned above the feeding bunks, each overseeing two feeding bunks, to monitor feeding activity comprehensively. The cameras were set to record in Full HD (1920 x 1080 pixels) at 30 frames per second. We processed the frames using Python’s OpenCV, resulting in 600 images that composed an array with dimensions 600 x 400x450 (pixels) x 3 (RGB). These images served as the basis for our analysis, which involved feature extraction via a ResNet-50 convolutional neural network, followed by dimensionality reduction through Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (t-SNE). Our methodology included the use of k-means clustering to detect the presence of cattle at the bunk, achieving an Adjusted Rand Index (ARI) of 0.9933. We applied the DBSCAN clustering algorithm in the ‘cattle present’ images for individual animal identification, obtaining an ARI of 0.9174, indicating high model accuracy. To assess feeding efficiency, we analyzed 12,156 images of feeding bunks obtained using the same Python’s OpenCV approach and then classified them into six categories based on Lundy et al., 2015: S00 (no feed), S05 (scattered feed), S10 (thin layer), S20 (25 to 50%), S30 (>50%), and S40 (untouched). Using a training, validation, and testing split of 70%, 15%, and 15%, respectively, our model demon

关键词：

来源：评论

学校读者我要写书评

暂无评论

Error-Based and Entropy-Based Discretization of Continuous Features 2

Error-Based and Entropy-Based Discretization of Continuous F...

引用

2nd International Conference on Knowledge Discovery and data Mining, KDD 1996

作者： Kohavi, Ron Sahami, Mehran Data Mining and Visualization Silicon GraphicsInc 2011 N. Shoreline Blvd Mountain ViewCA94043-1389 United States Computer Science Department Stanford University Gates Building 1A Room 126 StanfordCA94305-9010 United States

ISBN: (纸本)1577350049

We present a comparison of error-based and entropybased methods for discretization of continuous features. Our study includes both an extensive empirical comparison as well as an analysis of scenarios where error minimization may be an inappropriate discretization criterion. We present a discretization method based on the C4.5 decision tree algorithm and compare it to an existing entropy-based discretization algorithm, which employs the Minimum Description Length Principle, and a recently proposed error-based technique. We evaluate these discretization methods with respect to C4.5 and Naive-Bayesian classifiers on datasets from the UC1 repository and analyze the computational complexity of each method. Our results indicate that the entropy-based MDL heuristic outperforms error minimization on average. We then analyze the shortcomings of error-based approaches in comparison to entropy-based methods. © 1996 AAAI (***). All Rights Reserved.

关键词： Errors

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：