检索结果-内蒙古大学图书馆

ieee symposium on Visual Languages and Human Centric Computing (VL/HCC)

作者： Karl Smeltzer Oregon State University

Improvements in computer technology have spawned an exponential growth in both the scope and volume of data collection, as well as a corresponding shortage of capable analysts. This applies not just to scientists, but also to consumers who are gaining unprecedented access to data from their cars, homes, phones, and other devices. Meanwhile, visualization has emerged as an effective tool for exploring and gathering insight from large quantities of data. However, constructing effective visualizations is often difficult, and current tools often lack either the flexibility to extend to custom problem domains or else require low-level graphics programming expertise to generate even simple visualizations. Furthermore, most solutions are ad hoc, preventing users from transforming and evolving visualizations, instead forcing them into a rigid, linear workflow. One possible approach to solving these problems is through the definition of a domain-specific language (DSL). This approach offers a number of potential advantages, the most immediate being flexibility. A visualization DSL could support multiple levels of abstraction at once, each of which could be targeted at different user needs and expertise levels. This, in turn, could allow users with varying levels of expertise to make use of the abstraction layers they find most appropriate, and support the creation of simple and common visualizations without sacrificing the option for more detailed control when necessary. This layering could also allow implementation details to be hidden when desired. Pixel position information, for example, could be hidden behind a scalable and unitless environment which would allow the user to place and size visualization components in relation to one another.

关键词： data visualization DSL visualization data analysis Programming Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Visualizing Hidden Themes of Taxi Movement with Semantic Transformation

Visualizing Hidden Themes of Taxi Movement with Semantic Tra...

引用

Pacific (formerly Asia-Pacific APVIS) visualization symposium

作者： Ding Chu David A. Sheets Ye Zhao Yingyu Wu Jing Yang Maogong Zheng George Chen Kent State University UNC Charlotte Shenzhen Institute of Advanced Technologies

A new methodology is developed to discover and analyze the hidden knowledge of massive taxi trajectory data within a city. This approach creatively transforms the geographic coordinates (i.e. latitude and longitude) to street names reflecting contextual semantic information. Consequently, the movement of each taxi is studied as a document consisting of the taxi traversed street names, which enables semantic analysis of massive taxi data sets as document corpora. Hidden themes, namely taxi topics, are identified through textual topic modeling techniques. The taxi topics reflect urban mobility patterns and trends, which are displayed and analyzed through a visual analytics system. The system integrates interactive visualization tools, including taxi topic maps, topic routes, street clouds and parallel coordinates, to visualize the probability-based topical information. Urban planners, administration, travelers, and drivers can conduct their various knowledge discovery tasks with direct semantic and visual assists. The effectiveness of this approach is illustrated by case studies using a large taxi trajectory data set acquired from 21, 360 taxis in a city.

关键词： Trajectory Cities and towns Semantics Global Positioning System visualization data visualization Roads

来源：评论

学校读者我要写书评

暂无评论

2-3-4 Combination for parallel Compression on the K Computer

2-3-4 Combination for Parallel Compression on the K Computer

引用

Pacific (formerly Asia-Pacific APVIS) visualization symposium

作者： Chongke Bi Kenji Ono RIKEN

The development of supercomputers has successfully helped us to carry on complicated simulation with exploded size of dataset. For visualizing such kind of large-scale dataset, reducing the data size by using compression methods is one of the most useful approach. Moreover, parallelization of compression algorithm can greatly improve the efficiency and resolve the limitation of memory size. However, in parallel compression algorithm, interprocessor communication is indispensable, while it is also a bottleneck problem, especially for the general cases that the number of processors is not power-of-two. parallel POD (proper orthogonal decomposition) compression algorithm is such an example, the number of time steps must be power-of-two for the binary swap scheme. A method that can fully resolve this problem with low computational cost will be very popular. In this paper, we proposed such an approach called 2-3-4 combination approach, which can be simply implemented and also reach high performance of parallel computing algorithms. Furthermore, our method can obtain the best balance among all parallel computing processors. This is achieved by transferring the non-power-of-two problem into power-of-two problem to fully use the best balance feature of binary swap method. We evaluate our approach through applying it to the parallel POD compression algorithm on the K computer.

关键词： Program processors Computers Vectors Compression algorithms parallel processing Binary trees Computational modeling

来源：评论

学校读者我要写书评

暂无评论

High-Performance Zonal Histogramming on large-Scale Geospatial Rasters Using GPUs and GPU-Accelerated Clusters

High-Performance Zonal Histogramming on Large-Scale Geospati...

引用

ieee International symposium on parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Jianting Zhang Dali Wang Department of Computer Science The City College of New York New York NY USA

ISBN: (纸本)9781479941155

Hardware Accelerators are playing increasingly important roles in achieving desired performance from desktop to cluster computing. While General Purpose computing on graphics Processing Units (GPGPU) technologies have been widely applied to computing intensive applications, there is relatively little work on using GPUs and GPU-accelerated clusters for data intensive computing that typically involves significant irregular data accesses. In this study, we report our designs and implementations of a popular geospatial operation called Zonal Histogramming on Nvidia GPUs. Given a zonal dataset in the form of a collection of polygons and a geospatial raster that can be considered as a 2D grid, for each polygon, Zonal Histogramming computes a histogram of the values of raster cells that fall within the polygon. Our experiments on 3000+ US counties (polygons) over 20+ billion NASA Shuttle Radar Topography Mission (SRTM) 30 meter resolution Digital Elevation Model (DEM) raster cells have shown that, an impressive 46 seconds end-to-end runtime can be achieved using a single Nvidia GTX Titan GPU device. The runtime is further reduced to 10 seconds using 8 nodes on ORNL's Titan GPU-accelerated cluster. The desired high performance opens many possibilities for large-scale geospatial computing that is important for environmental and climate research.

关键词： Histograms Instruction sets graphics processing units Arrays Geospatial analysis Spatial resolution parallel processing

来源：评论

学校读者我要写书评

暂无评论

Omegalib: A multi-view application framework for hybrid reality display environments

Omegalib: A multi-view application framework for hybrid real...

引用

ieee Annual International symposium Virtual Reality

作者： Alessandro Febretti Arthur Nishimoto Victor Mateevitsi Luc Renambot Andrew Johnson Jason Leigh Electronic Visualization Laboratory University of Illinois Chicago

In the domain of large-scale visualization instruments, hybrid reality environments (HREs) are a recent innovation that combines the best-in-class capabilities of immersive environments, with the best-in-class capabilities of ultra-high-resolution display walls. HREs create a seamless 2D/3D environment that supports both information-rich analysis as well as virtual reality simulation exploration at a resolution matching human visual acuity. Co-located research groups in HREs tend to work on a variety of tasks during a research session (sometimes in parallel), and these tasks require 2D data views, 3D views, linking between them and the ability to bring in (or hide) data quickly as needed. In this paper we present Omegalib, a software framework that facilitates application development on HREs. Omegalib is designed to support dynamic reconfigurability of the display environment, so that areas of the display can be interactively allocated to 2D or 3D workspaces as needed. Compared to existing frameworks and toolkits, Omegalib makes it possible to have multiple immersive applications running on a cluster-controlled display system, have different input sources dynamically routed to applications, and have rendering results optionally redirected to a distributed compositing manager. Omegalib supports pluggable front-ends, to simplify the integration of third-party libraries like OpenGL, OpenSceneGraph, and the visualization Toolkit (VTK). We present examples of applications developed with Omegalib for the 74-megapixel, 72-tile CAVE2™ system, and show how a Hybrid Reality Environment proved effective in supporting work for a co-located research group in the environmental sciences.

关键词： Three-dimensional displays Runtime Rendering (computer graphics) Collaboration visualization Operating systems

来源：评论

学校读者我要写书评

暂无评论

Resource Centered Computing Delivering High parallel Performance

Resource Centered Computing Delivering High Parallel Perform...

引用

ieee International symposium on parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Jens Gustedt Stephane Vialle Patrick Mercier INRIA Nancy – Grand Est France AlGorille INRIA project team SUPELEC Metz France

ISBN: (纸本)9781479941155

Modern parallel programming requires a combination of different paradigms, expertise and tuning, that correspond to the different levels in today's hierarchical architectures. To cope with the inherent difficulty, ORWL (ordered read-write locks) presents a new paradigm and toolbox centered around local or remote resources, such as data, processors or accelerators. ORWL programmers describe their computation in terms of access to these resources during critical sections. Exclusive or shared access to the resources is granted through FIFOs and with read-write semantic. ORWL partially replaces a classical runtime and offers a new API for resource centric parallel programming. We successfully ran an ORWL benchmark application on different parallel architectures (a multicore CPU cluster, a NUMA machine, a CPU+GPU cluster). When processing large data we achieved scalability and performance similar to a reference code built on top of MPI+OpenMP+CUDA. The integration of optimized kernels of scientific computing libraries (ATLAS and cuBLAS) has been almost effortless, and we were able to increase performance using both CPU and GPU cores on our hybrid hierarchical cluster simultaneously. We aim to make ORWL a new easy-to-use and efficient programming model and toolbox for parallel developers.

关键词： Computational modeling graphics processing units Kernel Computer architecture parallel processing parallel programming

来源：评论

学校读者我要写书评

暂无评论

parallel APPROACH TO EXPEDITE MORPHOLOGICAL FEATURE EXTRACTION OF REMOTE SENSING IMAGES FOR CBIR SYSTEM

PARALLEL APPROACH TO EXPEDITE MORPHOLOGICAL FEATURE EXTRACTI...

引用

ieee International Geoscience and Remote Sensing symposium

作者： Sandeep Kumar Swati Jain Tanish Zaveri Computer Science and Engineering Department Nirma University Ahmedabad India Eletrical Engineering Department Nirma University Ahmedabad India

In this paper, we have proposed a parallel approach to the morphological feature extraction process and demonstrated a good computational speedup. Remote sensing images have a typical property of incrementing constantly and each image being very large. Since the images are acquired constantly and hence added into the database regularly in good numbers, hence there is a need to make the feature extraction work more efficient. Moreover morphological features are good texture descriptors and are extremely compute-intensive as well. It is hence attempted to utilize the power of multi-core architecture and expedite the process of feature extraction. These feature descriptors are tested on UC Merced Land Use Land Cover data set. Experimentation shows that with the use of parallel programming and architecture speed up of as good as 20X is obtained for CCH and RIT feature sets.

关键词： Feature extraction Remote sensing graphics processing units Merging Image retrieval Histograms

来源：评论

学校读者我要写书评

暂无评论

T-ReX: Interactive Global Illumination of Massive Models on Heterogeneous Computing Resources

引用

ieee TRANSACTIONS ON visualization AND COMPUTER graphics 2014年第3期20卷 481-494页

作者： Kim, Tae-Joon Sun, Xin Yoon, Sung-Eui Korea Adv Inst Sci & Technol Dept Comp Sci Taejon 305701 South Korea Microsoft Res Asia Beijing 100080 Peoples R China

We propose several interactive global illumination techniques for a diverse set of massive models. We integrate these techniques within a progressive rendering framework that aims to achieve both a high rendering throughput and an interactive responsiveness. To achieve a high rendering throughput, we utilize heterogeneous computing resources consisting of CPU and GPU. To reduce expensive data transmission costs between CPU and GPU, we propose to use separate, decoupled data representations dedicated for each CPU and GPU. Our representations consist of geometric and volumetric parts, provide different levels of resolutions, and support progressive global illumination for massive models. We also propose a novel, augmented volumetric representation that provides additional geometric resolutions within our volumetric representation. In addition, we employ tile-based rendering and propose a tile ordering technique considering visual perception. We have tested our approach with a diverse set of large-scale models including CAD, scanned, simulation models that consist of more than 300 million triangles. By using our methods, we are able to achieve ray processing performances of 3 M similar to 20 M rays per second, while limiting response time to users within 15 similar to 67 ms. We also allow dynamic modifications of light, and interactive setting of materials, while efficiently supporting novel view rendering.

关键词： Massive models ray tracing photon mapping global illumination heterogeneous parallel computing voxels compression

来源：评论

学校读者我要写书评

暂无评论

ieee symposium on large data Analysis and visualization 2013, LDAV 2013 - Proceedings

IEEE Symposium on Large Data Analysis and Visualization 2013...

引用

2013 3rd ieee symposium on large-Scale data Analysis and visualization, LDAV 2013

ISBN: (纸本)9781479916597

The proceedings contain 23 papers. The topics discussed include: distributed parallel particle advection using work requesting;a scalable algorithm for single-linkage hierarchical clustering on distributed-memory architectures;portable data-parallel visualization and analysis in distributed memory environments;efficient parallel volume rendering of large-scale adaptive mesh refinement data;visualizing large-scale atomistic simulations in ultra-resolution immersive environments;a provably-robust sampling method for generating colormaps of large data;trelliscope: a system for detailed visualization in the deep analysis of large complex data;filtering edge for exploration of large graphs;proper orthogonal decomposition based parallel compression for visualizing big data on the K Computer;and visual analysis on online display advertising data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed parallel particle advection using work requesting

Distributed parallel particle advection using work requestin...

引用

2013 3rd ieee symposium on large-Scale data Analysis and visualization, LDAV 2013

作者： Muller, Cornelius Camp, David Hentschel, Bernd Garth, Christoph University of Kaiserslautern Germany Lawrence Berkeley National Laboratory United States RWTH Aachen University Germany

ISBN: (纸本)9781479916597

Particle advection is an important vector field visualization technique that is difficult to apply to very large data sets in a distributed setting due to scalability limitations in existing algorithms. In this paper, we report on several experiments using work requesting dynamic scheduling which achieves balanced work distribution on arbitrary problems with minimal communication overhead. We present a corresponding prototype implementation, provide and analyze benchmark results, and compare our results to an existing algorithm. © 2013 ieee.

关键词： data visualization

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：