COMMUNITY-CURATED DATA RESOURCES AND LARGE-SCALE DATA-MODEL SYNTHESES: THE CHILDREN OF COHMAP

2016 ◽  
Author(s):  
John W. Williams ◽  
◽  
Simon Goring ◽  
Eric Grimm ◽  
Jason McLachlan
Author(s):  
P. Baumann ◽  
V. Merticariu ◽  
A. Dumitru ◽  
D. Misev

With the unprecedented availability of continuously updated measured and generated data there is an immense potential for getting new and timely insights &ndash; yet, the value is not fully leveraged as of today. The quest is up for high-level service interfaces for dissecting datasets and rejoining them with other datasets &ndash; ultimately, to allow users to ask "any question, anytime, on any size" enabling them to "build their own product on the go". <br><br> With OGC Coverages, a concrete, interoperable data model has been established which unifies n-D spatio-temporal regular and irregular grids, point clouds, and meshes. The Web Coverage Service (WCS) suite provides versatile streamlined coverage functionality ranging from simple access to flexible spatio-temporal analytics. Flexibility and scalability of the WCS suite has been demonstrated in practice through massive services run by large-scale data centers. We present the current status in OGC Coverage data and service models, contrast them to related work, and describe a scalable implementation based on the rasdaman array engine.


Author(s):  
P. Baumann ◽  
V. Merticariu ◽  
A. Dumitru ◽  
D. Misev

With the unprecedented availability of continuously updated measured and generated data there is an immense potential for getting new and timely insights &ndash; yet, the value is not fully leveraged as of today. The quest is up for high-level service interfaces for dissecting datasets and rejoining them with other datasets &ndash; ultimately, to allow users to ask "any question, anytime, on any size" enabling them to "build their own product on the go". &lt;br&gt;&lt;br&gt; With OGC Coverages, a concrete, interoperable data model has been established which unifies n-D spatio-temporal regular and irregular grids, point clouds, and meshes. The Web Coverage Service (WCS) suite provides versatile streamlined coverage functionality ranging from simple access to flexible spatio-temporal analytics. Flexibility and scalability of the WCS suite has been demonstrated in practice through massive services run by large-scale data centers. We present the current status in OGC Coverage data and service models, contrast them to related work, and describe a scalable implementation based on the rasdaman array engine.


2009 ◽  
Vol 28 (11) ◽  
pp. 2737-2740
Author(s):  
Xiao ZHANG ◽  
Shan WANG ◽  
Na LIAN

2008 ◽  
Vol 9 (10) ◽  
pp. 1373-1381 ◽  
Author(s):  
Ding-yin Xia ◽  
Fei Wu ◽  
Xu-qing Zhang ◽  
Yue-ting Zhuang

2021 ◽  
Vol 77 (2) ◽  
pp. 98-108
Author(s):  
R. M. Churchill ◽  
C. S. Chang ◽  
J. Choi ◽  
J. Wong ◽  
S. Klasky ◽  
...  

Author(s):  
Krzysztof Jurczuk ◽  
Marcin Czajkowski ◽  
Marek Kretowski

AbstractThis paper concerns the evolutionary induction of decision trees (DT) for large-scale data. Such a global approach is one of the alternatives to the top-down inducers. It searches for the tree structure and tests simultaneously and thus gives improvements in the prediction and size of resulting classifiers in many situations. However, it is the population-based and iterative approach that can be too computationally demanding to apply for big data mining directly. The paper demonstrates that this barrier can be overcome by smart distributed/parallel processing. Moreover, we ask the question whether the global approach can truly compete with the greedy systems for large-scale data. For this purpose, we propose a novel multi-GPU approach. It incorporates the knowledge of global DT induction and evolutionary algorithm parallelization together with efficient utilization of memory and computing GPU’s resources. The searches for the tree structure and tests are performed simultaneously on a CPU, while the fitness calculations are delegated to GPUs. Data-parallel decomposition strategy and CUDA framework are applied. Experimental validation is performed on both artificial and real-life datasets. In both cases, the obtained acceleration is very satisfactory. The solution is able to process even billions of instances in a few hours on a single workstation equipped with 4 GPUs. The impact of data characteristics (size and dimension) on convergence and speedup of the evolutionary search is also shown. When the number of GPUs grows, nearly linear scalability is observed what suggests that data size boundaries for evolutionary DT mining are fading.


Sign in / Sign up

Export Citation Format

Share Document