Filters








76,250 Hits in 3.4 sec

DigitHist

Michael Shekelyan, Anton Dignös, Johann Gamper
2017 Proceedings of the VLDB Endowment  
By combining multi-dimensional and one-dimensional histograms along regular grids of different resolutions, DigitHist provides an accurate and reliable histogram approach for multi-dimensional data.  ...  We propose DigitHist, a histogram summary for selectivity estimation on multi-dimensional data with tight error bounds.  ...  histogram H and, for each dimension i, a one-dimensional marginal histogram M i . 2.  ... 
doi:10.14778/3137628.3137658 fatcat:grfijk44wfb2bmeqchhbiitzie

Page 266 of Behavior Research Methods Vol. 27, Issue 2 [page]

1995 Behavior Research Methods  
266 YU AND BEHRENS VARIATIONS IN GRAPHICS FOR VISUALIZATIONS One-Dimensional Graphs The histogram is perhaps the most common graphic for displaying the distribution of a single variable.  ...  Two-Dimensional Graphs Bivariate data are usually presented in a scatterplot, which is also subject to the bandwidth problem.  ... 

An information theoretic histogram for single dimensional selectivity estimation

Chris Giannella, Bassem Sayrafi
2005 Proceedings of the 2005 ACM symposium on Applied computing - SAC '05  
This conclusion demonstrates that the entropy histograms are an excellent choice of summary structure for selectivity estimation with respect to the state-of-the-art.  ...  The entropy histograms outperformed all other methods on 4 out of 9 real datasets and tied for first on another two.  ...  We demonstrate that these histograms represent an excellent choice of summary structure for selectivity estimation with respect to the stateof-the-art.  ... 
doi:10.1145/1066677.1066831 dblp:conf/sac/GiannellaS05 fatcat:wh73pjhoivb6xjsu6ol4pysema

An experimental evaluation of large scale GBDT systems

Fangeheng Fu, Jiawei Jiang, Yingxia Shao, Bin Cui
2019 Proceedings of the VLDB Endowment  
Our theoretical and experimental results provide a guideline on choosing a proper data management policy for a given workload.  ...  Based on the analysis, we further propose a novel distributed GBDT system named Vero, which adopts the unexplored composition of vertical partitioning and row-store and suits for many large-scale cases  ...  Except for histogram construction, there are two other phases in GBDT, which are split finding and node splitting.  ... 
doi:10.14778/3342263.3342273 fatcat:h3lo7wel25fp3niclkoi2mvrf4

Efficient Indexing of High Dimensional Normalized Histograms [chapter]

Alexandru Coman, Jörg Sander, Mario A. Nascimento
2003 Lecture Notes in Computer Science  
This paper addresses the problem of indexing high dimensional normalized histogram data, i.e., D-dimensional feature vectors H where D i=1 Hi = 1.  ...  We show that the performance of similarity queries for normalized histogram data can be significantly improved by exploiting such properties within a simple indexing framework.  ...  In fact, d L2 (p, q) ≤ √ 2, for any two normalized histograms p and qindependent of their dimensionality.  ... 
doi:10.1007/978-3-540-45227-0_59 fatcat:45y6kf3fw5cvvivjhlboaco3ju

Detection and Classification [chapter]

2005 Classification, Parameter Estimation and State Estimation  
We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We construct three separate 64 bin histograms for hue, saturation and value since it is not practical to construct a joint histogram.  ... 
doi:10.1002/0470090154.ch2 fatcat:zxo57xv24rdahlrcx4mnybgpqm

Detection and Classification [chapter]

2007 Applied Iterative Methods  
We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We construct three separate 64 bin histograms for hue, saturation and value since it is not practical to construct a joint histogram.  ... 
doi:10.1201/b10651-41 fatcat:hdyxxwzrezavvcluzqane5s54q

Detection and Classification [chapter]

2017 Classification, Parameter Estimation and State Estimation  
We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We construct three separate 64 bin histograms for hue, saturation and value since it is not practical to construct a joint histogram.  ... 
doi:10.1002/9781119152484.ch3 fatcat:ekf4yqfvafcatlh3uxddvq7qzi

13 - Detection and Classification

2005 IEEE/SP 13th Workshop on Statistical Signal Processing, 2005  
We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We construct three separate 64 bin histograms for hue, saturation and value since it is not practical to construct a joint histogram.  ... 
doi:10.1109/ssp.2005.1628662 fatcat:xfsju5l2pvf5pcmey4hv2zsv7u

Region Covariance: A Fast Descriptor for Detection and Classification [chapter]

Oncel Tuzel, Fatih Porikli, Peter Meer
2006 Lecture Notes in Computer Science  
We describe a fast method for computation of covariances based on integral images.  ...  We describe a new region descriptor and apply it to two problems, object detection and texture classification.  ...  We construct three separate 64 bin histograms for hue, saturation and value since it is not practical to construct a joint histogram.  ... 
doi:10.1007/11744047_45 fatcat:3erjiyb4rngndal7ih54cmspia

A compact space decomposition for effective metric indexing

Edgar Chávez, Gonzalo Navarro
2005 Pattern Recognition Letters  
In this aspect our structure is unbeaten. We finish with a discussion of the role of unbalancing in metric space searching, and how it permits trading memory space for construction time.  ...  In this context, an index is a data structure that speeds up proximity queries. However, indexes lose their efficiency as the intrinsic data dimensionality increases.  ...  Our first experiment tries to determine the best choice among (p1) − (p5). Figure 3 shows the results using two different choices for m * (12 and 100) and r * (1/4 and 1/8 of the maximum distance).  ... 
doi:10.1016/j.patrec.2004.11.014 fatcat:5ogwhgm62zcfxgksid2cet57au

Upsampling for Improved Multidimensional Attribute Space Clustering of Multifield Data

Vladimir Molchanov, Lars Linsen
2018 Information  
Without interpolation, the analysis was highly sensitive to the histogram cell sizes, yielding inaccurate clustering for improper choices: Large histogram cells result in no cluster separation, while clusters  ...  Thus, sufficiently high number of data points can be generated, overcoming the curse of dimensionality for this particular type of multidimensional data.  ...  The cluster tree constructed for this histogram has depth 9 and contains 19 nodes, see Figure 13e .  ... 
doi:10.3390/info9070156 fatcat:tullazdmi5gq3c3jna53st72ta

Simple estimation of absolute free energies for biomolecules

F. Marty Ytreberg, Daniel M. Zuckerman
2006 Journal of Chemical Physics  
We present a method for calculating the absolute free energy that employs a simple construction of an exactly computable reference system which possesses high overlap with the state of interest.  ...  for leucine dipeptide in implicit solvent.  ...  ACKNOWLEDGMENTS The authors would like to thank Edward Lyman, Ronald White, Srinath Cheluvarajah, and Hagai Meirovitch for many fruitful discussions.  ... 
doi:10.1063/1.2174008 pmid:16542066 fatcat:e4vytptkhbdu7lkztjffel7zee

Network analysis using entropy component analysis

Cheng Ye, Richard C Wilson, Edwin R Hancock
2017 Journal of Complex Networks  
Since our entropy is defined in terms of vertex degree values defining an edge, we can histogram the edge entropy using a multi-dimensional array for both undirected and directed networks.  ...  of high-dimensional data, as an alternative to classical PCA for component analysis.  ...  For undirected graphs the edges are specified by the single degree values for the two participating vertices, and the histogram array is two-dimensional.  ... 
doi:10.1093/comnet/cnx045 fatcat:sshd7wyzqfaozpzxrapcsaybfq

NNH: Improving Performance of Nearest-Neighbor Searches Using Histograms [chapter]

Liang Jin, Nick Koudas, Chen Li
2004 Lecture Notes in Computer Science  
Our intensive experiments show that nearest neighbor histograms can be efficiently constructed and maintained, and when used in conjunction with a variety of algorithms for NN search, they can improve  ...  In this paper we propose a novel technique, called NNH ("Nearest Neighbor Histograms"), which uses specific histogram structures to improve the performance of NN search algorithms.  ...  We provided a complete specification of such histogram structures, showing how to efficiently and accurately construct them, how to incrementally maintain them under dynamic updates, and how to utilize  ... 
doi:10.1007/978-3-540-24741-8_23 fatcat:z6xp34cccfbixm2nmeokhkxrmi
« Previous Showing results 1 — 15 out of 76,250 results