The Community for Technology Leaders
Green Image
ABSTRACT
The volume of available data has been growing exponentially, increasing data problem's complexity and obscurity. In response, visual analytics (VA) has gained attention, yet its solutions haven't scaled well for big data. Computational methods can improve VA's scalability by giving users compact, meaningful information about the input data. However, the significant computation time these methods require hinders real-time interactive visualization of big data. By addressing crucial discrepancies between these methods and VA regarding precision and convergence, researchers have proposed ways to customize them for VA. These approaches, which include low-precision computation and iteration-level interactive visualization, ensure real-time interactive VA for big data.
INDEX TERMS
Visual analytics, Data visualization, Real-time systems, Principal component analysis, Clustering algorithms, Algorithm design and analysis,iteration-level visualization, Visual analytics, Data visualization, Convergence, Real-time systems, Principal component analysis, Clustering algorithms, Algorithm design and analysis, computer graphics, large-scale data, big data, visual analytics, dimension reduction, clustering, low-precision computation
CITATION
Jaegul Choo, Haesun Park, "Customizing Computational Methods for Visual Analytics with Big Data", IEEE Computer Graphics and Applications, vol. 33, no. , pp. 22-28, July-Aug. 2013, doi:10.1109/MCG.2013.39
616 ms
(Ver )