About the work
The box-counting (BC) algorithm is one of the most popular methods for calculating the fractal dimension (FD) of binary data. FD analysis has many important applications in the biomedical field, such as cancer detection from 2D computer axial tomography images, Alzheimer's disease diagnosis from magnetic resonance 3D volumetric data, and consciousness states characterization based on 4D data extracted from electroencephalography (EEG) signals, among many others. Currently, these kind of applications use data whose size and amount can be very large, with high computation times needed to calculate the BC of the whole datasets. Fast Box-Counting software is a very efficient parallel implementation of the BC algorithm for its execution on Graphics Processing Units (GPU) using the CUDA technology. This software can process 2D, 3D, and 4D data and has been tested on several platforms with different hardware configurations. Fast Box-Counting can achieve speedups of up to 92.38x (2D), 57.27 (3D) and 75.73x (4D) with respect to the corresponding CPU single.thread implementations of the box-counting algorithm. Against an OpenMP multihread CPU implementation, Fast Box-Counting can achieve speedups of up to 16.12x (2D), 6.86x (3D) and 7.49x(4D). Compared to previous GPU implementation of the BC algorithm in 3D, Fast Box-Counting can achieve speedups of up to 4.79x.
Copyright info provided by
Universidad de Granada
Copyright registered declarations
Consolidated inscription:
Copyright infringement notifications:
0
Contact
Miguel Ángel Posadas Arráez
Consolidated inscription:
Copyright infringement notifications:
0
Contact
Notify irregularities in this registration
Print work information
Work information
Title Fast computation of fractal dimension for 2D, 3D and 4D data
The box-counting (BC) algorithm is one of the most popular methods for calculating the fractal dimension (FD) of binary data. FD analysis has many important applications in the biomedical field, such as cancer detection from 2D computer axial tomography images, Alzheimer's disease diagnosis from magnetic resonance 3D volumetric data, and consciousness states characterization based on 4D data extracted from electroencephalography (EEG) signals, among many others. Currently, these kind of applications use data whose size and amount can be very large, with high computation times needed to calculate the BC of the whole datasets. Fast Box-Counting software is a very efficient parallel implementation of the BC algorithm for its execution on Graphics Processing Units (GPU) using the CUDA technology. This software can process 2D, 3D, and 4D data and has been tested on several platforms with different hardware configurations. Fast Box-Counting can achieve speedups of up to 92.38x (2D), 57.27 (3D) and 75.73x (4D) with respect to the corresponding CPU single.thread implementations of the box-counting algorithm. Against an OpenMP multihread CPU implementation, Fast Box-Counting can achieve speedups of up to 16.12x (2D), 6.86x (3D) and 7.49x(4D). Compared to previous GPU implementation of the BC algorithm in 3D, Fast Box-Counting can achieve speedups of up to 4.79x.
Work type Software and Database designs
Tags cuda, gpu, fractal_dimension, box_counting
-------------------------
Registry info in Safe Creative
Identifier 2212222930906
Entry date Dec 22, 2022, 12:31 PM UTC
License Creative Commons Attribution-NonCommercial-NoDerivatives 4.0
Copyright info provided by Universidad de Granada,
-------------------------
Copyright registered declarations
Author 60.00 %. Holder Juan Ruiz de Miras. Date Dec 22, 2022.
Author 40.00 %. Holder Miguel Ángel Posadas Arráez. Date Dec 22, 2022.
-------------------------
Related registrations
Revised in: 2212232944450 - Fast Box-Counting
Information available at https://www.safecreative.org/work/2212222930906-fast-computation-of-fractal-dimension-for-2d-3d-and-4d-data
/
Registration: 2212222930906
