Acceleration of a Feature Selection Algorithm Using High Performance Computing

Beceiro, Bieito; González-Domínguez, Jorge; Touriño, Juan

Use this link to cite:

http://hdl.handle.net/2183/26639

Acceleration of a Feature Selection Algorithm Using High Performance Computing

Files

B.Beceiro_2020_Acceleration_of_a_Feature_Selection_Algorithm.pdf (163.06 KB)

Identifiers

URI: http://hdl.handle.net/2183/26639

DOI: 10.3390/proceedings2020054054

Publication date

2020-09-01

Authors

Beceiro, Bieito

González-Domínguez, Jorge

Touriño, Juan

Bibliographic citation

Beceiro, B.; González-Domínguez, J.; Touriño, J. Acceleration of a Feature Selection Algorithm Using High Performance Computing. Proceedings 2020, 54, 54. https://doi.org/10.3390/proceedings2020054054

Abstract

[Abstract] Feature selection is a subfield of data analysis that is on reducing the dimensionality of datasets, so that subsequent analyses over them can be performed in affordable execution times while keeping the same results. Joint Mutual Information (JMI) is a highly used feature selection method that removes irrelevant and redundant characteristics. Nevertheless, it has high computational complexity. In this work, we present a multithreaded MPI parallel implementation of JMI to accelerate its execution on distributed memory systems, reaching speedups of up to 198.60 when running on 256 cores, and allowing for the analysis of very large datasets that do not fit in the main memory of a single node.