Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Universidad EAFIT
2018
|
| Subjects: | |
| Online Access: | https://www.redalyc.org/articulo.oa?id=83556831004 https://www.redalyc.org/journal/835/83556831004/ https://www.redalyc.org/journal/835/83556831004/html/ https://www.redalyc.org/journal/835/83556831004/83556831004.epub https://www.redalyc.org/journal/835/83556831004/movil |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866587323058094080 |
|---|---|
| author | Ana-Lorena Uribe-Hurtado |
| author_facet | Ana-Lorena Uribe-Hurtado |
| contents | Leave-one-out Evaluation of the Nearest Feature Line and the Rectified Nearest Feature Line Segment Classifiers Using Multi-core Architectures Ana-Lorena Uribe-Hurtado Eduardo-José Villegas-Jaramillo Mauricio Orozco-Alzate Ingeniería one Multi leave out test core computing In this paper we present the parallelization of the leave-one-out test: a reproducible test that is, in general, computationally expensive. Paralelization was implemented on multi-core multi-threaded architectures, us- ing the Flynn Single Instruction Multiple Data taxonomy. This technique was used for the preprocessing and processing stages of two classification algorithms that are oriented to enrich the representation in small sample cases: the nearest feature line (NFL) algorithm and the rectified nearest feature line segment (RNFLS) algorithm. Results show an acceleration of up to 18.17 times with the smallest dataset and 29.91 times with the largest one, using the most costly algorithm (RNFLS) whose complexity is O(n 4). The paper also shows the pseudo-codes of the serial and parallel algorithms using, in the latter case, a notation that describes the way the parallelization was carried out as a function of the threads. 2018 artículo científico 1794-9165 https://www.redalyc.org/articulo.oa?id=83556831004 https://www.redalyc.org/journal/835/83556831004/ https://www.redalyc.org/journal/835/83556831004/html/ https://www.redalyc.org/journal/835/83556831004/83556831004.epub https://www.redalyc.org/journal/835/83556831004/movil 10.17230/ingciencia.14.27.4 en http://www.redalyc.org/revista.oa?id=835 Ingeniería y Ciencia application/pdf Universidad EAFIT Ingeniería y Ciencia (Colombia) Num.27 Vol.14 |
| format | Artículo científico |
| id | redalyc_83556831004 |
| language | en |
| publishDate | 2018 |
| publisher | Universidad EAFIT |
| spellingShingle | Leave-one-out Evaluation of the Nearest Feature Line and the Rectified Nearest Feature Line Segment Classifiers Using Multi-core Architectures Ana-Lorena Uribe-Hurtado Ingeniería one Multi leave out test core computing Leave-one-out Evaluation of the Nearest Feature Line and the Rectified Nearest Feature Line Segment Classifiers Using Multi-core Architectures Ana-Lorena Uribe-Hurtado Eduardo-José Villegas-Jaramillo Mauricio Orozco-Alzate Ingeniería one Multi leave out test core computing In this paper we present the parallelization of the leave-one-out test: a reproducible test that is, in general, computationally expensive. Paralelization was implemented on multi-core multi-threaded architectures, us- ing the Flynn Single Instruction Multiple Data taxonomy. This technique was used for the preprocessing and processing stages of two classification algorithms that are oriented to enrich the representation in small sample cases: the nearest feature line (NFL) algorithm and the rectified nearest feature line segment (RNFLS) algorithm. Results show an acceleration of up to 18.17 times with the smallest dataset and 29.91 times with the largest one, using the most costly algorithm (RNFLS) whose complexity is O(n 4). The paper also shows the pseudo-codes of the serial and parallel algorithms using, in the latter case, a notation that describes the way the parallelization was carried out as a function of the threads. 2018 artículo científico 1794-9165 https://www.redalyc.org/articulo.oa?id=83556831004 https://www.redalyc.org/journal/835/83556831004/ https://www.redalyc.org/journal/835/83556831004/html/ https://www.redalyc.org/journal/835/83556831004/83556831004.epub https://www.redalyc.org/journal/835/83556831004/movil 10.17230/ingciencia.14.27.4 en http://www.redalyc.org/revista.oa?id=835 Ingeniería y Ciencia application/pdf Universidad EAFIT Ingeniería y Ciencia (Colombia) Num.27 Vol.14 |
| title | Leave-one-out Evaluation of the Nearest Feature Line and the Rectified Nearest Feature Line Segment Classifiers Using Multi-core Architectures |
| topic | Ingeniería one Multi leave out test core computing |
| url | https://www.redalyc.org/articulo.oa?id=83556831004 https://www.redalyc.org/journal/835/83556831004/ https://www.redalyc.org/journal/835/83556831004/html/ https://www.redalyc.org/journal/835/83556831004/83556831004.epub https://www.redalyc.org/journal/835/83556831004/movil |