GPU optimization of electroencephalogram analysis

Nowadays, with the advent of new non-invasive techniques of brain imaging, researchers have access to neural processes underlying the cognition in humans. One of the main challenges in this techniques is the detection of patterns in brain signals, generally very noisy and with artifacts inserted by...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Raimondo, Federico, Kamienkowski, Juan E., Fernández Slezak, Diego
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2011
Materias:	Ciencias Informáticas Electroencephalogram analysis GPU optimization
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/126113 https://40jaiio.sadio.org.ar/sites/default/files/T2011/HPC/693.pdf
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-126113
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Electroencephalogram analysis GPU optimization
spellingShingle	Ciencias Informáticas Electroencephalogram analysis GPU optimization Raimondo, Federico Kamienkowski, Juan E. Fernández Slezak, Diego GPU optimization of electroencephalogram analysis
topic_facet	Ciencias Informáticas Electroencephalogram analysis GPU optimization
description	Nowadays, with the advent of new non-invasive techniques of brain imaging, researchers have access to neural processes underlying the cognition in humans. One of the main challenges in this techniques is the detection of patterns in brain signals, generally very noisy and with artifacts inserted by vital signs. One of the most successful techniques for this is Independent Component Analysis which detects statistically independent components that are produced from different sources. These methods are very expensive in computational time, with many hours of processing for a single experiment. We analyzed this algorithm and detect two main types of operations: vector-matrix and matrix-matrix. We implemented an ad-hoc solution that executes on GPU and compared this with the original and CUBLAS versions. We obtained a 4x and 40x of performance increase of vector-matrix and matrix-matrix operations, respectively. These results are the first step towards real-time EEG processing which may produce a significant advance into BCI applications.
format	Objeto de conferencia Objeto de conferencia
author	Raimondo, Federico Kamienkowski, Juan E. Fernández Slezak, Diego
author_facet	Raimondo, Federico Kamienkowski, Juan E. Fernández Slezak, Diego
author_sort	Raimondo, Federico
title	GPU optimization of electroencephalogram analysis
title_short	GPU optimization of electroencephalogram analysis
title_full	GPU optimization of electroencephalogram analysis
title_fullStr	GPU optimization of electroencephalogram analysis
title_full_unstemmed	GPU optimization of electroencephalogram analysis
title_sort	gpu optimization of electroencephalogram analysis
publishDate	2011
url	http://sedici.unlp.edu.ar/handle/10915/126113 https://40jaiio.sadio.org.ar/sites/default/files/T2011/HPC/693.pdf
work_keys_str_mv	AT raimondofederico gpuoptimizationofelectroencephalogramanalysis AT kamienkowskijuane gpuoptimizationofelectroencephalogramanalysis AT fernandezslezakdiego gpuoptimizationofelectroencephalogramanalysis
bdutipo_str	Repositorios
_version_	1764820450113748992

GPU optimization of electroencephalogram analysis

Ejemplares similares