Analysis of source separation algorithms in industrial acoustic environments

This paper shows the results from the computation cost evaluation of three blind source separation algorithms. The algorithms tested were: FastICA, Adaptive Algorithm Based on Natural Gradient, and Adaptive EASI Based on Relative Gradient. The algorithms were chosen for their relative simplicity, an...

Descripción completa

Autores Principales: Lozano, Clevis, Gómez, Andrés, Chacón-Rodríguez, Alfonso, Merchán, Fernando, Julián, Pedro
Formato: Objeto de conferencia
Idioma: Inglés
Publicado: Institute of Electrical and Electronics Engineers Inc. 2017
Materias:
Acceso en línea: https://www.scopus.com/inward/record.url?eid=2-s2.0-84945156117&partnerID=40&md5=72998182186ff5845045de39e1c40ab7
https://hdl.handle.net/2238/6943
id RepoTEC6943
recordtype dspace
spelling RepoTEC69432022-04-09T03:05:37Z Analysis of source separation algorithms in industrial acoustic environments Lozano, Clevis Gómez, Andrés Chacón-Rodríguez, Alfonso Merchán, Fernando Julián, Pedro Algoritmos Hardware Research Subject Categories::TECHNOLOGY::Information technology::Computer science::Computer science This paper shows the results from the computation cost evaluation of three blind source separation algorithms. The algorithms tested were: FastICA, Adaptive Algorithm Based on Natural Gradient, and Adaptive EASI Based on Relative Gradient. The algorithms were chosen for their relative simplicity, and taking into account their hardware implementation feasibility, either on a FPGA or an ASIC, as part of a system for acoustic localization of mobile agents in industrial environments. 2017-04-05T17:34:55Z 2017-04-05T17:34:55Z 2015 info:eu-repo/semantics/conferenceObject https://www.scopus.com/inward/record.url?eid=2-s2.0-84945156117&partnerID=40&md5=72998182186ff5845045de39e1c40ab7 978-147998332-2 https://hdl.handle.net/2238/6943 eng Attribution-NonCommercial 3.0 Costa Rica https://creativecommons.org/licenses/by-nc/3.0/cr/ application/pdf Institute of Electrical and Electronics Engineers Inc. C. Lozano, A. Gómez, A. Chacón-Rodríguez, F. Merchán, & P. Julian. (2015). Analysis of source separation algorithms in industrial acoustic environments. Paper presented at the 2015 IEEE 6th Latin American Symposium on Circuits & Systems (LASCAS), 1-4. doi:10.1109/LASCAS.2015.7250482
institution Tecnológico de Costa Rica
collection Repositorio TEC
language Inglés
topic Algoritmos
Hardware
Research Subject Categories::TECHNOLOGY::Information technology::Computer science::Computer science
spellingShingle Algoritmos
Hardware
Research Subject Categories::TECHNOLOGY::Information technology::Computer science::Computer science
Lozano, Clevis
Gómez, Andrés
Chacón-Rodríguez, Alfonso
Merchán, Fernando
Julián, Pedro
Analysis of source separation algorithms in industrial acoustic environments
description This paper shows the results from the computation cost evaluation of three blind source separation algorithms. The algorithms tested were: FastICA, Adaptive Algorithm Based on Natural Gradient, and Adaptive EASI Based on Relative Gradient. The algorithms were chosen for their relative simplicity, and taking into account their hardware implementation feasibility, either on a FPGA or an ASIC, as part of a system for acoustic localization of mobile agents in industrial environments.
format Objeto de conferencia
author Lozano, Clevis
Gómez, Andrés
Chacón-Rodríguez, Alfonso
Merchán, Fernando
Julián, Pedro
author_sort Lozano, Clevis
title Analysis of source separation algorithms in industrial acoustic environments
title_short Analysis of source separation algorithms in industrial acoustic environments
title_full Analysis of source separation algorithms in industrial acoustic environments
title_fullStr Analysis of source separation algorithms in industrial acoustic environments
title_full_unstemmed Analysis of source separation algorithms in industrial acoustic environments
title_sort analysis of source separation algorithms in industrial acoustic environments
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2017
url https://www.scopus.com/inward/record.url?eid=2-s2.0-84945156117&partnerID=40&md5=72998182186ff5845045de39e1c40ab7
https://hdl.handle.net/2238/6943
_version_ 1796140535589634048
score 12.043273