Pattern recognition via projection – based k – NN rules

Fil: Fraiman, Ricardo. Universidad de San Andrés. Departamento de Matemática y Ciencias; Argentina.

Guardado en:

Detalles Bibliográficos
Autores principales:	Fraiman, Ricardo, Justel, Ana, Svarc, Marcela
Formato:	Documento de Trabajo Documento de trabajo draft
Lenguaje:	Inglés
Publicado:	Universidad de San Andrés. Departamento de Matemáticas y Ciencias 2011
Materias:	Multivariate analysis Robust statistics Pattern perception
Acceso en línea:	http://hdl.handle.net/10908/553
Aporte de:	Repositorio Digital - Universidad de San Andrés (UdeSa) de Universidad de San Andrés

id	I37-R143-10908-553
record_format	dspace
spelling	I37-R143-10908-5532024-09-21T06:27:13Z Pattern recognition via projection – based k – NN rules Fraiman, Ricardo Justel, Ana Svarc, Marcela Multivariate analysis Robust statistics Pattern perception Fil: Fraiman, Ricardo. Universidad de San Andrés. Departamento de Matemática y Ciencias; Argentina. Fil: Justel, Ana. Universidad de San Andrés. Departamento de Matemática y Ciencias; Argentina. Fil: Svarc, Marcela. Universidad de San Andrés. Departamento de Matemática y Ciencias; Argentina. We introduce a new procedure for pattern recognition, based on the concepts of random projections and nearest neighbors. It can be thought as an improvement of the classical nearest neighbors classification rules. Besides the concept of neighbors we introduce the notion of district, a larger set which will be projected. Then we apply one dimensional k-NN methods to the projected data on randomly selected directions. In this way we are able to provide a method with some robustness properties and more accurate to handle high dimensional data. The procedure is also universally consistent. We challenge the method with the Isolet data where we obtain a very high classification score. 2011-09-19T13:48:44Z 2011-09-19T13:48:44Z 2008-06 Documento de Trabajo info:eu-repo/semantics/workingPaper info:ar-repo/semantics/documento de trabajo info:eu-repo/semantics/draft http://hdl.handle.net/10908/553 eng info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf application/pdf Universidad de San Andrés. Departamento de Matemáticas y Ciencias
institution	Universidad de San Andrés
institution_str	I-37
repository_str	R-143
collection	Repositorio Digital - Universidad de San Andrés (UdeSa)
language	Inglés
topic	Multivariate analysis Robust statistics Pattern perception
spellingShingle	Multivariate analysis Robust statistics Pattern perception Fraiman, Ricardo Justel, Ana Svarc, Marcela Pattern recognition via projection – based k – NN rules
topic_facet	Multivariate analysis Robust statistics Pattern perception
description	Fil: Fraiman, Ricardo. Universidad de San Andrés. Departamento de Matemática y Ciencias; Argentina.
format	Documento de Trabajo Documento de trabajo Documento de trabajo draft
author	Fraiman, Ricardo Justel, Ana Svarc, Marcela
author_facet	Fraiman, Ricardo Justel, Ana Svarc, Marcela
author_sort	Fraiman, Ricardo
title	Pattern recognition via projection – based k – NN rules
title_short	Pattern recognition via projection – based k – NN rules
title_full	Pattern recognition via projection – based k – NN rules
title_fullStr	Pattern recognition via projection – based k – NN rules
title_full_unstemmed	Pattern recognition via projection – based k – NN rules
title_sort	pattern recognition via projection – based k – nn rules
publisher	Universidad de San Andrés. Departamento de Matemáticas y Ciencias
publishDate	2011
url	http://hdl.handle.net/10908/553
work_keys_str_mv	AT fraimanricardo patternrecognitionviaprojectionbasedknnrules AT justelana patternrecognitionviaprojectionbasedknnrules AT svarcmarcela patternrecognitionviaprojectionbasedknnrules
_version_	1816376861558571008

Pattern recognition via projection – based k – NN rules

Ejemplares similares