Recognizing human activities from sensors using hidden Markov models constructed by feature selection techniquesReportar como inadecuado




Recognizing human activities from sensors using hidden Markov models constructed by feature selection techniques - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Publisher: MDPI Publishing

Issued date: 2009-02

Citation: Algorithms 2009, 21, p. 282-300

ISSN: 1999-4893

DOI: 10.3390-a2010282

Sponsor: This work was supported in part by Projects CICYT TIN2008-06742-C02-02-TSI, CICYT TEC2008-06732-C02-02-TEC, SINPROB and CAM MADRINET S-0505-TIC-0255.

Review: PeerReviewed

Publisher version: http:-dx.doi.org-10.3390-a2010282

Keywords: Computer Vision , Human Activity Recognition , Feature Selection , Hidden Markov Models

Abstract:In this paper a method for selecting features for Human Activity Recognition from sensors is presented. Using a large feature set that contains features that may describe the activities to recognize, Best First Search and Genetic Algorithms are employed to selIn this paper a method for selecting features for Human Activity Recognition from sensors is presented. Using a large feature set that contains features that may describe the activities to recognize, Best First Search and Genetic Algorithms are employed to select the feature subset that maximizes the accuracy of a Hidden Markov Model generated from the subset. A comparative of the proposed techniques is presented to demonstrate their performance building Hidden Markov Models to classify different human activities using video sensors.+-

Description:19 pages, 8 figures.- This article belongs to the Special Issue -Sensor Algorithms-.





Autor: Cilla, Rodrigo; Patricio Guisado, Miguel Ángel; García, Jesús; Berlanga, Antonio; Molina, José M.

Fuente: http://e-archivo.uc3m.es


Introducción



Universidad Carlos III de Madrid Repositorio institucional e-Archivo http:--e-archivo.uc3m.es Grupo de Inteligencia Artificial Aplicada (GIAA) DI - GIAA - Artículos de Revistas 2009-02 Recognizing human activities from sensors using hidden Markov models constructed by feature selection techniques Cilla, Rodrigo MDPI Publishing Algorithms 2009, 2(1), p.
282-300 http:--hdl.handle.net-10016-9315 Descargado de e-Archivo, repositorio institucional de la Universidad Carlos III de Madrid Algorithms 2009, 2, 282-300; doi:10.3390-a2010282 OPEN ACCESS algorithms ISSN 1999-4893 www.mdpi.com-journal-algorithms Article Recognizing Human Activities from Sensors Using Hidden Markov Models Constructed by Feature Selection Techniques Rodrigo Cilla ? , Miguel A.
Patricio, Jesús Garcı́a, Antonio Berlanga and Jose M.
Molina Computer Science Department, Universidad Carlos III de Madrid, Avda.
de la Universidad Carlos III, 22, Colmenarejo, Spain E-mails: mpatrici@inf.uc3m.es, jgherrer@inf.uc3m.es, aberlan@ia.uc3m.es, molina@ia.uc3m.es ? Author to whom correspondence should be addressed; E-mail: rcilla@inf.uc3m.es Received: 28 November 2008; in revised form: 2 February 2009 - Accepted: 16 February 2009 - Published: 21 February 2009 Abstract: In this paper a method for selecting features for Human Activity Recognition from sensors is presented.
Using a large feature set that contains features that may describe the activities to recognize, Best First Search and Genetic Algorithms are employed to select the feature subset that maximizes the accuracy of a Hidden Markov Model generated from the subset.
A comparative of the proposed techniques is presented to demonstrate their performance building Hidden Markov Models to classify different human activities using video sensors Keywords: Computer vision; Human Activity Recognition; Feature Selection; Hidden Markov Models 1. Introduction Sensors allow computers to perceive the world that surrounds them.
By the use of sensors, lik...





Documentos relacionados