Independent component analysis for the identification of sources of variation on an industrial nirs application

Moya Gonzalez, Adolfo; Barreiro Elorza, Pilar; Jouan-Rimbaud Bouveresse, D. y Rutledge, Douglas N. (2011). Independent component analysis for the identification of sources of variation on an industrial nirs application. En: "Chimiométrie 2011", 01/12/2011 - 02/12/2011, Marsella, Francia. pp. 97-100.

Descripción

Título: Independent component analysis for the identification of sources of variation on an industrial nirs application
Autor/es:
  • Moya Gonzalez, Adolfo
  • Barreiro Elorza, Pilar
  • Jouan-Rimbaud Bouveresse, D.
  • Rutledge, Douglas N.
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: Chimiométrie 2011
Fechas del Evento: 01/12/2011 - 02/12/2011
Lugar del Evento: Marsella, Francia
Título del Libro: Proceedings of Chimiométrie 2011
Fecha: 2011
Materias:
Escuela: E.T.S.I. Agrónomos (UPM) [antigua denominación]
Departamento: Ingeniería Rural [hasta 2014]
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (514kB) | Vista Previa

Resumen

A Near Infrared Spectroscopy (NIRS) industrial application was developed by the LPF-Tagralia team, and transferred to a Spanish dehydrator company (Agrotécnica Extremeña S.L.) for the classification of dehydrator onion bulbs for breeding purposes. The automated operation of the system has allowed the classification of more than one million onion bulbs during seasons 2004 to 2008 (Table 1). The performance achieved by the original model (R2=0,65; SEC=2,28ºBrix) was enough for qualitative classification thanks to the broad range of variation of the initial population (18ºBrix). Nevertheless, a reduction of the classification performance of the model has been observed with the passing of seasons. One of the reasons put forward is the reduction of the range of variation that naturally occurs during a breeding process, the other is the variations in other parameters than the variable of interest but whose effects would probably be affecting the measurements [1]. This study points to the application of Independent Component Analysis (ICA) on this highly variable dataset coming from a NIRS industrial application for the identification of the different sources of variation present through seasons.

Más información

ID de Registro: 13405
Identificador DC: http://oa.upm.es/13405/
Identificador OAI: oai:oa.upm.es:13405
URL Oficial: http://www.chimiometrie.fr/chimiometrie2011/
Depositado por: Memoria Investigacion
Depositado el: 24 Oct 2012 08:26
Ultima Modificación: 21 Abr 2016 12:43
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM