Memorias de investigación
Artículos en revistas:
Analysis of pattern recognition and dimensionality reduction techniques for odor biometrics
Año:2013
Áreas de investigación
  • Ingenierías
Datos
Descripción
In this paper, we analyze the performance of several well-known pattern recognition and dimensionality reduction techniques when applied to mass-spectrometry data for odor biometric identification. Motivated by the successful results of previous works capturing the odor from other parts of the body, this work attempts to evaluate the feasibility of identifying people by the odor emanated from the hands. By formulating this task according to a machine learning scheme, the problem is identified with a small-sample-size supervised classification problem in which the input data is formed by mass spectrograms from the hand odor of 13 subjects captured in different sessions. The high dimensionality of the data makes it necessary to apply feature selection and extraction techniques together with a simple classifier in order to improve the generalization capabilities of the model. Our experimental results achieve recognition rates over 85% which reveals that there exists discriminatory information in the hand odor and points at body odor as a promising biometric identifier.
Internacional
Si
JCR del ISI
Si
Título de la revista
KNOWLEDGE-BASED SYSTEMS
ISSN
0950-7051
Factor de impacto JCR
2,422
Información de impacto
Volumen
52
DOI
10.1016/j.knosys.2013.08.002
Número de revista
Desde la página
279
Hasta la página
289
Mes
SIN MES
Ranking
0
Esta actividad pertenece a memorias de investigación
Participantes
  • Autor: Irene Rodríguez Luján UPM
  • Autor: Gonzalo Bailador Pozo UPM
  • Autor: Maria del Carmen Sanchez Avila UPM
  • Autor: ana herrero
  • Autor: guillermo vidal-de-miguel
Grupos de investigación, Departamentos, Centros e Institutos de I+D+i relacionados
  • Creador: Centro o Instituto I+D+i: Centro de Domótica Integral, CEDINT
  • Departamento: Matemática Aplicada a las Tecnologías de la Información