Discrimination of two-mixture fragrances odor using artificial odor recognition system with ensemble backpropagation neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The human sensory test is often used to obtain the sensory quantities of odors, however, the fluctuation of results due to the experts condition can cause discrepancies among panelists. We have developed an artificial odor recognition system using a quartz resonator sensor and backpropagation neural networks as the pattern recognition system in order to eliminate the disadvantage of human panelist system. The backpropagation neural networks shows high recognition rate for single component odor, however, become very low when it is used to discriminate mixture fragrances odor. In this paper we have proposed an ensemble of backpropagation neural networks as the pattern recognition system, and by using the ensemble learning mechanisms, the recognition rate is significantly increased, especially when using ensemble neural networks with five components.

Original languageEnglish
Title of host publicationSensors, Measurement and Intelligent Materials
Pages1514-1518
Number of pages5
DOIs
Publication statusPublished - 12 Mar 2013
Event2012 International Conference on Sensors, Measurement and Intelligent Materials, ICSMIM 2012 - Guilin, China
Duration: 26 Dec 201227 Dec 2012

Publication series

NameApplied Mechanics and Materials
Volume303-306
ISSN (Print)1660-9336
ISSN (Electronic)1662-7482

Conference

Conference2012 International Conference on Sensors, Measurement and Intelligent Materials, ICSMIM 2012
CountryChina
CityGuilin
Period26/12/1227/12/12

Keywords

  • Artificial odor recognition system
  • Backpropagation neural networks
  • Ensemble backpropagation
  • Mixture fragrances odors
  • Negative correlation learning algorithm

Fingerprint Dive into the research topics of 'Discrimination of two-mixture fragrances odor using artificial odor recognition system with ensemble backpropagation neural networks'. Together they form a unique fingerprint.

Cite this