Advertisement

E-Nose System by Using Neural Networks

  • Sigeru OmatuEmail author
  • Mitsuaki Yano
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 290)

Abstract

This paper considers a new construction of an electronic nose system based on a neural network. The neural network used here is a competitive neural network by the learning vector quantization. Various odors are measured with an array of many metal oxide gas sensors. After reducing noises from the odor data which are measured under the different concentrations, we take the maximum values among the time series data of odors. They are affected by concentration levels, we use a normalization method to reduce the fluctuation of the data due to the concentration levels. Those data are used to classify the various odors of teas and coffees. The accuracy of the classification is around 96% in case of four kinds of teas and around 89% for five kinds of coffees.

Keywords

E-nose learning vector quantization metal oxide gas sensor odor classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Milke, J.A.: Application of Neural Networks for discriminating Fire Detectors. In: 10th International Conference on Automatic Fire Detection, AUBE 1995, Duisburg, Germany, pp. 213–222 (1995)Google Scholar
  2. 2.
    Charumporn, B., Yoshioka, M., Fujinaka, T., Omatu, S.: An E-nose System Using Back Propagation Neural Networks with a Centroid Training Data Set. In: Proc. Eighth International Symposium on Artificial Life and Robotics, Japan, pp. 605–608 (2003)Google Scholar
  3. 3.
    Fujinaka, T., Yoshioka, M., Omatu, S., Kosaka, T.: Intelligent Electronic Nose Systems for Fiore Detection Systems Based on Neural Netwoks. In: The Second International Conference on Advanced Engineering Computing and Applications in Sciences, Valencia, Spain, pp. 73–76 (2008)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Osaka Institute of TechnologyOsakaJapan

Personalised recommendations