Classification of optical-sensor response cues with a Bi-dimensional wavelet-transform approach Conference Paper uri icon

abstract

  • In this work is used the two-dimensional discrete wavelet transform as a feature extractor of time responses from a porous silicon optical gas sensor for gas identification. The wavelet decomposition allows us to have a more in-deep sight of the sensor response. In addition, using a linear support vector machine (SVM) as classifier we evaluate our approach for a six-analyte discrimination problem. © 2011 American Institute of Physics.

publication date

  • 2011-01-01