Alexander KM Leung - Compression of Ultraviolet-visible Spectrum with Recurrent Neutral Network

Document created by Alexander KM Leung on Aug 22, 2014
Version 1Show Document
  • View in full screen mode

  Publication Details (including relevant citation   information):

  Chemometrics   and Intelligent Laboratory System, Vol.   52(2), 135-143 (2000)

  Abstract:

  Data compression method based on the recurrent neural network   (RNN) of the dynamical system approach was proposed and applied   to ultraviolet–visible (UV–VIS) spectra. RNN schemes with   different network size were studied and their performance was   evaluated by using both synthetic and experimental data. It was   found that the storage space of the spectral information under   study could be reduced significantly by using the proposed RNN   method with quality spectra regenerated from the compressed data.   Furthermore, the method was found to perform as good as the   wavelet transform (WT) in data compression and in some cases,   even better.

  Address (URL): http://dx.doi.org/10.1016/S0169-7439(00)00074-5

 

Attachments

    Outcomes