In the last column, we showed how we could perform Fourier transformation (FT) of a near-infrared (NIR) spectrum in a few lines of matrix algebra and said that in this column we would use it in a novel way. The task we are going to perform is that of changing scales of spectroscopic (NIR) data. This may be novel, we are not aware that anyone else does it this way, but of course instrument manufacturers sometimes like to be silent about the methods they employ.
Tony Davies Columns
Pages
A new joint venture between Galactic Industries and Nicolet has further added to the list of innovation in reference spectroscopic data delivery. The internet service running under http://ftiresearch.com was launched on 17 April 2000. With this new service coming on-line, the spectroscopist must now regard the year 2000 as one of the best for the introduction of new strategies and options for reference database access and service ever!
At the end of the last column we promised that this time we would show how matrix algebra can be used for real computational tasks. The chosen task is Fourier transformation (FT) of a near infrared (NIR) spectrum. Those who know Tony Davies will not be surprised at this choice of subject but in the third lesson the reason for wanting to do the obvious will become apparent.
This is a loose collection of thoughts about the "chemo" in Chemometrics. The reader should not try to find too much structure in the text. The topic is much too wide to be treated in full in such a limited space. So there is no promise of an exhaustive treatment, but it is hoped that the ideas expressed here may serve as a source of inspiration for readers.
Tony Davies tackles a crucial concept in chemometrics: the way in which data was collected may not be the best form for analysing it.