The ultimate success of spectroscopic applications often hinges on data preprocessing. The goal of preprocessing is to mitigate the effects of clutter, i.e. variation in the data due to physical effects, instrument drift, noise and analytical interferents. Models can then focus on variation related to the properties of interest. Many methods have been developed to remove various sources of clutter. This course will illustrate these methods with hands-on examples with a variety of data sets from spectroscopy and spectrometry.
For this course it is assumed that participants have a basic understanding of elementary linear algebra and are familiar with basic chemometric methods including Principal Components Analysis (PCA) and Partial Least Squares regression (PLS).
This course will be delivered via WebEx webinar in two segments of three and a half hours each. The course material is based on our popular Eigenvector University Advanced Preprocessing for Spectral Applications course. Please refer to it for a complete description and course outline.
The course will include many follow-along examples and several homework problems. In order to take advantage of these, participants should equip their computers with current versions of our MATLAB based software PLS_Toolbox and MIA_Toolbox. Alternately participants can use our stand-alone Solo+MIA software (available for Windows, MacOS and Linux). Demo copies will work just fine. Users with Eigenvector accounts can download free demos. If you don’t have an account, start by creating one.