Pattern Recognition in Chemistry pp 102-105 | Cite as
Preprocessing
Chapter
Abstract
The typical steps during an application of pattern recognition methods for a chemical classification problem are:
-
- Empirical selection of measurements that are expected to be related to the classification problem.
-
- Preprocessing of the raw data and selection of relevant features.
-
- Training of a classifier.
-
- Evaluation of the trained classifier.
-
- If the performance of the classifier is not good enough then modifications on the first three steps are necessary.
Preview
Unable to display preview. Download preview PDF.
Copyright information
© Springer-Verlag Berlin Heidelberg 1980