
Overview of Knowledge Discovery ◾ 21
on. e cleaned data can be further processed by feature selection and extraction
algorithms (to reduce dimensionality), by the derivation of new attributes (say by
discretization), and by the summarization of data (data granularization). e result
would be new data records, meeting specic input requirements for the use of the
potential DM tools.
Data Mining
is is also regarded as a key step in the knowledge discovery process. Although it
is the DM tools that discover new information, their application usually takes less
time than data preparation. is step involves the usage of the planned DM tools
and the ...