Graphics Reference
In-Depth Information
Feature Selection
Instance Selection
Discretization
Fig. 1.4
Forms of data reduction
factors, such as the decreasing of the complexity and improvement of the quality of
the models yielded, the role of data reduction is again decisive.
As mentioned before, what are the basic issues that must be resolved in data
reduction? Again, we provide a series of questions associated with the correct answer
related to each type of task that belongs to the data reduction techniques:
How do I reduce the dimensionality of data?—Feature Selection (FS).
How do I remove redundant and/or conflictive examples?—Instance Selection
(IS).
How do I simplify the domain of an attribute?—Discretization.
How do I fill in gaps in data?—Feature Extraction and/or Instance Generation.
In the following, we provide a concise explanation of the four techniques enu-
merated before. Figure
1.4
shows an illustrative picture that reflects the forms of data
reduction. All of themwill be extended, studied and analyzed throughout the various
chapters of the topic.
