Question about data processing

[Perter_Be]

Hi guys,
I am writing a term paper where data mining is used to improve the security of a power grid and I have a question about data processing.

So various kinds of data is collected from a power grid like: Outages, transformer data, power quality, system loads etc.
This data is then processed for an machine learning application. And it is said that the following things are done with the collected data:
- Parse ans scale features
- Aggregation and binning
- Convert categorical to boolean features

I don't have the foggiest clue about what is menat "Convert categorical to boolean features". Could anyone of you imagine what this could mean.

[editor]

This conversion is standard when applying many types of machine learning algorithms like neural nets which cannot deal easily with nominal values.

For example, say you have a feature COLOR, and it can have values,
RED, GREEN, and BLUE. Then you would replace it with 3 new attributes:

COLOR_RED (if COLOR="RED" then 1 else 0),
COLOR_GREEN (if COLOR="GREEN" then 1 else 0),
COLOR_BLUE (if COLOR="BLUE" then 1 else 0)

[Perter_Be]

Thank you for your answer. But now I have 2 question with regard to you answer:
1) Why can many machine learning algorithms not deal with nominal values
2) If we use boolean valuse why do we have to Parse ans scale features