|
The Data Pair Outlier Filter separates any data pairs whose elements do not fall
within specified bounds. The data pairs whose elements fall within the bounds
are passed through the right output port. The other elements are passed through
the bottom output port.
Configuring
To set the upper and lower bounds for each element, use the configure command.
NOL displays this configuration panel:
|
To specify the number of elements of each vector, enter the dimensions for the
data pair's x and y vectors in the Number of Inputs and Number of Targets
attributes, respectively.
|
The editor has two columns: Lower and Upper bounds. When you enter the
bounds, the Upper bounds must always be greater than the Lower bounds. Therefore, you must enter the values in a specified order.
Making Values Permanent
When you choose make permanent from the block's menu, the block saves the
filter's upper and lower bounds.
Example
In the example below, the Data Pair Outlier Filter takes data pairs from a Data
Pair Buffer. It passes data pairs that fit into its bounds to the In-Bounds Data Set
and the rest to the Out-of-Bounds Data Set.
|
These spreadsheets show the bounds for the Data Pair Outlier Filter above.
|
See Also
For more information on how to use this block, see the pages below.
| Click here for more information... |
|---|
|
Basic Block Behavior
|
|
Outlier Filter
|
|
Data Pair Quality Filter
|
|
Maximum Age Filter
|
|
Size Limitation Filter
|
|
Novelty Filter
|
| Prev
| Next | Start of Chapter | End of Chapter | Contents | Index | (7 out of 18)
Copyright © 1996, Gensym Corporation, Inc.