Main Page Class Hierarchy Alphabetical List Compound List Compound Members

prapi::SequentialSelector Class Reference

#include <FeatureSelector.h>

Inheritance diagram for prapi::SequentialSelector:

Detailed Description

Methods for sequential feature selection.

This class is capable of performing (feature) subset selection with the SFS, SFFS, SBS, and SBFS methods. In fact, due to the abstraction of performance evaluation, this class serves just as an algorithm that can be used in selecting a sub-optimal subset from just about anything. A common example is finding a sub-optimal subset of model samples from a large number of candidates.

Public Methods

SequentialSelector (GoodnessMeasure &measure, bool forward=true, bool floating=true)

Create a new (feature) selector.

void setParams (bool forward, bool floating)

Set search parameters.

bool isFloating () const

See if the search is of "floating" type.

bool isForward () const

See if the search goes forward.

util::List< int > optimize (int totalCount, int desiredCount=-1)

Find a sub-optimal subset of items.

Constructor & Destructor Documentation

prapi::SequentialSelector::SequentialSelector ( GoodnessMeasure & measure,

bool forward = true,

bool floating = true

) [inline]

Create a new (feature) selector.
The different types of selection schemes can be achieved with the following parameter combinations:
Method | forward floating -------+----------------- SBS | false false SBFS | false true SFS | true false SFFS | true true
Parameters:

forward if true, selection is started with an empty item set. At each iteration, all remaining items are added to "enabled" items in turn, the resulting sets are evaluated, and the best one is selected. If false, the search goes backward. That is, selection is started with all items enabled. Each item is dropped out in turn, and the item whose removal resulted in the best score is discarded.

floating if true, the search goes both back and forth, alternating each phase.

Member Function Documentation

List< int > prapi::SequentialSelector::optimize ( int totalCount,

int desiredCount = -1

) [virtual]

Find a sub-optimal subset of items.
The implementation of this method is method-dependent. By convention, each implementation should fire a SelectionEvent every time an optimization round is finished.
Parameters:

totalCount the total number of items out of which the subset is to be selected.

the desired number of enabled items after optimization. If this value is set to a non-positive value, optimization is stopped only after the goodness threshold is exceeded.

Implements prapi::SubSetSelector.

The documentation for this class was generated from the following files:

FeatureSelector.h
FeatureSelector.cc

Public Methods
	SequentialSelector (GoodnessMeasure &measure, bool forward=true, bool floating=true)
	Create a new (feature) selector.
void	setParams (bool forward, bool floating)
	Set search parameters.
bool	isFloating () const
	See if the search is of "floating" type.
bool	isForward () const
	See if the search goes forward.
util::List< int >	optimize (int totalCount, int desiredCount=-1)
	Find a sub-optimal subset of items.