Multi-Label Feature Selection with Conditional Mutual Information

Algorithm 1

MCMI.

	Input: a feature set F, a label set L, and the number of selected features K.
	Output: selected feature subset S.
(1)
(2)
(3)	for i = 1 to n do
(4)	for j = 1 to m do
(5)	calculate the relevance between fi and lj
(6)	end for
(7)	end for
(8)	while k < K do
(9)	ifthen
(10)	select the feature fi with the greatest relevance
(11)	else
(12)	for every elements fi in F do
(13)	for every elements fj in F except fido
(14)	sum the rebundancy between fi and fj
	(15)end for
(16)	according to formula (16) and calculate the J (fi)
(17)	end for
(18)
(19)
(20)
(21)	end if
(22)	end while
(23)	return S.