A Log-Based Anomaly Detection Method with Efficient Neighbor Searching and Automatic K Neighbor Selection

Algorithm 4

The strategy of anomaly detection.

	Require: The sample to be detected S. An actual neighbor set containing neighbor samples for sample S. A positive sample set containing m normal samples in . A negative sample set containing n abnormal samples in Actual_Neighbor .
	Ensure: The label of S
(1)	function (P, F, m, n)
(2)	fordo
(3)
(4)	end for
(5)	for j do
(6)
(7)	end for
(8)	ifthen
(9)	return normal
(10)	else
(11)	return abnormal
(12)	end if
(21)	end function