EURASIP Journal on Advances in Signal Processing

Table 11 Results of anomaly detection

From: A machine-learning phase classification scheme for anomaly detection in signals with periodic characteristics

Type	Detection Rate	%
Phases	83/85	98%
Amplitudes	102/102	100%
Pulse	102/103	99%
Total anomalies	287/290	99%
False positives	115/26798	0.43%
White noise (σ≤6)	11/19	58%
White noise (σ>6)	64/75	85%

Back to article page