A new criterion for optimal constrained minimax detection and classification

This paper adresses the problem of anomaly detection and classification by using a noisy measurement vector corrupted by some linear unknown nuisance parameters. An invariant constrained asymptotically uniformly minimax test is proposed. It minimizes the maximum false classfication probability as the signal-to-noise ratio becomes arbitrary large, uniformly with respect to the unknown anomaly amplitude and independently on the nuisance parameters. The probability of maximum classification error is calculated in a closed-form.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Lionel Fillatre, Igor Nikiforov
• Keywords: ICASSP 2011, Nuisance Parameters, Signal Processing, Unknown Anomaly Amplitude, Unknown Nuisance Parameters