Error control for the detection of rare and weak signatures in massive data

Céline Meillier (1, 2) , Florent Chatelain (1) , Olivier Michel (2) , H Ayasso (2)

1 GIPSA-SAIGA - GIPSA - Signal et Automatique pour la surveillance, le diagnostic et la biomécanique
2 GIPSA-CICS - GIPSA - Communication Information and Complex Systems

In this paper, we address the general issue of detecting rare and weak signatures in very noisy data. Multiple hypotheses testing approaches can be used to extract a list of components of the data that are likely to be contaminated by a source while controlling a global error criterion. However most of efficients methods available in the literature are derived for independent tests. Based on the work of Benjamini and Yekutieli [1], we show that under some classical positiv-ity assumptions, the Benjamini-Hochberg procedure for False Discovery Rate (FDR) control can be directly applied to the result produced by a very common tool in signal and image processing: the matched filter. This shows that despite the dependency structure between the components of the matched filter output, the Benjamini-Hochberg procedure still guarantee the FDR control. This is illustrated on both synthetic and real data.

Mots clés: massive data; source detection; matched filter; error control; FDR

Domaines: Traitement du signal et de l'image [eess.SP]; Statistiques [stat]

Céline Meillier, Florent Chatelain, Olivier Michel, H Ayasso. Error control for the detection of rare and weak signatures in massive data. EUSIPCO 2015 - 23th European Signal Processing Conference, Aug 2015, Nice, France. ⟨hal-01198717⟩