Stochastic Complexity-Based Model Selection With False Alarm Rate Control in Optical Spectroscopy - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Letters Année : 2015

Stochastic Complexity-Based Model Selection With False Alarm Rate Control in Optical Spectroscopy

Julien Fade

Résumé

Stochastic complexity-based penalization criteria can prove efficient and robust in spectroscopy applications for unsupervised identification and concentration estimation of spectrally interfering chemical components. It is shown here how the so-called Normalized Maximized Likelihood (nMDL) introduced in Rissanen (1996) can be tailored to provide control of the detection performances in terms of probability of false alarm. Numerical experiments conducted on realistic simulated optical spectroscopy signals evidence that the nMDL approach outperforms standard information criteria in terms of model selection performances. Moreover, the ability to control false alarm rates with the proposed modified nMDL criterion is demonstrated on simulations.
Fichier non déposé

Dates et versions

hal-01181361 , version 1 (30-07-2015)

Identifiants

Citer

Julien Fade. Stochastic Complexity-Based Model Selection With False Alarm Rate Control in Optical Spectroscopy. Pattern Recognition Letters, 2015, 65, pp.152-156. ⟨10.1016/j.patrec.2015.07.022⟩. ⟨hal-01181361⟩
42 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More