Title :
Optimal Detection and Classification of Diverse Short-duration Signals
Author :
Baggenstoss, Paul M.
Author_Institution :
Naval Undersea Warfare Center, Newport, RI, USA
Abstract :
Recent theoretical advances in class-dependent feature extraction are reviewed. These advances, culminating in the multi-resolution HMM (MR-HMM) statistical model are proposed for the detection and classification of transient signals that are composed of diverse components with widely varying structure and resolution.
Keywords :
hidden Markov models; signal classification; signal detection; signal resolution; MR-HMM statistical model; class-dependent feature extraction; diverse short-duration signals; multiresolution hidden Markov model statistical model; optimal classification; optimal detection; transient signals; Bayes methods; Entropy; Feature extraction; Hidden Markov models; Probability density function; Signal resolution; Class-specific features; maximum entropy; segmentation; signal classification;
Conference_Titel :
Cloud Engineering (IC2E), 2014 IEEE International Conference on
Conference_Location :
Boston, MA
DOI :
10.1109/IC2E.2014.96
