Multicomponent signal classification using the PMHT algorithm
Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997) - Tập 1 - Trang 751-757 vol.1
Tóm tắt
The probabilistic multi-hypothesis tracking (PMHT) algorithm is extended for application to classification. The PMHT model is reformulated as a bank of continuous-state hidden Markov models, allowing for supervised learning of the class-conditional probability density models, and for likelihood evaluation of multicomponent signals.
Từ khóa
#Pattern classification #Hidden Markov models #Target tracking #Trajectory #Supervised learning #Underwater acoustics #Time measurement #Underwater tracking #Condition monitoring #Probability density functionTài liệu tham khảo
streit, 1993, A probabilistic multi-hypothesis tracking algorithm without enumeration and pruning, Proceedings of the Sixth Joint Data Fusion Symposium
10.1214/aoms/1177697196
10.1093/biomet/80.2.267
titterington, 1985, Statistical Analysis of Finite Mixture Distributions
10.1109/TSP.2002.1003060
ainsleigh, 2001, Theory of Continuous-state Hidden Markov Models and Hidden Gauss-Markov Models, 10.21236/ADA415930
streit, 1995, Probabilistic mutli-hypothesis tracking
streit, 1994, Maximum likelihood method for probabilistic multi-hypothesis tracking, Proc SPIE Signal Data Process Small Targets, 2335
10.1111/j.1467-9892.1982.tb00349.x
dempster, 1977, Maximum likelihood from incomplete data via the em algorithm, Journal of the Royal Statistical Society Series B, 39, 1
10.1016/0005-1098(66)90019-7
10.1109/TAC.1969.1099196