DocumentCode
2345997
Title
The most informative stopping times for Viterbi algorithm: sequential properties
Author
Kogan, Joseph A.
Author_Institution
Courant Inst. of Math. Sci., New York Univ., NY, USA
fYear
1994
fDate
27-29 Oct 1994
Firstpage
89
Abstract
Sequential properties of the Viterbi algorithm are studied based on a renewal sequence of the most informative stopping times which can be explicitly found during the Viterbi recognition of the most likeliest hidden Markovian state-sequence
Keywords
dynamic programming; estimation theory; hidden Markov models; maximum likelihood estimation; Viterbi algorithm; dynamic programming; hidden Markovian state-sequence; most informative stopping times; renewal sequence; sequential properties; Hidden Markov models; Information analysis; Sequential analysis; Viterbi algorithm;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Theory and Statistics, 1994. Proceedings., 1994 IEEE-IMS Workshop on
Conference_Location
Alexandria, VA
Print_ISBN
0-7803-2761-6
Type
conf
DOI
10.1109/WITS.1994.513916
Filename
513916
Link To Document