Phasic Triplet Markov Chains
| Autor: | Amar Aissani, Emmanuel Monfrini, Mohamed El Yazid Boudaren, Wojciech Pieczynski |
|---|---|
| Přispěvatelé: | Communications, Images et Traitement de l'Information (CITI), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), Ecole Militaire Polytechnique [Alger] (EMP), Ministère de l'Enseignement Supérieur et de la Recherche Scientifique [Algérie] (MESRS)-Ministère de la Défense Nationale [Algérie], Centre National de la Recherche Scientifique (CNRS), Université des Sciences et de la Technologie Houari Boumediene [Alger] (USTHB) |
| Rok vydání: | 2015 |
| Předmět: |
Markov kernel
Computer science Bayesian probability Markov process Markov model Viterbi algorithm Continuous-time Markov chain symbols.namesake Artificial Intelligence Markov renewal process [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] Markov algorithm Biology and genetics Maximum a posteriori estimation Bayesian restoration Additive Markov chain Triplet Markov chains Hidden Markov model Maximal posterior mode Markov chain mixing time Markov chain business.industry Applied Mathematics Maximum-entropy Markov model Variable-order Markov model Markov processes Partially observable Markov decision process Statistical model Pattern recognition Maximum a posteriori Hidden Markov chains Computational Theory and Mathematics Balance equation symbols Markov property Examples of Markov chains Computer Vision and Pattern Recognition Artificial intelligence Hidden semi-Markov model business Algorithm Software |
| Zdroj: | IEEE Transactions on Pattern Analysis and Machine Intelligence IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2014, 36 (11), pp.2310-2316. ⟨10.1109/TPAMI.2014.2327974⟩ |
| ISSN: | 1939-3539 0162-8828 |
| DOI: | 10.1109/TPAMI.2014.2327974⟩ |
| Popis: | International audience; Hidden Markov chains have been shown to be inadequate for data modeling under some complex conditions. In this work, we address the problem of statistical modeling of phenomena involving two heterogeneous system states. Such phenomena may arise in biology or communications, among other fields. Namely, we consider that a sequence of meaningful words is to be searched within a whole observation that also contains arbitrary one-by-one symbols. Moreover, a word may be interrupted at some site to be carried on later. Applying plain HMCs to such data, while ignoring their specificity, yields unsatisfactory results. The Phasic triplet Markov chain, proposed in this paper, overcomes this difficulty by means of an auxiliary underlying process in accordance with the triplet Markov chains theory. Related Bayesian restoration techniques and parameters estimation procedures according to the new model are then described. Finally, to assess the performance of the proposed model against the conventional hidden Markov chain model, experiments are conducted on synthetic and real data |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|