Publication
Training hidden markov models with the taguchi method
| dc.contributor.author | Coelho, João Paulo | |
| dc.contributor.author | Cunha, José Boaventura | |
| dc.contributor.author | Oliveira, Paulo de Moura | |
| dc.date.accessioned | 2011-05-23T13:49:26Z | |
| dc.date.available | 2011-05-23T13:49:26Z | |
| dc.date.issued | 2010 | |
| dc.description.abstract | In some control systems structures, like predictive control, mathematical models for the control process must be derived. Those models can be obtained by a broad class of methods like parametric models applied to experimental data. In this context, and for systems with multiple operation regimes, the Hidden Markov model, due to its properties, is a convincing choice. However the parameter estimation of this type of models involves the optimization of a non-convex cost function. So the Baum-Welch method only can find sub-optimal parameters. This article shows that the use of the Taguchi method minimizes the training algorithm sensibility local minima. | por |
| dc.identifier.citation | Coelho, João; Cunha, José; Oliveira, Paulo (2010). Training hidden markov models with the taguchi method. In 9th Portuguese Conference on Automatic Control. | por |
| dc.identifier.uri | http://hdl.handle.net/10198/4468 | |
| dc.language.iso | eng | por |
| dc.peerreviewed | yes | por |
| dc.subject | Hidden Markov models | |
| dc.subject | Taguchi method | |
| dc.subject | Optimization problems | |
| dc.title | Training hidden markov models with the taguchi method | por |
| dc.type | conference object | |
| dspace.entity.type | Publication | |
| oaire.citation.title | CONTROLO’2010 – 9th Portuguese Conference on Automatic Control | por |
| person.familyName | Coelho | |
| person.givenName | João Paulo | |
| person.identifier | R-001-EXZ | |
| person.identifier.ciencia-id | D61E-A586-7D4A | |
| person.identifier.orcid | 0000-0002-7616-1383 | |
| person.identifier.rid | J-6887-2013 | |
| person.identifier.scopus-author-id | 55137039300 | |
| rcaap.rights | restrictedAccess | por |
| rcaap.type | conferenceObject | por |
| relation.isAuthorOfPublication | 2861f33b-b49a-421d-9bfa-92b4304d2668 | |
| relation.isAuthorOfPublication.latestForDiscovery | 2861f33b-b49a-421d-9bfa-92b4304d2668 |