Ci-dessous, les différences entre deux révisions de la page.
Les deux révisions précédentesRévision précédenteProchaine révision | Révision précédente | ||
fr:recherche [2011/11/21 14:54] – sdesterc | fr:recherche [Date inconnue] (Version actuelle) – supprimée - modification externe (Date inconnue) 127.0.0.1 | ||
---|---|---|---|
Ligne 1: | Ligne 1: | ||
- | My researches mainly concern uncertainty modeling and treatment with the help of imprecise probabilistic approaches (Lower previsions theory, Dempster-Shafer theory, Possibility theory). Roughly speaking, these approaches propose to blend interval and probabilistic methods to deal with situations of severe uncertainty (missing or imprecise data, few available information, | ||
- | Inside this theories, most of my research energy is spent in proposing practical solutions to various problems using these methods or in linking the solutions that those theories propose to common problems (information fusion, independence modeling, ...). | ||
- | |||
- | ====== Practical uncertainty representations ====== | ||
- | |||
- | There exist many practical representations in imprecise probability theories, including possibility distributions, | ||
- | |||
- | Aside establishing new relations between the properties of several models (i.e. clouds, p-boxes, possibility distributions), | ||
- | |||
- | Our current focus is to link this model with other models (such as info-gap theory) that use the idea of nested sets to propose solutions to statistical problems. | ||
- | |||
- | ====== Information fusion and combination ====== | ||
- | |||
- | Merging information from multiple sources is a common problem in modern systems. Common problems encountered by such merging are to cope with dependent and conflicting sources, and to take account of sources characteristics (reliability, | ||
- | |||
- | For practical purposes, we have proposed to use the notion of maximal coherent subsets as a way to deal with conflict among sources, and have applied it to the problem of estimating source reliability form meta-information. | ||
- | |||
- | Our current focus on this area is to apply information fusion and combination ideas to the problem of classifier combination. | ||
- | |||
- | ====== Classification problems ====== | ||
- | |||
- | |||
- |