Principled hybrid systems: theory and applications (Physta)

Kollias, Stefanos; Piat, Frederic

dc.contributor.author	Kollias, Stefanos	en
dc.contributor.author	Piat, Frederic	en
dc.date.accessioned	2014-03-01T01:15:04Z
dc.date.available	2014-03-01T01:15:04Z
dc.date.issued	1999	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13327
dc.subject	Conceptual Framework	en
dc.subject	Human Computer Interaction	en
dc.subject	Hybrid System	en
dc.subject	Multimedia Application	en
dc.subject	Rule Based System	en
dc.subject	Signal Processing	en
dc.subject	Visual Cues	en
dc.subject	Neural Network	en
dc.subject.other	Algorithmic languages	en
dc.subject.other	Artificial intelligence	en
dc.subject.other	Expert systems	en
dc.subject.other	Human computer interaction	en
dc.subject.other	Neural networks	en
dc.subject.other	Signal processing	en
dc.subject.other	Emotion analysis	en
dc.subject.other	Principled hybrid systems	en
dc.subject.other	Subsymbolic processing	en
dc.subject.other	Symbolic processing	en
dc.subject.other	Learning systems	en
dc.title	Principled hybrid systems: theory and applications (Physta)	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/MMCS.1999.778667	en
heal.identifier.secondary	http://dx.doi.org/10.1109/MMCS.1999.778667	en
heal.publicationDate	1999	en
heal.abstract	Systematic principles for integrating symbolic and subsymbolic processing will be developed in the project. Key aims are to ensure that the resulting total hybrid system retains desirable properties of both processing levels. On the one side the signal processing abilities, robustness and learning capability of neural networks should be preserved. On the other side advantage should be taken of the ability of rule-based systems to exploit high level knowledge and existing algorithms and to explain (to a user) why conclusions were reached in particular cases. The methodologies developed in the project are tested in a challenging multimedia application related to human computer interaction, which is recognition of emotion based on both voice and visual cues. Low level features are extracted from signals using neural networks and subsequent formulation of rules provides a conceptual framework, substantial for emotion analysis.	en
heal.publisher	IEEE, Los Alamitos, CA, United States	en
heal.journalName	International Conference on Multimedia Computing and Systems -Proceedings	en
dc.identifier.doi	10.1109/MMCS.1999.778667	en
dc.identifier.volume	2	en
dc.identifier.spage	1089	en
dc.identifier.epage	1091	en