Event recognition using a semantic-probabilistic network

Autor:	Mykyta Kovalenko, Mykola Hodovychenko, Svetlana Antoshchuk
Rok vydání:	2015
Předmět:	Relation (database) Sketch recognition business.industry Computer science Probabilistic logic Bayesian network Ontology (information science) Machine learning computer.software_genre Variable-order Bayesian network Gesture recognition Artificial intelligence business Hidden Markov model computer
Zdroj:	2015 Information Technologies in Innovation Business Conference (ITIB).
Popis:	In this paper a semantic-probabilistic network for event recognition is proposed. The approach uses pre-defined domain ontology to describe the events and scenarios in the scene as a hierarchical decomposition of simple concepts and variables and then perform an automated conversion of the ontology into a Bayesian network. A novel approach to Bayesian network nodes weights calculation is used based on the weighted relation between concepts of the ontology. We then test the performance of our approach to recognize gestures in a human gesture recognition system.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::223a96592764596fdb250278f42cd27a https://doi.org/10.1109/itib.2015.7355069 Zobrazit plný text záznamu