Publikation: Dissertationsschrift

Methods for engineering symbolic human behaviour models for activity recognition

Grunddaten
Abstract
Autoren
Einrichtung

Grunddaten

Titel	Methods for engineering symbolic human behaviour models for activity recognition
Erscheinungsjahr	2014
Publikationsform	Elektronische Ressource
Publikationsart	Dissertationsschrift
Sprache	Englisch
Letzte Änderung	16.09.2014 02:17:40
Bearbeitungsstatus	durch UB Rostock abschließend validiert
Dauerhafte URL	http://purl.uni-rostock.de/fodb/pub/45849
Links zu Katalogen

Abstract

This work investigates the ability of symbolic models to encode context information that is later used for generating probabilistic models for activity recognition. The contributions of the work are as follows: it shows that it is possible to successfully use symbolic models for activity recognition; it provides a modelling toolkit that contains patterns for reducing the model complexity; it proposes a structured development process for building and evaluating computational causal behaviour models.

Autor

Yordanova, Kristina

Einrichtung

IEF/Bereich Informatik