zum Inhalt

 

Yordanova,  Kristina Yordanova

Methods for engineering symbolic human behaviour models for activity recognition

Rostock : Universität , 2014

https://doi.org/10.18453/rosdok_id00001381

http://purl.uni-rostock.de/rosdok/id00001381

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.

Dissertation Open Access


Einrichtung :
Fakultät für Informatik und Elektrotechnik
Gutachter :
Kirste,  Thomas  (Prof. Dr.-Ing.)
Uhrmacher,  Adelinde  (Prof. Dr. rer. nat. habil.)
Heisel,  Maritta  (Prof. Dr. rer. nat.)
Jahr der Abgabe:
2014
Jahr der Verteidigung:
2014
Sprache(n) :
Englisch
Schlagworte:
intention recognition, context-aware systems, intelligent systems, symbolic state space models, computational causal behaviour models, proactive assistance
DDC Klassifikation :
004 Informatik
URN :
urn:nbn:de:gbv:28-diss2014-0133-5
Persistente URL:
http://purl.uni-rostock.de/rosdok/id00001381
erstellt am:
2014-09-03
zuletzt geändert am:
2018-06-30
Volltext