zum Inhalt

 

Mohammed,  Redwan Abdo Abdullah

Predicting human behavior in smart environments  : theory and application to gaze prediction

Rostock : Universität , 2017

https://doi.org/10.18453/rosdok_id00001865

http://purl.uni-rostock.de/rosdok/id00001865

Predicting human behavior is desirable in many application scenarios in smart environments. The existing models for eye movements do not take contextual factors into account. This addressed in this thesis using a systematic machine-learning approach, where user profiles for eye movements behaviors are learned from data. In addition, a theoretical innovation is presented, which goes beyond pure data analysis. The thesis proposed the modeling of eye movements as a Markov Decision Processes. It uses Inverse Reinforcement Learning paradigm to infer the user eye movements behaviors.

Dissertation Open Access


Einrichtung :
Fakultät für Informatik und Elektrotechnik
Gutachter :
Staadt,  Oliver  (Prof. Dr. Sc. techn.)
Kirste,  Thomas  (Prof. Dr.-Ing.)
Sprekeler,  Henning  (Prof. Dr.)
Schwabe,  Lars  (Dr. rer. nat.)
Jahr der Abgabe:
2015
Jahr der Verteidigung:
2016
Sprache(n) :
Englisch
Schlagworte:
visual attention recognition, context-aware systems, gaze prediction, normative models, intelligent systems
DDC Klassifikation :
004 Informatik
URN :
urn:nbn:de:gbv:28-diss2017-0029-6
Persistente URL:
http://purl.uni-rostock.de/rosdok/id00001865
erstellt am:
2017-03-03
zuletzt geändert am:
2018-06-30
Volltext