Publikation: Dissertationsschrift

System-level design of energy-efficient sensor-based human activity recognition systems

Grunddaten
Abstract
Autoren

Grunddaten

Titel	System-level design of energy-efficient sensor-based human activity recognition systems
Untertitel	a model-based approach
Erscheinungsjahr	2021
Verlag	Universität Rostock
Verlagsort	Rostock
Publikationsform	Elektronische Ressource
Publikationsart	Dissertationsschrift
Sprache	Englisch
DOI	10.18453/rosdok_id00003373
Letzte Änderung	25.11.2021 06:01:52
Bearbeitungsstatus	durch UB Rostock abschließend validiert
Dauerhafte URL	http://purl.uni-rostock.de/fodb/pub/66402
Links zu Katalogen

Abstract

This thesis contributes an evaluation of state-of-the-art dataflow models of computation regarding their suitability for a model-based design and analysis of human activity recognition systems, in terms of expressiveness and analyzability, as well as model accuracy. Different aspects of state-of-the-art human activity recognition systems have been modeled and analyzed. Based on existing methods, novel analysis approaches have been developed to acquire extra-functional properties like processor utilization, data communication rates, and finally energy consumption of the system.

Autor

Grützmacher, Florian