System-level design of energy-efficient sensor-based human activity recognition systems: a model-based approach Grützmacher, Florian , 1990- (VerfasserIn) Haubelt, Christian , 1972- (AkademischeR BetreuerIn) Kirste, Thomas , 1962- (AkademischeR BetreuerIn) Pimentel, Andy (AkademischeR BetreuerIn) Universität Rostock (Grad-verleihende Institution) Universität Rostock Fakultät für Informatik und Elektrotechnik (Grad-verleihende Institution) Text theses Text Hochschulschrift 2021 2021 eng electronic resourceremoteComputermedienOnline-Ressource1 Online-Ressource 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.<eng> vorgelegt von Florian Grützmacher GutachterInnen: Christian Haubelt (University of Rostock, Germany) ; Thomas Kirste (University of Rostock, Germany) ; Andy Pimentel (University of Amsterdam, Netherlands) Dissertation Universität Rostock 2021 000 621.3 004.2 004 54.21 http://purl.uni-rostock.de/rosdok/id00003373 https://doi.org/10.18453/rosdok_id00003373 https://nbn-resolving.org/urn:nbn:de:gbv:28-rosdok_id00003373-3 https://d-nb.info/1293535451/34 System-level design of energy-efficient sensor-based human activity recognition systems--(DE-627)1778242898 urn:nbn:de:gbv:28-rosdok_id00003373-3 doi: 10.18453/rosdok_id00003373 oclc: 1285538691 ppn: (DE-627)1777952328