Optimizing pervasive sensor data acquisition utilizing missing values substitution
Michael Michalopoulos, Christos B. Anagnostopoulos, Charalampos N. Doukas, Ilias G. Maglogiannis, Stathes P. Hadjiefthymiades · 2010
Acquisition of pervasive sensor data can be often unsuccessful due to power outage at nodes, time synchronization issues, interference, network transmission failures or sensor hardware issues. Such failures can lead to inadequate data delivery to the monitoring applications resulting in erroneous conclusions. This paper presents a missing values substitution framework that addresses the aforementioned issue. The presented framework has been evaluated within a pervasive sensor monitoring environment that collects and transmits patient health related data and results have been presented. Copyright © 2010 ACM.