Authors:
Masoud Vatanpour Azghandi
;
Ioanis Nikolaidis
and
Eleni Stroulia
Affiliation:
University of Alberta, Canada
Keyword(s):
Wireless Sensor Networks, Indoor Localization, Optimization, Sensor Placement, Smart Homes, Genetic Algorithms.
Related
Ontology
Subjects/Areas/Topics:
Data Communication Networking
;
Enterprise Information Systems
;
Internet of Things
;
Sensor Networks
;
Software Agents and Internet Computing
;
Software and Architectures
;
Telecommunications
Abstract:
Single occupant localization in an indoor environment can be accomplished by the deployment of, properly
placed, motion sensors. In this paper, we address the problem of cost-efficient sensor placement for highquality
indoor localization, taking into account sensors with diverse coverage footprints, and the occlusion
effects due to obstructions typically found in indoor environments. The objective is the placement of the
smallest number of sensors with the right combination of footprints. To address the problem, and motivated
by the vast search space of possible placement and footprint combinations, we adopt an evolutionary technique.
We demonstrate that our technique performs faster and/or produces more accurate results (depending on the
application) when compared to previously proposed greedy methods. Furthermore, our technique is flexible
in that adding new sensor footprints can be trivially accomplished.