|Wireless sensor networks (WSNs) consist of a large number of sensor nodes that measure properties
of interests of their local environment. The sensor nodes communicate and share information with
neighbor nodes in order to enhance their limited measurement or decision capabilities. WSNs
have been considered for various monitoring and control applications such as target detection,
recognition, localization, biomedical applications, home and office applications
, and structural health monitoring. These applications require in common
a capability to efficiently process the distributed information, utilizing the restricted resource.
We investigate efficient learning algorithms for WSNs that can accurately estimate quantities of interests despite a large amount of data, limited communication capacity, and low computation power.
For more information, visit the lab webpage.