metal oxide gas sensors; gaussian mixture model; principal component analysis; k nearest neighbours
Abstract :
[en] Electronic noses are intelligent instruments that are able to
classify and quantify different gas/odours. Here we suggest the
integration of a small form factor computer inside the electronic
nose. This concept allows us to easily provide remote connectivity,
large data storage and complex signal processing. The evolution of
this technology will permit distributed sensing with applications to
agriculture and environment. Proposed instrument allows incoming
connections for remote control of bad odours in landfill sites.
Preliminary approach to this application using commercial sensors
and mixture model pattern recognition scheme is exposed.
