Along this line, building envelopes that separate the indoor from the outdoor environments, and in particular building façades, play a substantial role for energy saving in buildings.
In summary, our methodological approach was to train individual multivariate pattern classifiers (MVPCs) to distinguish indoor from outdoor scenes separately in each of the three task conditions.
Within the context of a panel study of children with asthma in Montreal, Canada, we describe an automated classification of GPS data into location-based categories that makes use of temperature data to assist in discriminating indoor from outdoor locations.
In addition, their use of temperature to distinguish indoor from outdoor locations in the winter of Colorado may not be applicable to other regions or seasons when indoor and outdoor temperature does not vary as much.
For instance, a Canadian study assigned all GPS points within 350 m of a residence as home and 400 m of a work place as work, and did not differentiate indoor from outdoor environments [ 50]; such an approach could lead to substantial exposure misclassification.
