Copyright notice: Permission to make digital/hard copy of all or part of any of the following publications and technical reports for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage. These publications are covered by copyright of the authors and Publishing agencies.
Zodiac project tackles the problem of heterogeneity in sensor naming across buildings. The dataset contains ground sensor names for four buildings at UC San Diego along with their raw metadata. Zodiac algorithm employs active learning to reduce manual effort required to map the sensors to a uniform naming schema.
Link to Paper