AURES: A Wide-Band Ultrasonic Occupancy Sensing Platform
Anthony Rowe, Patrick Lazik, Oliver Shih

Citation
Anthony Rowe, Patrick Lazik, Oliver Shih. "AURES: A Wide-Band Ultrasonic Occupancy Sensing Platform". The 3rd ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys 2016), November, 2016.

Abstract
In this paper, we present a platform designed for low-power real-time sensing of the number of occupants in indoor spaces. The system transmits a wide-band ultrasonic signal into a room and then processes the superposition of the reflections recorded by a microphone. The system has two modes of operation, one for presence detection and one for estimating the number of occupants in a region. The presence detec- tion uses the difference between multiple transmissions in succession with a set of general classifiers that make a bi- nary decision about if the room contains occupants. We then use a semi-supervised learning approach based on Weighted Principal Component Analysis (WPCA) that requires mini- mal training data to estimate the number of occupants. We also present the design of an energy harvesting embedded platform for this purpose and demonstrate that our algo- rithm can continuously execute using energy harvested from indoor solar panels. The platform has a dual Bluetooth Low- Energy and 802.15.4 interface to communicate with a gate- way or nearby mobile phone that runs an interface used for labeling crowd level. We evaluate the algorithm on a wide- variety of indoor spaces as well as benchmark the hardware in terms of sampling rate given an energy budget. On more than three weeks of data, we see that we can detect motions with an average of 85% recall rate and occupancy counting with an average error of 10% in terms of maximum occu- pancy.

Electronic downloads

Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Anthony Rowe, Patrick Lazik, Oliver Shih. <a
  href="http://www.terraswarm.org/pubs/820.html"
  >AURES: A Wide-Band Ultrasonic Occupancy Sensing
  Platform</a>, The 3rd ACM International Conference on
  Systems for Energy-Efficient Built Environments (BuildSys
  2016), November, 2016.

• Plain text

  Anthony Rowe, Patrick Lazik, Oliver Shih. "AURES: A
  Wide-Band Ultrasonic Occupancy Sensing Platform". The
  3rd ACM International Conference on Systems for
  Energy-Efficient Built Environments (BuildSys 2016),
  November, 2016.

• BibTeX

  @inproceedings{RoweLazikShih16_AURESWideBandUltrasonicOccupancySensingPlatform,
      author = {Anthony Rowe and Patrick Lazik and Oliver Shih},
      title = {AURES: A Wide-Band Ultrasonic Occupancy Sensing
                Platform},
      booktitle = {The 3rd ACM International Conference on Systems
                for Energy-Efficient Built Environments (BuildSys
                2016)},
      month = {November},
      year = {2016},
      abstract = {In this paper, we present a platform designed for
                low-power real-time sensing of the number of
                occupants in indoor spaces. The system transmits a
                wide-band ultrasonic signal into a room and then
                processes the superposition of the reflections
                recorded by a microphone. The system has two modes
                of operation, one for presence detection and one
                for estimating the number of occupants in a
                region. The presence detec- tion uses the
                difference between multiple transmissions in
                succession with a set of general classifiers that
                make a bi- nary decision about if the room
                contains occupants. We then use a semi-supervised
                learning approach based on Weighted Principal
                Component Analysis (WPCA) that requires mini- mal
                training data to estimate the number of occupants.
                We also present the design of an energy harvesting
                embedded platform for this purpose and demonstrate
                that our algo- rithm can continuously execute
                using energy harvested from indoor solar panels.
                The platform has a dual Bluetooth Low- Energy and
                802.15.4 interface to communicate with a gate- way
                or nearby mobile phone that runs an interface used
                for labeling crowd level. We evaluate the
                algorithm on a wide- variety of indoor spaces as
                well as benchmark the hardware in terms of
                sampling rate given an energy budget. On more than
                three weeks of data, we see that we can detect
                motions with an average of 85% recall rate and
                occupancy counting with an average error of 10% in
                terms of maximum occu- pancy.},
      URL = {http://terraswarm.org/pubs/820.html}
  }
  

Posted by Anthony Rowe on 9 Sep 2016.