Nonintrusive ultrasonic-based occupant identification for energy efficient smart building applications

Nacer Khalil, Driss Benhaddou, Omprakash Gnawali and Jaspal Subhlok

Applied Energy, 2018, vol. 220, issue C, 814-828

Abstract: The ability to non-intrusively identify people will enable smart buildings to customize the environment to meet occupants’ comfort level while saving energy. Occupant identification can help in energy savings effort in a building because we can retrieve each occupant’s temperature preference profile and choose the temperature that minimizes the total discomfort of a group in the building. To enable occupant identification in buildings, many methods used can be intrusive, such as using cameras or requiring the users to carry mobile gadgets or a smart phone. Non-intrusive techniques are gaining interest in smart building applications. In this paper, we present a non-intrusive ultrasonic based sensing technique to identify people by sensing their body shape and movement. The ultrasonic sensors are placed on the top and sides of doors to measure the height and width as the occupant walks through the instrumented doorway. Height and width and their related features can give a unique signature to occupants to identify them. In this study, the proposed system senses a stream of height and width data, recognizes the walking event when a person walks through the door, and extracts features that capture a person’s movement as well as physical shape. These features are fed to a clustering algorithm that associates each occupant with a distinct cluster. The system was deployed for a total of three months. The results show that the proposed approach achieves 95% accuracy with 20 occupants suggesting the suitability of our approach in commercial building settings. In addition, the results show that using girth to distinguish between occupants is more successful than using height. We show that this system generalizes beyond our datasets and works for different populations of different physical distributions.

Keywords: Occupant identification; Sensor networks; Smart buildings; Clustering; Machine learning (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261918303477
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:220:y:2018:i:c:p:814-828

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2018.03.018

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().