“Nonintrusive Ultrasonic-Based Occupant Identification for Energy Efficient Smart Building Applications” by Nacer Khalil, Driss Benhaddou, Omprakash Gnawali, and Jaspal Subhlok. Applied Energy, vol. 220 , June 2018, pp. 814-828, Elsevier.
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.
BibTeX entry:
@article{ultrasonic-appliedenergy2018,
author = {Nacer Khalil, and Driss Benhaddou and Omprakash Gnawali and
Jaspal Subhlok},
title = {Nonintrusive Ultrasonic-Based Occupant Identification for
Energy Efficient Smart Building Applications},
journal = {Applied Energy},
volume = { 220 },
pages = { 814-828},
publisher = {Elsevier},
month = jun,
year = {2018}
}