Privacy-Friendly Wi-Fi-Based Occupancy Estimation with Minimal Resources

Privacy-Friendly Wi-Fi-Based Occupancy Estimation with Minimal Resources

E. Makri (School of Governance, Law and Urban Development, Saxion University of Applied Sciences, Enschede, The Netherlands), J. ten Brinke (School of Creative Technology, Saxion University of Applied Sciences, Enschede, The Netherlands), R. Evers (School of Creative Technology, Saxion University of Applied Sciences, Enschede, The Netherlands), P. Man (School of Creative Technology, Saxion University of Applied Sciences, Enschede, The Netherlands) and H. Olthof (School of Creative Technology, Saxion University of Applied Sciences, Enschede, The Netherlands)
Copyright: © 2018 |Pages: 18
DOI: 10.4018/IJACI.2018100103

Abstract

Occupancy estimation is becoming an increasingly popular research topic, as solutions can be deployed both to the challenges of demand-driven ambient comfort control applications, and to the challenges of building safety and security. With this article, the authors aim to estimate the number of people in a particular area of a building, using only existing infrastructure. To achieve this, information is collected from the Wi-Fi Access Points installed throughout a building, in such a way that the privacy of the persons using the Wi-Fi resources remains intact. While several approaches have been proposed to address the occupancy question, the main contribution lies in that the solution uses only standard Wi-Fi infrastructure, already deployed in any modern building. In addition, the authors claim that their solution comes at virtually zero cost, as their mechanisms add negligible network traffic, using minimal network and processing resources, and it does not require specialised hardware.
Article Preview
Top

1. Introduction

Occupancy estimation is becoming increasingly popular, especially during the last six years. It is not occupancy per se that current solutions aim to detect (i.e., answering the occupied/not occupied question), but actually estimate the number of people in a specific part of a building. This information can vastly contribute in energy savings, as HVAC (heating, ventilating, and air conditioning) systems can be automatically adjusted to the actual needs per area of a building. Since buildings account for 40% of the U.S. energy consumption (Yang et al., 2012), we can conclude that this is a very important aspect of sustainability and energy conservation.

In addition to the energy and environmental benefits that occupancy count bears, it is also of utmost importance to building safety and security. Although less emphasized in the current literature, information on the number of people in a certain part of a building, can be of great assistance to the public safety and security services. Use cases include emergency egress scenarios such as fire, and hostage situations. When emergency services (e.g., fire and police department) are aware of the number of people present in the specific area of interest, they can more efficiently manage resources. Knowing how many persons need to be rescued, and their true location within a building saves valuable resources. This is essential in emergency situations occurring at the same time, in the same region. More interestingly, proper resource management can result in timely responses, and eventually contribute in the protection of life and property. In conclusion, we argue that accurate information on the number of people in the different parts of a building is fundamental in the development of smart and safe buildings.

A lot of solutions have been proposed in the literature, with many of them achieving above 80% accuracy. However, the majority of these works (Benezeth et al., 2011; Depatla, Muralidharan, & Mostofi, 2015; Dodier et al., 2006; Dong et al., 2010; Han, Gao, & Fan, 2012; Li, Calis, & Becerik-Gerber, 2012; Meyn et al., 2009; Pan et al., 2014; Tomastik et al., 2010; Woo et al., 2011; Yang et al., 2012) requires dedicated equipment; others (Balaji et al., 2013; Benezeth et al., 2011; Christensen et al., 2014; Khan, Hossain, & Roy, 2015; Li, Calis, & Becerik-Gerber, 2012; Meyn et al., 2009; Tomastik et al., 2010) are intrusive; and some (Ebadat et al., 2013; Lam et al., 2009) assume existing sensors that are not always present in today’s buildings. We aim in developing a plug and play, software-based system that is sufficiently accurate in counting the number of people in a building area, so as to serve the purposes of the aforementioned application scenarios.

We propose a Wi-Fi based occupancy estimation tool, which respects user privacy. To preserve the occupant’s privacy, we deploy the current state-of-the-art hashing techniques on the collected user identifiable information, namely the IP, and MAC addresses. We consider this to be an important feature of our tool, as being able to identify where, and when a user is, can facilitate an adversary in creating user profiles that can be used from marketing and advertising purposes, to even facilitate physical crime (Stottelaar et al., 2014).

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 12: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing