On cleaning strategies for WiFi positioning to monitor dynamic crowds

Abstract

Monitoring open crowded areas is fundamental for policy makers to set up the proper measures for people security and safety. Different techniques have been developed to tackle this issue. The most relevant approaches, which are currently available to estimate the number of attenders, are based on the size of the area hosting the event, the count of people passing through specific points, and the employment of satellite images. All these techniques roughly estimate static crowds, but they may be limited by different factors such as the availability of satellite images, the cost of dedicated unmanned vehicles, and the capability to set up multiple counting points. In order to fill this gap, a tool to monitor dynamic crowds, based on WiFi positioning, is presented. The tool allows not only to assess the total number of people attending an event, but also to monitor their spatiotemporal distribution. In particular, the impact of the cleaning strategies on both the estimated number of participants and their spatiotemporal distribution is analyzed. The proposed approach is demonstrated using real data collected during the JRC Open Day 2016. From the results, the need of a clear strategy to identify real users in order to avoid misleading results emerges. Moreover, a proper setting of the thresholds used for the identification criteria is required. Such thresholds need to be set according to the dimension of the site, the geography of the WiFi network, and the duration of the event.

Indoor Crowd 3D Localization in Big Buildings from Wi-Fi Access Anonymous Data

“…The position that we adopt in this paper is that of ensuring maximal privacy to the subjects [1], therefore our system does not contemplate any identity related information capture or process, not even the MAC of the device which other approaches [2] use for counting and disambiguation purposes. In cases of information fusion personal data protection may be at risk, such as mentioned above.…”

“…The data used in this work is limited to relatively short periods and it is averaged hourly, therefore the results offer low time resolution. Some works in the literature [2] cover only one day, but with greater time resolution and large attendance (over several thousand people). Moreover, the number of people moving around inside the building is not big, so our accuracy claims need further confirmation on buildings with greater attendance, such as buildings devoted to classrooms.…”

“…Crowd detection is an important security problem, which is further complicated in European countries by the increasing public sensitivity about personal data protection that has led to new regulations such as the European General Data Protection Regulation (GDPR) [1] imposing tight controls and limitations to the collection and processing of personal data [2]. Therefore, crowd detection tools that ensure personal data privacy by relying only on anonymous information are highly desirable.…”

“…In contrast, the approach proposed in this paper does not need new infrastructure deployment and works for large buildings regardless of conditions such as furniture and walls. The experiment reported in [2] combines several estimation approaches, namely RSSI and position-based approaches, in an open space event. Their use of the spatial localization of the Wi-Fi-APs is a nice antecedent of our own approach.…”

“…We collect the AP information about the number of accesses to a central server, which collects their time series. This server could carry out some data cleaning, such as removing laser printers and other Wi-Fi-enabled devices that are not personal [2]. In our data gathering example, it carries out the averaging per hour, which is our time resolution for the reported computational experiments.…”