Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 May 30;23(11):5210.
doi: 10.3390/s23115210.

Automatic Passenger Counting on the Edge via Unsupervised Clustering

Giorgio Delzanno  1 , Luca Caputo  1 , Daniele D'Agostino  1 , Daniele Grosso  2 , Abdul Hannan Mustajab  1 , Luca Bixio  3 , Matteo Rulli  3
Affiliations

Automatic Passenger Counting on the Edge via Unsupervised Clustering

Giorgio Delzanno et al. Sensors (Basel). .

Abstract

We present a device- and network-based solution for automatic passnger counting that operates on the edge in real time. The proposed solution consists of a low-cost WiFi scanner device equipped with custom algorithms for dealing with MAC address randomization. Our low-cost scanner is able to capture and analyze 802.11 probe requests emitted by passengers' devices such as laptops, smartphones, and tablets. The device is configured with a Python data-processing pipeline that combines data coming from different types of sensors and processes them on the fly. For the analysis task, we have devised a lightweight version of the DBSCAN algorithm. Our software artifact is designed in a modular way in order to accommodate possible extensions of the pipeline, e.g., either additional filters or data sources. Furthermore, we exploit multi-threading and multi-processing for speeding up the entire computation. The proposed solution has been tested with different types of mobile devices, obtaining promising experimental results. In this paper, we present the key ingredients of our edge computing solution.

Keywords: IoT; WSN; artificial intelligence; edge computing.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Use of tcpdump command for sniffing probe-requests.
Figure 2
Figure 2
Record returned by tcpdump.
Figure 3
Figure 3
Comparison of MAC addresses.
Figure 4
Figure 4
Prototype of the WiFi scanner with external BrosTrend AC650 WiFi antenna (left); the Raspberry Pi4 with LTE antenna and 4G hat (center); the SIM7600X 4G hat (right).
Figure 5
Figure 5
DBSCAN search space.
Figure 6
Figure 6
Dashboard.
Figure 7
Figure 7
Counter script main loop.
Figure 8
Figure 8
Threshold and regular expressions.
Figure 9
Figure 9
The send_module main part.
Figure 10
Figure 10
The read_buf procedure.
Figure 11
Figure 11
The send_task method.
Figure 12
Figure 12
Example of acquired dataset from the unsupervised test with randomized MAC addresses.
Figure 13
Figure 13
First example of acquired dataset from the supervised test with randomized MAC addresses.
Figure 14
Figure 14
Second example of acquired dataset from the supervised test with randomized MAC addresses.
See this image and copyright information in PMC

References

    1. Kouyoumdjieva S.T., Danielis P., Karlsson G. Survey of Non-Image-Based Approaches for Counting People. IEEE Commun. Surv. Tutorials. 2019;22:1305–1336. doi: 10.1109/COMST.2019.2902824. - DOI
    1. Vieira T., Almeida P., Meireles M., Ribeiro R. Public Transport Occupancy Estimation using WLAN Probing and Mathematical Modeling. Transp. Res. Procedia. 2020;48:3299–3309. doi: 10.1016/j.trpro.2020.08.122. - DOI
    1. Hidayat A., Terabe S., Yaginuma H. Estimating bus passenger volume based on a Wi-Fi scanner survey. Transp. Res. Interdiscip. Perspect. 2020;6:100142. doi: 10.1016/j.trip.2020.100142. - DOI
    1. Uras M., Cossu R., Ferrara E., Bagdasar O., Liotta A., Atzori L. WiFi Probes Sniffing: An Artificial Intelligence Based Approach for MAC Addresses De-Randomization; Proceedings of the 2020 IEEE 25th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks; Pisa, Italy. 14–16 September 2020.
    1. Pintor L., Atzori L. A dataset of labelled device Wi-Fi probe requests for MAC address de-randomization. Comput. Netw. 2022;205:108783. doi: 10.1016/j.comnet.2022.108783. - DOI

LinkOut - more resources