CoChat

The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index; none of the 13 sources its claims cite is checked for support yet.

iABACUS: A Wi-Fi-Based Automatic Bus Passenger Counting System

Open access
Nitti, Michele, Pinna, Francesca, Pintor, Lucia, Pilloni, Virginia, Barabino, Benedetto · 2020 · Energies

Abstract

Since the early stages of the Internet-of-Things (IoT), one of the application scenarios that have been affected the most by this new paradigm is mobility. Smart Cities have greatly benefited from the awareness of some people’s habits to develop efficient mobility services. In particular, knowing how people use public transportation services and move throughout urban infrastructure is crucial in several areas, among which the most prominent are tourism and transportation. Indeed, especially for Public Transportation Companies (PTCs), long- and short-term planning of the transit network requires having a thorough knowledge of the flows of passengers in and out vehicles. Thanks to the ubiquitous presence of Internet connections, this knowledge can be easily enabled by sensors deployed on board of public transport vehicles. In this paper, a Wi-Fi-based Automatic Bus pAssenger CoUnting System, named iABACUS, is presented. The objective of iABACUS is to observe and analyze urban mobility by tracking passengers throughout their journey on public transportation vehicles, without the need for them to take any action. Test results proves that iABACUS efficiently detects the number of devices with an active Wi-Fi interface, with an accuracy of 100% in the static case and almost 94% in the dynamic case. In the latter case, there is a random error that only appears when two bus stops are very close to each other.

Overview

CoChat Summary

TL;DR

iABACUS is a Wi-Fi-based automatic bus passenger counting system that sniffs Probe Request frames and de-randomizes MAC addresses to count and track passenger devices without passenger action. It reports 100% accuracy in a static test and almost 94% in a dynamic car-simulated bus test, with random errors mainly when two bus stops are very close.

Key findings

  • In the static de-randomization test with 21 devices with active Wi-Fi in a university room over 15 minutes, iABACUS returned the exact number of devices (21), while a traditional Wi-Fi APCS that ignores MAC randomization would have counted 37; the abstract reports 100% accuracy in the static case.
  • In the dynamic car-simulated bus experiments in Cagliari, with 13 stops and 8 Wi-Fi devices (3 implementing MAC randomization), the abstract reports almost 94% accuracy; errors were random and appeared when two bus stops were very close.
  • Across three dynamic tests, the first test missed devices A and H, misassigned devices D and C, and counted an unplanned external device X; the second test had only a device C alighting/boarding error; the third test solved the device C problem and counted no external devices even with the required frame count set to 1, but device D was again misassigned because stops 2 and 3 were very close and their guard times overlapped.
  • The paper states MAC randomization is a serious problem: even the presence of only three devices can lead to a count six times higher in a 15-minute interval, while the de-randomization algorithm successfully recognized all randomized MAC addresses in the 21-device test.

Methods

  • iABACUS uses an on-board Wi-Fi sniffer to collect Probe Request frames, stores them in a MySQL database via a Lua script, and queries them with a PHP application; the de-randomization algorithm uses tagged parameters, timestamps, and frame sequence numbers, while the counting algorithm applies temporal windows, frame-count thresholds, received-power thresholds, permanence checks, guard times, and sectors around bus stops.
  • Static evaluation: a Wireshark sniffer in Monitor Mode captured broadcast Probe Request frames in a university room for 15 minutes, with 21 devices with active Wi-Fi, 2.4 GHz reception, and a received-power threshold of −55 dBm.
  • Dynamic evaluation: a car simulated a bus path in Cagliari, Italy, with 13 stops, about 2.4 km, and about 15 minutes travel time; 8 Wi-Fi devices were used, 3 with MAC randomization, and boarding/alighting was simulated by switching Wi-Fi interfaces on and off; the sniffer was implemented on a Raspberry Pi 2 with Raspbian Stretch, a USB Wi-Fi dongle, and a GPS module sending position every 5 s; three tests tuned parameters such as temporal window, required frame count, power threshold, permanence time, and guard time.

Limitations

  • The paper states future work is needed on real-use conditions such as Wi-Fi signal attenuation due to bus size or passenger bodies, interference, and non-line-of-sight; on how many sniffers are required and their optimal position; on the random error related to proximity of two bus stops; and on the systematic error due to non-connected users, including comparison with local bus transport data and city-specific adjusting factors.
  • The paper states that scaling factors are needed because the number of devices may not equal the number of passengers, and that calibrating these factors is out of scope; Wi-Fi may underestimate passenger volumes if Wi-Fi is turned off, while multiple devices per passenger may overestimate counts.
  • Evident from the text: the dynamic experiments used a car to simulate a bus, involved only 8 devices with 3 randomized, and were run in moderate traffic before or during lunch; errors were tied to low or irregular Probe Request frequency and energy-saving mode, and close bus stops could cause guard-time overlap and unavoidable misassignment.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/en13061446

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 iABACUS.
Figure 1 iABACUS.CC-BY · From the PDF
Figure 2 Wi-Fi Probe Request frame [44].
Figure 2 Wi-Fi Probe Request frame [44].CC-BY · From the PDF
Figure 3 Tag Section Probe Request Frame.
Figure 3 Tag Section Probe Request Frame.CC-BY · From the PDF
Figure 4 Flow chart of the system.
Figure 4 Flow chart of the system.CC-BY · From the PDF
Figure 5 Counting problem and parameters.
Figure 5 Counting problem and parameters.CC-BY · From the PDF
Figure 6 Percentage of received Probe Request frames with respect to their receiving power.
Figure 6 Percentage of received Probe Request frames with respect to their receiving power.CC-BY · From the PDF
Figure 7 Path of the vehicle for the experiments.
Figure 7 Path of the vehicle for the experiments.CC-BY · From the PDF

Verification

Claims the paper makes

0 Valid · 3 Not valid · 11 Not checked · 60 Own results and interpretations

38 more claims

Create a free account to see all 74 claims and to verify the 1 reference still open.

See all claims — free account
  • It may state two separate claims as one. 20
  • Probably not a substantial claim. 16

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

2 of 2

Citations

Cites

Show all 40 references

Research works printed but not linked: 4

  1. Barabino, 2013, The quality of public transport service: The 13816 standard and a methodological approach to an Italian case, Ing. Ferrov., 68, 475
  2. Pinna, 2010, Automatic passenger counting and vehicle load monitoring, Ing. Ferrov., 65, 101
  3. Kyritsis, D. (2017). The Identification of Road Modality and Occupancy Patterns by Wi-Fi Monitoring Sensors as a Way to Support the “Smart Cities” Concept: Application at the City Centre of Dordrecht. [Master’s Thesis, TU Delft].
  4. IEEE Computer Society LAN/MAN Standards Committee (2007). IEEE Standard for Information Technology-Telecommunications and Information Exchange between Systems-Local and Metropolitan Area Networks-Specific Requirements Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications, IEEE. IEEE Std 802.11.

Cited by

See all 80

Metadata

Authors
Nitti, M., Pinna, F., Pintor, L., Pilloni, V., & Barabino, B.
Affiliations
  • University of Cagliari (IT)
  • Department of Electrical and Electronic Engineering (DIEE), University of Cagliari, 09123 Cagliari, Italy
  • University of Brescia (IT)
Corresponding author
  • Nitti, Michele
  • Pilloni, Virginia
  • Barabino, Benedetto
Venue
Energies
Publisher
MDPI AG
Published
2020-03-19
Volume
13
Issue
6
Pages
1446
ISSN
1996-1073 (ISSN-L)
OpenAlex
W3012110674
Cited by
72
References
40
Citations by year
2026: 3 · 2025: 17 · 2024: 20 · 2023: 12 · 2022: 10 · 2021: 7 · 2020: 3
FWCI
7.14
Type
journal article
Language
en
Open access
Locations
  • Energies (publishedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Institutional Research Information System (Università degli Studi di Brescia) (submittedVersion, cc-by)
  • UNICA IRIS Institutional Research Information System (University of Cagliari) (submittedVersion, other-oa)
Funders
  • Ministero dell’Istruzione, dell’Università e della Ricerca (SCN_00281, PON04a2_00381)
  • Ministero dello Sviluppo Economico (PON 2014/2020 POS. 395)
Topics
  • Social Sciences › Transportation › Human Mobility and Location-Based Analysis
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Indoor and Outdoor Localization Technologies
  • Social Sciences › Transportation › Transportation Planning and Optimization
Keywords
automatic passenger counting, WiFi sensing, Internet of Things, public transport, urban mobility, smart cities, in-vehicle sensors, device detection, transit network planning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: iABACUS: A Wi-Fi-Based Automatic Bus Passenger Counting System. https://app.cochat.ai/papers/10.3390/en13061446
The paper
Nitti, M., Pinna, F., Pintor, L., Pilloni, V., & Barabino, B. (2020). iABACUS: A Wi-Fi-Based Automatic Bus Passenger Counting System. Energies. https://doi.org/10.3390/en13061446

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.