Identifying movements in noisy crowd analytics data

Cristian Chilipirea, Ciprian Dobre, Mitra Baratchi, Martinus Richardus van Steen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
14 Downloads (Pure)

Abstract

Privacy-preserved tracking of WiFi-enabled devices such as smartphones offers a highly scalable solution for large-scale crowd movement studies. However, extracting knowledge out of pedestrian-tracking data acquired this way is not simple. This is, generally, due to the inherent inaccuracy of the measurement technique. Segmenting an individual's trajectory data into periods of stops and moves is a fundamental step in analyzing crowds' movement. Such distinctions allow us to answer advanced questions regarding visited locations or even social behavior. Algorithms previously designed for distinguishing movements from stay periods, assume datasets are gathered using GPS, which offers precise positioning. WiFi tracking, however, does not offer such precision. The location of devices can at best be reduced to a large area around the WiFi scanner. In this paper, we study a set of established algorithms for detecting periods of stops and moves from GPS-based datasets and their applicability to WiFi-based data. Consequently, we propose possible improvements to such algorithms considering the inherent characteristics of WiFi tracking data.
Original languageEnglish
Title of host publication19th International Conference on Mobile Data Management (MDM)
PublisherIEEE
Pages161-166
ISBN (Electronic)978-1-5386-4133-0
DOIs
Publication statusPublished - 16 Jul 2018
Event19th IEEE International Conference on Mobile Data Management 2018 - Aalborg, Denmark
Duration: 26 Jun 201828 Jun 2018
Conference number: 19
http://mdmconferences.org/mdm2018/

Conference

Conference19th IEEE International Conference on Mobile Data Management 2018
Abbreviated titleIEEE MDM 2018
CountryDenmark
CityAalborg
Period26/06/1828/06/18
Internet address

Fingerprint

Global positioning system
Smartphones
Trajectories

Cite this

Chilipirea, C., Dobre, C., Baratchi, M., & van Steen, M. R. (2018). Identifying movements in noisy crowd analytics data. In 19th International Conference on Mobile Data Management (MDM) (pp. 161-166). IEEE. https://doi.org/10.1109/MDM.2018.00033
Chilipirea, Cristian ; Dobre, Ciprian ; Baratchi, Mitra ; van Steen, Martinus Richardus. / Identifying movements in noisy crowd analytics data. 19th International Conference on Mobile Data Management (MDM). IEEE, 2018. pp. 161-166
@inproceedings{113228605fd84f09a177b4290446175f,
title = "Identifying movements in noisy crowd analytics data",
abstract = "Privacy-preserved tracking of WiFi-enabled devices such as smartphones offers a highly scalable solution for large-scale crowd movement studies. However, extracting knowledge out of pedestrian-tracking data acquired this way is not simple. This is, generally, due to the inherent inaccuracy of the measurement technique. Segmenting an individual's trajectory data into periods of stops and moves is a fundamental step in analyzing crowds' movement. Such distinctions allow us to answer advanced questions regarding visited locations or even social behavior. Algorithms previously designed for distinguishing movements from stay periods, assume datasets are gathered using GPS, which offers precise positioning. WiFi tracking, however, does not offer such precision. The location of devices can at best be reduced to a large area around the WiFi scanner. In this paper, we study a set of established algorithms for detecting periods of stops and moves from GPS-based datasets and their applicability to WiFi-based data. Consequently, we propose possible improvements to such algorithms considering the inherent characteristics of WiFi tracking data.",
author = "Cristian Chilipirea and Ciprian Dobre and Mitra Baratchi and {van Steen}, {Martinus Richardus}",
year = "2018",
month = "7",
day = "16",
doi = "10.1109/MDM.2018.00033",
language = "English",
pages = "161--166",
booktitle = "19th International Conference on Mobile Data Management (MDM)",
publisher = "IEEE",
address = "United States",

}

Chilipirea, C, Dobre, C, Baratchi, M & van Steen, MR 2018, Identifying movements in noisy crowd analytics data. in 19th International Conference on Mobile Data Management (MDM). IEEE, pp. 161-166, 19th IEEE International Conference on Mobile Data Management 2018, Aalborg, Denmark, 26/06/18. https://doi.org/10.1109/MDM.2018.00033

Identifying movements in noisy crowd analytics data. / Chilipirea, Cristian; Dobre, Ciprian; Baratchi, Mitra ; van Steen, Martinus Richardus.

19th International Conference on Mobile Data Management (MDM). IEEE, 2018. p. 161-166.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Identifying movements in noisy crowd analytics data

AU - Chilipirea, Cristian

AU - Dobre, Ciprian

AU - Baratchi, Mitra

AU - van Steen, Martinus Richardus

PY - 2018/7/16

Y1 - 2018/7/16

N2 - Privacy-preserved tracking of WiFi-enabled devices such as smartphones offers a highly scalable solution for large-scale crowd movement studies. However, extracting knowledge out of pedestrian-tracking data acquired this way is not simple. This is, generally, due to the inherent inaccuracy of the measurement technique. Segmenting an individual's trajectory data into periods of stops and moves is a fundamental step in analyzing crowds' movement. Such distinctions allow us to answer advanced questions regarding visited locations or even social behavior. Algorithms previously designed for distinguishing movements from stay periods, assume datasets are gathered using GPS, which offers precise positioning. WiFi tracking, however, does not offer such precision. The location of devices can at best be reduced to a large area around the WiFi scanner. In this paper, we study a set of established algorithms for detecting periods of stops and moves from GPS-based datasets and their applicability to WiFi-based data. Consequently, we propose possible improvements to such algorithms considering the inherent characteristics of WiFi tracking data.

AB - Privacy-preserved tracking of WiFi-enabled devices such as smartphones offers a highly scalable solution for large-scale crowd movement studies. However, extracting knowledge out of pedestrian-tracking data acquired this way is not simple. This is, generally, due to the inherent inaccuracy of the measurement technique. Segmenting an individual's trajectory data into periods of stops and moves is a fundamental step in analyzing crowds' movement. Such distinctions allow us to answer advanced questions regarding visited locations or even social behavior. Algorithms previously designed for distinguishing movements from stay periods, assume datasets are gathered using GPS, which offers precise positioning. WiFi tracking, however, does not offer such precision. The location of devices can at best be reduced to a large area around the WiFi scanner. In this paper, we study a set of established algorithms for detecting periods of stops and moves from GPS-based datasets and their applicability to WiFi-based data. Consequently, we propose possible improvements to such algorithms considering the inherent characteristics of WiFi tracking data.

UR - https://www.distributed-systems.net/my-data/papers/2018.mdm.pdf

U2 - 10.1109/MDM.2018.00033

DO - 10.1109/MDM.2018.00033

M3 - Conference contribution

SP - 161

EP - 166

BT - 19th International Conference on Mobile Data Management (MDM)

PB - IEEE

ER -

Chilipirea C, Dobre C, Baratchi M, van Steen MR. Identifying movements in noisy crowd analytics data. In 19th International Conference on Mobile Data Management (MDM). IEEE. 2018. p. 161-166 https://doi.org/10.1109/MDM.2018.00033