Inferring transportation mode from smartphone sensors: Evaluating the potential of Wi-Fi and Bluetooth

Research output: Contribution to journalJournal articlepeer-review

Standard

Inferring transportation mode from smartphone sensors : Evaluating the potential of Wi-Fi and Bluetooth. / Bjerre-Nielsen, Andreas; Minor, Kelton; Sapieżyński, Piotr; Lehmann, Sune; Lassen, David Dreyer.

In: PLoS ONE, Vol. 15, No. 7, e0234003, 2020.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Bjerre-Nielsen, A, Minor, K, Sapieżyński, P, Lehmann, S & Lassen, DD 2020, 'Inferring transportation mode from smartphone sensors: Evaluating the potential of Wi-Fi and Bluetooth', PLoS ONE, vol. 15, no. 7, e0234003. https://doi.org/10.1371/journal.pone.0234003

APA

Bjerre-Nielsen, A., Minor, K., Sapieżyński, P., Lehmann, S., & Lassen, D. D. (2020). Inferring transportation mode from smartphone sensors: Evaluating the potential of Wi-Fi and Bluetooth. PLoS ONE, 15(7), [e0234003]. https://doi.org/10.1371/journal.pone.0234003

Vancouver

Bjerre-Nielsen A, Minor K, Sapieżyński P, Lehmann S, Lassen DD. Inferring transportation mode from smartphone sensors: Evaluating the potential of Wi-Fi and Bluetooth. PLoS ONE. 2020;15(7). e0234003. https://doi.org/10.1371/journal.pone.0234003

Author

Bjerre-Nielsen, Andreas ; Minor, Kelton ; Sapieżyński, Piotr ; Lehmann, Sune ; Lassen, David Dreyer. / Inferring transportation mode from smartphone sensors : Evaluating the potential of Wi-Fi and Bluetooth. In: PLoS ONE. 2020 ; Vol. 15, No. 7.

Bibtex

@article{64bf89dae8c2429a964d5c9d93141e8c,
title = "Inferring transportation mode from smartphone sensors: Evaluating the potential of Wi-Fi and Bluetooth",
abstract = "Understanding which transportation modes people use is critical for smart cities and planners to better serve their citizens. We show that using information from pervasive Wi-Fi access points and Bluetooth devices can enhance GPS and geographic information to improve transportation detection on smartphones. Wi-Fi information also improves the identification of transportation mode and helps conserve battery since it is already collected by most mobile phones. Our approach uses a machine learning approach to determine the mode from pre-prepocessed data. This approach yields an overall accuracy of 89% and average F1 score of 83% for inferring the three grouped modes of self-powered, car-based, and public transportation. When broken out by individual modes, Wi-Fi features improve detection accuracy of bus trips, train travel, and driving compared to GPS features alone and can substitute for GIS features without decreasing performance. Our results suggest that Wi-Fi and Bluetooth can be useful in urban transportation research, for example by improving mobile travel surveys and urban sensing applications.",
author = "Andreas Bjerre-Nielsen and Kelton Minor and Piotr Sapie{\.z}y{\'n}ski and Sune Lehmann and Lassen, {David Dreyer}",
year = "2020",
doi = "10.1371/journal.pone.0234003",
language = "English",
volume = "15",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "7",

}

RIS

TY - JOUR

T1 - Inferring transportation mode from smartphone sensors

T2 - Evaluating the potential of Wi-Fi and Bluetooth

AU - Bjerre-Nielsen, Andreas

AU - Minor, Kelton

AU - Sapieżyński, Piotr

AU - Lehmann, Sune

AU - Lassen, David Dreyer

PY - 2020

Y1 - 2020

N2 - Understanding which transportation modes people use is critical for smart cities and planners to better serve their citizens. We show that using information from pervasive Wi-Fi access points and Bluetooth devices can enhance GPS and geographic information to improve transportation detection on smartphones. Wi-Fi information also improves the identification of transportation mode and helps conserve battery since it is already collected by most mobile phones. Our approach uses a machine learning approach to determine the mode from pre-prepocessed data. This approach yields an overall accuracy of 89% and average F1 score of 83% for inferring the three grouped modes of self-powered, car-based, and public transportation. When broken out by individual modes, Wi-Fi features improve detection accuracy of bus trips, train travel, and driving compared to GPS features alone and can substitute for GIS features without decreasing performance. Our results suggest that Wi-Fi and Bluetooth can be useful in urban transportation research, for example by improving mobile travel surveys and urban sensing applications.

AB - Understanding which transportation modes people use is critical for smart cities and planners to better serve their citizens. We show that using information from pervasive Wi-Fi access points and Bluetooth devices can enhance GPS and geographic information to improve transportation detection on smartphones. Wi-Fi information also improves the identification of transportation mode and helps conserve battery since it is already collected by most mobile phones. Our approach uses a machine learning approach to determine the mode from pre-prepocessed data. This approach yields an overall accuracy of 89% and average F1 score of 83% for inferring the three grouped modes of self-powered, car-based, and public transportation. When broken out by individual modes, Wi-Fi features improve detection accuracy of bus trips, train travel, and driving compared to GPS features alone and can substitute for GIS features without decreasing performance. Our results suggest that Wi-Fi and Bluetooth can be useful in urban transportation research, for example by improving mobile travel surveys and urban sensing applications.

U2 - 10.1371/journal.pone.0234003

DO - 10.1371/journal.pone.0234003

M3 - Journal article

C2 - 32614842

AN - SCOPUS:85087472390

VL - 15

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 7

M1 - e0234003

ER -

ID: 245278267