BikeMate: Bike riding behavior monitoring with smartphones

Weixi Gu; Zimu Zhou; Yuxun Zhou; Han Zou; Yunxin Liu; Costas J. Spanos; Lin Zhang

doi:10.1145/3144457.3144462

BikeMate: Bike riding behavior monitoring with smartphones

Weixi Gu
, Zimu Zhou
, Yuxun Zhou
, Han Zou
, Yunxin Liu
, Costas J. Spanos
, Lin Zhang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

35 Citations (Scopus)

Abstract

Detecting dangerous riding behaviors is of great importance to improve bicycling safety. Existing bike safety precautionary measures rely on dedicated infrastructures that incur high installation costs. In this work, we propose BikeMate, a ubiquitous bicycling behavior monitoring system with smartphones. BikeMate invokes smartphone sensors to infer dangerous riding behaviors including lane weaving, standing pedalling and wrong-way riding. For easy adoption, BikeMate leverages transfer learning to reduce the overhead of training models for different users, and applies crowdsourcing to infer legal riding directions without prior knowledge. Experiments with 12 participants show that BikeMate achieves an overall accuracy of 86.8% for lane weaving and standing pedalling detection, and yields a detection accuracy of 90% for wrong-way riding using crowdsourced GPS traces. © 2017 Association for Computing Machinery.

Original language	English
Title of host publication	14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017
Publisher	Association for Computing Machinery
Pages	313-322
ISBN (Print)	9781450353687
DOIs	https://doi.org/10.1145/3144457.3144462
Publication status	Published - 7 Nov 2017
Externally published	Yes
Event	14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017 - Melbourne, Australia Duration: 7 Nov 2017 → 10 Nov 2017

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017
Place	Australia
City	Melbourne
Period	7/11/17 → 10/11/17

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Research Keywords

Activity Recognition
Bike
Smartphones

Access Output

10.1145/3144457.3144462

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Gu, W., Zhou, Z., Zhou, Y., Zou, H., Liu, Y., Spanos, C. J., & Zhang, L. (2017). BikeMate: Bike riding behavior monitoring with smartphones. In 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017 (pp. 313-322). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3144457.3144462

@inproceedings{4fcecc6c704a4d7c80286976ee222ce5,

title = "BikeMate: Bike riding behavior monitoring with smartphones",

abstract = "Detecting dangerous riding behaviors is of great importance to improve bicycling safety. Existing bike safety precautionary measures rely on dedicated infrastructures that incur high installation costs. In this work, we propose BikeMate, a ubiquitous bicycling behavior monitoring system with smartphones. BikeMate invokes smartphone sensors to infer dangerous riding behaviors including lane weaving, standing pedalling and wrong-way riding. For easy adoption, BikeMate leverages transfer learning to reduce the overhead of training models for different users, and applies crowdsourcing to infer legal riding directions without prior knowledge. Experiments with 12 participants show that BikeMate achieves an overall accuracy of 86.8\% for lane weaving and standing pedalling detection, and yields a detection accuracy of 90\% for wrong-way riding using crowdsourced GPS traces. {\textcopyright} 2017 Association for Computing Machinery.",

keywords = "Activity Recognition, Bike, Smartphones",

author = "Weixi Gu and Zimu Zhou and Yuxun Zhou and Han Zou and Yunxin Liu and Spanos, \{Costas J.\} and Lin Zhang",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected]. ; 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017 ; Conference date: 07-11-2017 Through 10-11-2017",

year = "2017",

month = nov,

day = "7",

doi = "10.1145/3144457.3144462",

language = "English",

isbn = "9781450353687",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "313--322",

booktitle = "14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017",

address = "United States",

}

Gu, W, Zhou, Z, Zhou, Y, Zou, H, Liu, Y, Spanos, CJ & Zhang, L 2017, BikeMate: Bike riding behavior monitoring with smartphones. in 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 313-322, 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017, Melbourne, Australia, 7/11/17. https://doi.org/10.1145/3144457.3144462

BikeMate: Bike riding behavior monitoring with smartphones. / Gu, Weixi; Zhou, Zimu; Zhou, Yuxun et al.
14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017. Association for Computing Machinery, 2017. p. 313-322 (ACM International Conference Proceeding Series).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - BikeMate

T2 - 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017

AU - Gu, Weixi

AU - Zhou, Zimu

AU - Zhou, Yuxun

AU - Zou, Han

AU - Liu, Yunxin

AU - Spanos, Costas J.

AU - Zhang, Lin

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2017/11/7

Y1 - 2017/11/7

N2 - Detecting dangerous riding behaviors is of great importance to improve bicycling safety. Existing bike safety precautionary measures rely on dedicated infrastructures that incur high installation costs. In this work, we propose BikeMate, a ubiquitous bicycling behavior monitoring system with smartphones. BikeMate invokes smartphone sensors to infer dangerous riding behaviors including lane weaving, standing pedalling and wrong-way riding. For easy adoption, BikeMate leverages transfer learning to reduce the overhead of training models for different users, and applies crowdsourcing to infer legal riding directions without prior knowledge. Experiments with 12 participants show that BikeMate achieves an overall accuracy of 86.8% for lane weaving and standing pedalling detection, and yields a detection accuracy of 90% for wrong-way riding using crowdsourced GPS traces. © 2017 Association for Computing Machinery.

AB - Detecting dangerous riding behaviors is of great importance to improve bicycling safety. Existing bike safety precautionary measures rely on dedicated infrastructures that incur high installation costs. In this work, we propose BikeMate, a ubiquitous bicycling behavior monitoring system with smartphones. BikeMate invokes smartphone sensors to infer dangerous riding behaviors including lane weaving, standing pedalling and wrong-way riding. For easy adoption, BikeMate leverages transfer learning to reduce the overhead of training models for different users, and applies crowdsourcing to infer legal riding directions without prior knowledge. Experiments with 12 participants show that BikeMate achieves an overall accuracy of 86.8% for lane weaving and standing pedalling detection, and yields a detection accuracy of 90% for wrong-way riding using crowdsourced GPS traces. © 2017 Association for Computing Machinery.

KW - Activity Recognition

KW - Bike

KW - Smartphones

UR - https://www.scopus.com/pages/publications/85052527660

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85052527660&origin=recordpage

U2 - 10.1145/3144457.3144462

DO - 10.1145/3144457.3144462

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781450353687

T3 - ACM International Conference Proceeding Series

SP - 313

EP - 322

BT - 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017

PB - Association for Computing Machinery

Y2 - 7 November 2017 through 10 November 2017

ER -

Gu W, Zhou Z, Zhou Y, Zou H, Liu Y, Spanos CJ et al. BikeMate: Bike riding behavior monitoring with smartphones. In 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017. Association for Computing Machinery. 2017. p. 313-322. (ACM International Conference Proceeding Series). doi: 10.1145/3144457.3144462

BikeMate: Bike riding behavior monitoring with smartphones

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this