A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior

Fatjon Seraj; Kui Zhang; Okan Türkes; Nirvana Meratnia; Paul J.M. Havinga

doi:10.1145/2800835.2800981

A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior

Fatjon Seraj, Kui Zhang, Okan Türkes, Nirvana Meratnia, Paul J.M. Havinga

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

15 Citations (Scopus)

119 Downloads (Pure)

Abstract

This paper introduces a method to detect road anomalies by analyzing driver behaviours. The analysis is based on the data and the features extracted from smartphone inertial sensors to calculate the angle of swerving and also based on distinctive states of a driver behaviour event. A novel approach is introduced to deal with the gyroscope drift, reducing the average angle estimation error for curves up to 2° and the overall average angle error up to 5°. Using a simple machine learning approach and a clustering algorithm, the method can detect 70% of the swerves and 95% of the turns on the road.

Original language	English
Title of host publication	UbiComp & ISWC'15
Subtitle of host publication	proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the proceedings of the 2015 ACM International Symposium on Wearable Computers
Place of Publication	New York
Publisher	Association for Computing Machinery (ACM)
Pages	1169-1177
Number of pages	9
ISBN (Print)	978-1-4503-3575-1
DOIs	https://doi.org/10.1145/2800835.2800981
Publication status	Published - Sep 2015
Event	ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2015 ACM International Symposium on Wearable Computers - Osaka, Japan Duration: 7 Sep 2015 → 11 Sep 2015

Conference

Conference	ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2015 ACM International Symposium on Wearable Computers
Abbreviated title	UbiComp & ISWC
Country	Japan
City	Osaka
Period	7/09/15 → 11/09/15

Keywords

EWI-26651
Smartphone Sensing
Driver Behaviour
METIS-315138
IR-98920
Anomaly Detection
Road Monitoring

Access to Document

10.1145/2800835.2800981

p1169-seraj
open

Fingerprint Dive into the research topics of 'A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior'. Together they form a unique fingerprint.

Cite this

Seraj, F., Zhang, K., Türkes, O., Meratnia, N., & Havinga, P. J. M. (2015). A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior. In UbiComp & ISWC'15: proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the proceedings of the 2015 ACM International Symposium on Wearable Computers (pp. 1169-1177). New York: Association for Computing Machinery (ACM). https://doi.org/10.1145/2800835.2800981

Seraj, Fatjon ; Zhang, Kui ; Türkes, Okan ; Meratnia, Nirvana ; Havinga, Paul J.M. / A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior. UbiComp & ISWC'15: proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the proceedings of the 2015 ACM International Symposium on Wearable Computers. New York : Association for Computing Machinery (ACM), 2015. pp. 1169-1177

@inproceedings{f23645749f184f0b8f1e6a626aa9a1a6,

title = "A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior",

abstract = "This paper introduces a method to detect road anomalies by analyzing driver behaviours. The analysis is based on the data and the features extracted from smartphone inertial sensors to calculate the angle of swerving and also based on distinctive states of a driver behaviour event. A novel approach is introduced to deal with the gyroscope drift, reducing the average angle estimation error for curves up to 2° and the overall average angle error up to 5°. Using a simple machine learning approach and a clustering algorithm, the method can detect 70{\%} of the swerves and 95{\%} of the turns on the road.",

keywords = "EWI-26651, Smartphone Sensing, Driver Behaviour, METIS-315138, IR-98920, Anomaly Detection, Road Monitoring",

author = "Fatjon Seraj and Kui Zhang and Okan T{\"u}rkes and Nirvana Meratnia and Havinga, {Paul J.M.}",

note = "eemcs-eprint-26651",

year = "2015",

month = "9",

doi = "10.1145/2800835.2800981",

language = "English",

isbn = "978-1-4503-3575-1",

pages = "1169--1177",

booktitle = "UbiComp & ISWC'15",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

}

Seraj, F, Zhang, K, Türkes, O, Meratnia, N & Havinga, PJM 2015, A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior. in UbiComp & ISWC'15: proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the proceedings of the 2015 ACM International Symposium on Wearable Computers. Association for Computing Machinery (ACM), New York, pp. 1169-1177, ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2015 ACM International Symposium on Wearable Computers, Osaka, Japan, 7/09/15. https://doi.org/10.1145/2800835.2800981

A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior. / Seraj, Fatjon; Zhang, Kui; Türkes, Okan; Meratnia, Nirvana ; Havinga, Paul J.M.

UbiComp & ISWC'15: proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the proceedings of the 2015 ACM International Symposium on Wearable Computers. New York : Association for Computing Machinery (ACM), 2015. p. 1169-1177.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior

AU - Seraj, Fatjon

AU - Zhang, Kui

AU - Türkes, Okan

AU - Meratnia, Nirvana

AU - Havinga, Paul J.M.

N1 - eemcs-eprint-26651

PY - 2015/9

Y1 - 2015/9

N2 - This paper introduces a method to detect road anomalies by analyzing driver behaviours. The analysis is based on the data and the features extracted from smartphone inertial sensors to calculate the angle of swerving and also based on distinctive states of a driver behaviour event. A novel approach is introduced to deal with the gyroscope drift, reducing the average angle estimation error for curves up to 2° and the overall average angle error up to 5°. Using a simple machine learning approach and a clustering algorithm, the method can detect 70% of the swerves and 95% of the turns on the road.

AB - This paper introduces a method to detect road anomalies by analyzing driver behaviours. The analysis is based on the data and the features extracted from smartphone inertial sensors to calculate the angle of swerving and also based on distinctive states of a driver behaviour event. A novel approach is introduced to deal with the gyroscope drift, reducing the average angle estimation error for curves up to 2° and the overall average angle error up to 5°. Using a simple machine learning approach and a clustering algorithm, the method can detect 70% of the swerves and 95% of the turns on the road.

KW - EWI-26651

KW - Smartphone Sensing

KW - Driver Behaviour

KW - METIS-315138

KW - IR-98920

KW - Anomaly Detection

KW - Road Monitoring

U2 - 10.1145/2800835.2800981

DO - 10.1145/2800835.2800981

M3 - Conference contribution

SN - 978-1-4503-3575-1

SP - 1169

EP - 1177

BT - UbiComp & ISWC'15

PB - Association for Computing Machinery (ACM)

CY - New York

ER -

Seraj F, Zhang K, Türkes O, Meratnia N , Havinga PJM. A smartphone based method to enhance road pavement anomaly detection by analyzing the driver behavior. In UbiComp & ISWC'15: proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the proceedings of the 2015 ACM International Symposium on Wearable Computers. New York: Association for Computing Machinery (ACM). 2015. p. 1169-1177 https://doi.org/10.1145/2800835.2800981