RoADS: A road pavement monitoring system for anomaly detection using smart phones

Fatjon Seraj; B.J. van der Zwaag; Arta Dilo; Tamara Luarasi; Paul J.M. Havinga

doi:10.1007/978-3-319-29009-6

RoADS: A road pavement monitoring system for anomaly detection using smart phones

Fatjon Seraj, B.J. van der Zwaag, Arta Dilo, Tamara Luarasi, Paul J.M. Havinga

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

131 Downloads (Pure)

Abstract

Monitoring the road pavement is a challenging task. Authorities spend time and finances to monitor the state and quality of the road pavement. This paper investigate road surface monitoring with smartphones equipped with GPS and inertial sensors: accelerometer and gyroscope. In this study we describe the conducted experiments with data from the time domain, frequency domain and wavelet transformation, and a method to reduce the effects of speed, slopes and drifts from sensor signals. A new audiovisual data labelling technique is proposed. Our system named RoADS, implements wavelet decomposition analysis for signal processing of inertial sensor signals and Support Vector Machine (SVM) for anomaly detection and classification. Using these methods we are able to build a real time multiclass road anomaly detector. We obtained a consistent accuracy of ≈90% on detecting severe anomalies regardless of vehicle type and road location. Local road authorities and communities can benefit from this system to evaluate the state of their road network pavement in real time.

Original language	Undefined
Title of host publication	Big Data Analytics in the Social and Ubiquitous Context
Editors	Martin Atzmueller, Alvin Chin, Frederik Janssen, Immanuel Schweizer, Christoph Trattner
Place of Publication	Berlin
Publisher	Springer
Pages	128-146
Number of pages	16
ISBN (Print)	978-3-319-29008-9
DOIs	https://doi.org/10.1007/978-3-319-29009-6 https://doi.org/10.1007/978-3-319-29009-6_7
Publication status	Published - 7 Jan 2016
Event	1st International Workshop on Machine Learning for Urban Sensor Data, SenseML 2014 - Nancy, France Duration: 15 Sep 2014 → 15 Sep 2014

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Number	9546
Volume	9546
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Workshop

Workshop	1st International Workshop on Machine Learning for Urban Sensor Data, SenseML 2014
Period	15/09/14 → 15/09/14
Other	15 September 2014

Keywords

EWI-26650
Anomaly Detection
METIS-315137
IR-98919
Machine Learning

Access to Document

Seraj_et_al._-_RoADS
open

Cite this

Seraj, F., van der Zwaag, B. J., Dilo, A., Luarasi, T., & Havinga, P. J. M. (2016). RoADS: A road pavement monitoring system for anomaly detection using smart phones. In M. Atzmueller, A. Chin, F. Janssen, I. Schweizer, & C. Trattner (Eds.), Big Data Analytics in the Social and Ubiquitous Context (pp. 128-146). (Lecture Notes in Computer Science; Vol. 9546, No. 9546). Springer. https://doi.org/10.1007/978-3-319-29009-6, https://doi.org/10.1007/978-3-319-29009-6_7

Seraj, Fatjon ; van der Zwaag, B.J. ; Dilo, Arta ; Luarasi, Tamara ; Havinga, Paul J.M. / RoADS: A road pavement monitoring system for anomaly detection using smart phones. Big Data Analytics in the Social and Ubiquitous Context. editor / Martin Atzmueller ; Alvin Chin ; Frederik Janssen ; Immanuel Schweizer ; Christoph Trattner. Berlin : Springer, 2016. pp. 128-146 (Lecture Notes in Computer Science; 9546).

@inbook{fdd6438946eb45e683034306ea376089,

title = "RoADS: A road pavement monitoring system for anomaly detection using smart phones",

abstract = "Monitoring the road pavement is a challenging task. Authorities spend time and finances to monitor the state and quality of the road pavement. This paper investigate road surface monitoring with smartphones equipped with GPS and inertial sensors: accelerometer and gyroscope. In this study we describe the conducted experiments with data from the time domain, frequency domain and wavelet transformation, and a method to reduce the effects of speed, slopes and drifts from sensor signals. A new audiovisual data labelling technique is proposed. Our system named RoADS, implements wavelet decomposition analysis for signal processing of inertial sensor signals and Support Vector Machine (SVM) for anomaly detection and classification. Using these methods we are able to build a real time multiclass road anomaly detector. We obtained a consistent accuracy of ≈90% on detecting severe anomalies regardless of vehicle type and road location. Local road authorities and communities can benefit from this system to evaluate the state of their road network pavement in real time.",

keywords = "EWI-26650, Anomaly Detection, METIS-315137, IR-98919, Machine Learning",

author = "Fatjon Seraj and {van der Zwaag}, B.J. and Arta Dilo and Tamara Luarasi and Havinga, {Paul J.M.}",

note = "5th International Workshop on Modeling Social Media, MSM 2014, 5th International Workshop on Mining Ubiquitous and Social Environments, MUSE 2014, and First International Workshop on Machine Learning for Urban Sensor Data, SenseML 2014, Revised Selected Papers; null ; Conference date: 15-09-2014 Through 15-09-2014",

year = "2016",

month = jan,

day = "7",

doi = "10.1007/978-3-319-29009-6",

language = "Undefined",

isbn = "978-3-319-29008-9",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

number = "9546",

pages = "128--146",

editor = "Martin Atzmueller and Alvin Chin and Frederik Janssen and Immanuel Schweizer and Christoph Trattner",

booktitle = "Big Data Analytics in the Social and Ubiquitous Context",

address = "Netherlands",

}

Seraj, F, van der Zwaag, BJ, Dilo, A, Luarasi, T & Havinga, PJM 2016, RoADS: A road pavement monitoring system for anomaly detection using smart phones. in M Atzmueller, A Chin, F Janssen, I Schweizer & C Trattner (eds), Big Data Analytics in the Social and Ubiquitous Context. Lecture Notes in Computer Science, no. 9546, vol. 9546, Springer, Berlin, pp. 128-146, 1st International Workshop on Machine Learning for Urban Sensor Data, SenseML 2014, 15/09/14. https://doi.org/10.1007/978-3-319-29009-6, https://doi.org/10.1007/978-3-319-29009-6_7

RoADS: A road pavement monitoring system for anomaly detection using smart phones. / Seraj, Fatjon; van der Zwaag, B.J.; Dilo, Arta; Luarasi, Tamara; Havinga, Paul J.M.

Big Data Analytics in the Social and Ubiquitous Context. ed. / Martin Atzmueller; Alvin Chin; Frederik Janssen; Immanuel Schweizer; Christoph Trattner. Berlin : Springer, 2016. p. 128-146 (Lecture Notes in Computer Science; Vol. 9546, No. 9546).

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

TY - CHAP

T1 - RoADS: A road pavement monitoring system for anomaly detection using smart phones

AU - Seraj, Fatjon

AU - van der Zwaag, B.J.

AU - Dilo, Arta

AU - Luarasi, Tamara

AU - Havinga, Paul J.M.

N1 - 5th International Workshop on Modeling Social Media, MSM 2014, 5th International Workshop on Mining Ubiquitous and Social Environments, MUSE 2014, and First International Workshop on Machine Learning for Urban Sensor Data, SenseML 2014, Revised Selected Papers

PY - 2016/1/7

Y1 - 2016/1/7

N2 - Monitoring the road pavement is a challenging task. Authorities spend time and finances to monitor the state and quality of the road pavement. This paper investigate road surface monitoring with smartphones equipped with GPS and inertial sensors: accelerometer and gyroscope. In this study we describe the conducted experiments with data from the time domain, frequency domain and wavelet transformation, and a method to reduce the effects of speed, slopes and drifts from sensor signals. A new audiovisual data labelling technique is proposed. Our system named RoADS, implements wavelet decomposition analysis for signal processing of inertial sensor signals and Support Vector Machine (SVM) for anomaly detection and classification. Using these methods we are able to build a real time multiclass road anomaly detector. We obtained a consistent accuracy of ≈90% on detecting severe anomalies regardless of vehicle type and road location. Local road authorities and communities can benefit from this system to evaluate the state of their road network pavement in real time.

AB - Monitoring the road pavement is a challenging task. Authorities spend time and finances to monitor the state and quality of the road pavement. This paper investigate road surface monitoring with smartphones equipped with GPS and inertial sensors: accelerometer and gyroscope. In this study we describe the conducted experiments with data from the time domain, frequency domain and wavelet transformation, and a method to reduce the effects of speed, slopes and drifts from sensor signals. A new audiovisual data labelling technique is proposed. Our system named RoADS, implements wavelet decomposition analysis for signal processing of inertial sensor signals and Support Vector Machine (SVM) for anomaly detection and classification. Using these methods we are able to build a real time multiclass road anomaly detector. We obtained a consistent accuracy of ≈90% on detecting severe anomalies regardless of vehicle type and road location. Local road authorities and communities can benefit from this system to evaluate the state of their road network pavement in real time.

KW - EWI-26650

KW - Anomaly Detection

KW - METIS-315137

KW - IR-98919

KW - Machine Learning

U2 - 10.1007/978-3-319-29009-6

DO - 10.1007/978-3-319-29009-6

M3 - Chapter

SN - 978-3-319-29008-9

T3 - Lecture Notes in Computer Science

SP - 128

EP - 146

BT - Big Data Analytics in the Social and Ubiquitous Context

A2 - Atzmueller, Martin

A2 - Chin, Alvin

A2 - Janssen, Frederik

A2 - Schweizer, Immanuel

A2 - Trattner, Christoph

PB - Springer

CY - Berlin

Y2 - 15 September 2014 through 15 September 2014

ER -

Seraj F, van der Zwaag BJ, Dilo A, Luarasi T, Havinga PJM. RoADS: A road pavement monitoring system for anomaly detection using smart phones. In Atzmueller M, Chin A, Janssen F, Schweizer I, Trattner C, editors, Big Data Analytics in the Social and Ubiquitous Context. Berlin: Springer. 2016. p. 128-146. (Lecture Notes in Computer Science; 9546). https://doi.org/10.1007/978-3-319-29009-6, https://doi.org/10.1007/978-3-319-29009-6_7