Abstract

All drivers have their own habitual choice of driving behavior, causing variations in fuel consumption. It would be beneficial to classify these driving styles and extract the most economical and ecological driving patterns. However, driving style of each driver is not consistent and may vary within a single trip. Therefore, this paper proposes a novel technique to robustly classify driving style using the Support Vector Clustering approach, which attempts to differentiate the variations in individual's driving pattern and provides an objective driver classification. Real driving data of three human participants were collected using an instrumented vehicle. For data processing, each trip data were first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering was performed to classify driving style during the trip. The trained classifier was used to indicate the driving pattern variations in percentage. The validity of the proposed method was evaluated using the jerk profile, where a high correlation was found between the classification results and jerk distributions. Moreover, a positive relation between fuel consumption and driving aggressivity was also confirmed. Furthermore, it was found that weather condition, time of the day and ultimately, the driver's eagerness, can cause significant variations in driving style.

Original languageEnglish
Title of host publication2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018
PublisherIEEE
Pages264-268
Number of pages5
ISBN (Electronic)9781538678312
DOIs
Publication statusPublished - 18 Oct 2018
Event3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018 - Singapore, Singapore
Duration: 3 Sep 20185 Sep 2018

Publication series

Name2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018

Conference

Conference3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018
CountrySingapore
CitySingapore
Period3/09/185/09/18

Keywords

  • Driving style classification
  • Fuel consumption
  • Principal component analysis
  • Support vector clustering

ASJC Scopus subject areas

  • Decision Sciences (miscellaneous)
  • Automotive Engineering
  • Civil and Structural Engineering
  • Control and Optimization
  • Transportation
  • Urban Studies

Cite this

Feng, Y., Pickering, S., Chappell, E., Iravani, P., & Brace, C. (2018). Driving Style Analysis by Classifying Real-World Data with Support Vector Clustering. In 2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018 (pp. 264-268). [8492700] (2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018). IEEE. https://doi.org/10.1109/ICITE.2018.8492700

Driving Style Analysis by Classifying Real-World Data with Support Vector Clustering. / Feng, Yuxiang; Pickering, Simon; Chappell, Edward; Iravani, Pejman; Brace, Chris.

2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018. IEEE, 2018. p. 264-268 8492700 (2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Feng, Y, Pickering, S, Chappell, E, Iravani, P & Brace, C 2018, Driving Style Analysis by Classifying Real-World Data with Support Vector Clustering. in 2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018., 8492700, 2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018, IEEE, pp. 264-268, 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018, Singapore, Singapore, 3/09/18. https://doi.org/10.1109/ICITE.2018.8492700
Feng Y, Pickering S, Chappell E, Iravani P, Brace C. Driving Style Analysis by Classifying Real-World Data with Support Vector Clustering. In 2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018. IEEE. 2018. p. 264-268. 8492700. (2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018). https://doi.org/10.1109/ICITE.2018.8492700
Feng, Yuxiang ; Pickering, Simon ; Chappell, Edward ; Iravani, Pejman ; Brace, Chris. / Driving Style Analysis by Classifying Real-World Data with Support Vector Clustering. 2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018. IEEE, 2018. pp. 264-268 (2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018).
@inproceedings{3b0d9e549b5549a5916db43b2813822f,
title = "Driving Style Analysis by Classifying Real-World Data with Support Vector Clustering",
abstract = "All drivers have their own habitual choice of driving behavior, causing variations in fuel consumption. It would be beneficial to classify these driving styles and extract the most economical and ecological driving patterns. However, driving style of each driver is not consistent and may vary within a single trip. Therefore, this paper proposes a novel technique to robustly classify driving style using the Support Vector Clustering approach, which attempts to differentiate the variations in individual's driving pattern and provides an objective driver classification. Real driving data of three human participants were collected using an instrumented vehicle. For data processing, each trip data were first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering was performed to classify driving style during the trip. The trained classifier was used to indicate the driving pattern variations in percentage. The validity of the proposed method was evaluated using the jerk profile, where a high correlation was found between the classification results and jerk distributions. Moreover, a positive relation between fuel consumption and driving aggressivity was also confirmed. Furthermore, it was found that weather condition, time of the day and ultimately, the driver's eagerness, can cause significant variations in driving style.",
keywords = "Driving style classification, Fuel consumption, Principal component analysis, Support vector clustering",
author = "Yuxiang Feng and Simon Pickering and Edward Chappell and Pejman Iravani and Chris Brace",
year = "2018",
month = "10",
day = "18",
doi = "10.1109/ICITE.2018.8492700",
language = "English",
series = "2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018",
publisher = "IEEE",
pages = "264--268",
booktitle = "2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018",
address = "USA United States",

}

TY - GEN

T1 - Driving Style Analysis by Classifying Real-World Data with Support Vector Clustering

AU - Feng, Yuxiang

AU - Pickering, Simon

AU - Chappell, Edward

AU - Iravani, Pejman

AU - Brace, Chris

PY - 2018/10/18

Y1 - 2018/10/18

N2 - All drivers have their own habitual choice of driving behavior, causing variations in fuel consumption. It would be beneficial to classify these driving styles and extract the most economical and ecological driving patterns. However, driving style of each driver is not consistent and may vary within a single trip. Therefore, this paper proposes a novel technique to robustly classify driving style using the Support Vector Clustering approach, which attempts to differentiate the variations in individual's driving pattern and provides an objective driver classification. Real driving data of three human participants were collected using an instrumented vehicle. For data processing, each trip data were first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering was performed to classify driving style during the trip. The trained classifier was used to indicate the driving pattern variations in percentage. The validity of the proposed method was evaluated using the jerk profile, where a high correlation was found between the classification results and jerk distributions. Moreover, a positive relation between fuel consumption and driving aggressivity was also confirmed. Furthermore, it was found that weather condition, time of the day and ultimately, the driver's eagerness, can cause significant variations in driving style.

AB - All drivers have their own habitual choice of driving behavior, causing variations in fuel consumption. It would be beneficial to classify these driving styles and extract the most economical and ecological driving patterns. However, driving style of each driver is not consistent and may vary within a single trip. Therefore, this paper proposes a novel technique to robustly classify driving style using the Support Vector Clustering approach, which attempts to differentiate the variations in individual's driving pattern and provides an objective driver classification. Real driving data of three human participants were collected using an instrumented vehicle. For data processing, each trip data were first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering was performed to classify driving style during the trip. The trained classifier was used to indicate the driving pattern variations in percentage. The validity of the proposed method was evaluated using the jerk profile, where a high correlation was found between the classification results and jerk distributions. Moreover, a positive relation between fuel consumption and driving aggressivity was also confirmed. Furthermore, it was found that weather condition, time of the day and ultimately, the driver's eagerness, can cause significant variations in driving style.

KW - Driving style classification

KW - Fuel consumption

KW - Principal component analysis

KW - Support vector clustering

UR - http://www.scopus.com/inward/record.url?scp=85049672454&partnerID=8YFLogxK

U2 - 10.1109/ICITE.2018.8492700

DO - 10.1109/ICITE.2018.8492700

M3 - Conference contribution

T3 - 2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018

SP - 264

EP - 268

BT - 2018 3rd IEEE International Conference on Intelligent Transportation Engineering, ICITE 2018

PB - IEEE

ER -