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. It is part of a research program aiming to replicate some humans' driving behaviors on chassis dynamometer using a robot driver. Moreover, it can potentially be used in developing more economical and personalized advanced driver assistance systems (ADAS) and humanized autonomous driving strategies. With the easily accessible on-board diagnostics (OBD) data on modern vehicles, both vehicle state and traffic information of three drivers were collected using an instrumented vehicle, which had external forward-looking radar and a monocular dashcam. For data processing, each trip data was first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis (PCA) on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering (SVC) 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.

LanguageEnglish
Pages344-350
Number of pages7
JournalInternational Journal of Machine Learning and Computing
Volume9
Issue number3
DOIs
StatusAccepted/In press - 1 Jun 2019

Keywords

  • Driving style analysis
  • Fuel consumption
  • Real-world driving data
  • Support vector clustering

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

@article{f14e2443166d4e2eb0329d62c34194a0,
title = "A support vector clustering based approach for driving style classification",
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. It is part of a research program aiming to replicate some humans' driving behaviors on chassis dynamometer using a robot driver. Moreover, it can potentially be used in developing more economical and personalized advanced driver assistance systems (ADAS) and humanized autonomous driving strategies. With the easily accessible on-board diagnostics (OBD) data on modern vehicles, both vehicle state and traffic information of three drivers were collected using an instrumented vehicle, which had external forward-looking radar and a monocular dashcam. For data processing, each trip data was first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis (PCA) on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering (SVC) 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 analysis, Fuel consumption, Real-world driving data, Support vector clustering",
author = "Yuxiang Feng and Simon Pickering and Edward Chappell and Pejman Iravani and Chris Brace",
year = "2019",
month = "6",
day = "1",
doi = "10.18178/ijmlc.2019.9.3.808",
language = "English",
volume = "9",
pages = "344--350",
journal = "International Journal of Machine Learning and Computing",
issn = "2010-3700",
publisher = "International Association of Computer Science & Information Technology",
number = "3",

}

TY - JOUR

T1 - A support vector clustering based approach for driving style classification

AU - Feng, Yuxiang

AU - Pickering, Simon

AU - Chappell, Edward

AU - Iravani, Pejman

AU - Brace, Chris

PY - 2019/6/1

Y1 - 2019/6/1

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. It is part of a research program aiming to replicate some humans' driving behaviors on chassis dynamometer using a robot driver. Moreover, it can potentially be used in developing more economical and personalized advanced driver assistance systems (ADAS) and humanized autonomous driving strategies. With the easily accessible on-board diagnostics (OBD) data on modern vehicles, both vehicle state and traffic information of three drivers were collected using an instrumented vehicle, which had external forward-looking radar and a monocular dashcam. For data processing, each trip data was first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis (PCA) on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering (SVC) 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. It is part of a research program aiming to replicate some humans' driving behaviors on chassis dynamometer using a robot driver. Moreover, it can potentially be used in developing more economical and personalized advanced driver assistance systems (ADAS) and humanized autonomous driving strategies. With the easily accessible on-board diagnostics (OBD) data on modern vehicles, both vehicle state and traffic information of three drivers were collected using an instrumented vehicle, which had external forward-looking radar and a monocular dashcam. For data processing, each trip data was first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis (PCA) on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering (SVC) 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 analysis

KW - Fuel consumption

KW - Real-world driving data

KW - Support vector clustering

UR - http://www.scopus.com/inward/record.url?scp=85067069664&partnerID=8YFLogxK

U2 - 10.18178/ijmlc.2019.9.3.808

DO - 10.18178/ijmlc.2019.9.3.808

M3 - Article

VL - 9

SP - 344

EP - 350

JO - International Journal of Machine Learning and Computing

T2 - International Journal of Machine Learning and Computing

JF - International Journal of Machine Learning and Computing

SN - 2010-3700

IS - 3

ER -