Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Data Augmentation of IMU Signals and Evaluation via a Semi-Supervised Classification of Driving Behavior

Jaafer, Amani ; Nilsson, Gustav and Como, Giacomo LU (2020) 23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020 In 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
Abstract

Over the past years, interest in classifying drivers' behavior from data has surged. Such interest is particularly relevant for car insurance companies who, due to privacy constraints, often only have access to data from Inertial Measurement Units (IMU) or similar. In this paper, we present a semi-supervised learning solution to classify portions of trips according to whether drivers are driving aggressively or normally based on such IMU data. Since the amount of labeled IMU data is limited and costly to generate, we utilize Recurrent Conditional Generative Adversarial Networks (RCGAN) to generate more labeled data. Our results show that, by utilizing RCGAN-generated labeled data, the classification of the drivers is improved in 79% of... (More)

Over the past years, interest in classifying drivers' behavior from data has surged. Such interest is particularly relevant for car insurance companies who, due to privacy constraints, often only have access to data from Inertial Measurement Units (IMU) or similar. In this paper, we present a semi-supervised learning solution to classify portions of trips according to whether drivers are driving aggressively or normally based on such IMU data. Since the amount of labeled IMU data is limited and costly to generate, we utilize Recurrent Conditional Generative Adversarial Networks (RCGAN) to generate more labeled data. Our results show that, by utilizing RCGAN-generated labeled data, the classification of the drivers is improved in 79% of the cases, compared to when the drivers are classified with no generated data.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
data evaluation, data generation, driving behaviors, IMU sensor
host publication
2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
series title
2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
article number
9294496
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020
conference location
Rhodes, Greece
conference dates
2020-09-20 - 2020-09-23
external identifiers
  • scopus:85099661398
ISBN
9781728141497
DOI
10.1109/ITSC45102.2020.9294496
language
English
LU publication?
yes
id
9c6f4c12-bec9-4318-8785-0fc4f2594372
date added to LUP
2021-02-05 09:15:45
date last changed
2022-04-27 00:01:22
@inproceedings{9c6f4c12-bec9-4318-8785-0fc4f2594372,
  abstract     = {{<p>Over the past years, interest in classifying drivers' behavior from data has surged. Such interest is particularly relevant for car insurance companies who, due to privacy constraints, often only have access to data from Inertial Measurement Units (IMU) or similar. In this paper, we present a semi-supervised learning solution to classify portions of trips according to whether drivers are driving aggressively or normally based on such IMU data. Since the amount of labeled IMU data is limited and costly to generate, we utilize Recurrent Conditional Generative Adversarial Networks (RCGAN) to generate more labeled data. Our results show that, by utilizing RCGAN-generated labeled data, the classification of the drivers is improved in 79% of the cases, compared to when the drivers are classified with no generated data.</p>}},
  author       = {{Jaafer, Amani and Nilsson, Gustav and Como, Giacomo}},
  booktitle    = {{2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020}},
  isbn         = {{9781728141497}},
  keywords     = {{data evaluation; data generation; driving behaviors; IMU sensor}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020}},
  title        = {{Data Augmentation of IMU Signals and Evaluation via a Semi-Supervised Classification of Driving Behavior}},
  url          = {{http://dx.doi.org/10.1109/ITSC45102.2020.9294496}},
  doi          = {{10.1109/ITSC45102.2020.9294496}},
  year         = {{2020}},
}