Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks

Rafał Doniec; Justyna Konior; Szymon Sieciński; Artur Piet; Muhammad Tausif Irshad; Natalia Piaseczna; Md Abid Hasan; Frédéric Li; Muhammad Adeel Nisar; Marcin Grzegorzek

doi:10.3390/s23125551

Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks

Rafał Doniec^*, Justyna Konior^*, Szymon Sieciński, Artur Piet, Muhammad Tausif Irshad, Natalia Piaseczna, Md Abid Hasan, Frédéric Li, Muhammad Adeel Nisar, Marcin Grzegorzek

^*Corresponding author for this work

Institute of Medical Informatics

9 Citations (Scopus)

Abstract

To drive safely, the driver must be aware of the surroundings, pay attention to the road traffic, and be ready to adapt to new circumstances. Most studies on driving safety focus on detecting anomalies in driver behavior and monitoring cognitive capabilities in drivers. In our study, we proposed a classifier for basic activities in driving a car, based on a similar approach that could be applied to the recognition of basic activities in daily life, that is, using electrooculographic (EOG) signals and a one-dimensional convolutional neural network (1D CNN). Our classifier achieved an accuracy of 80% for the 16 primary and secondary activities. The accuracy related to activities in driving, including crossroad, parking, roundabout, and secondary activities, was 97.9%, 96.8%, 97.4%, and 99.5%, respectively. The F1 score for secondary driving actions (0.99) was higher than for primary driving activities (0.93–0.94). Furthermore, using the same algorithm, it was possible to distinguish four activities related to activities of daily life that were secondary activities when driving a car.

Translated title of the contribution	Sensorbasierte Klassifizierung von primären und sekundären Aktivitäten des Autofahrers mit Hilfe von faltenden neuronalen Netzwerken
Original language	English
Article number	5551
Journal	Sensors (Basel, Switzerland)
Volume	23
Issue number	12
Pages (from-to)	5551
Number of pages	1
ISSN	1424-8220
DOIs	https://doi.org/10.3390/s23125551
Publication status	Published - 13.06.2023

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure

Research Areas and Centers

Academic Focus: Biomedical Engineering
Academic Focus: Center for Brain, Behavior and Metabolism (CBBM)

Access to Document

10.3390/s23125551Licence: CC BY

https://www.mdpi.com/1424-8220/23/12/5551Licence: CC BY

Cite this

@article{74aa19ac6a974364b90963df24a0eb1e,

title = "Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks",

abstract = "To drive safely, the driver must be aware of the surroundings, pay attention to the road traffic, and be ready to adapt to new circumstances. Most studies on driving safety focus on detecting anomalies in driver behavior and monitoring cognitive capabilities in drivers. In our study, we proposed a classifier for basic activities in driving a car, based on a similar approach that could be applied to the recognition of basic activities in daily life, that is, using electrooculographic (EOG) signals and a one-dimensional convolutional neural network (1D CNN). Our classifier achieved an accuracy of 80\% for the 16 primary and secondary activities. The accuracy related to activities in driving, including crossroad, parking, roundabout, and secondary activities, was 97.9\%, 96.8\%, 97.4\%, and 99.5\%, respectively. The F1 score for secondary driving actions (0.99) was higher than for primary driving activities (0.93–0.94). Furthermore, using the same algorithm, it was possible to distinguish four activities related to activities of daily life that were secondary activities when driving a car.",

author = "Rafa{\l} Doniec and Justyna Konior and Szymon Sieci{\'n}ski and Artur Piet and Irshad, \{Muhammad Tausif\} and Natalia Piaseczna and Hasan, \{Md Abid\} and Fr{\'e}d{\'e}ric Li and Nisar, \{Muhammad Adeel\} and Marcin Grzegorzek",

note = "Doniec R, Konior J, Sieci{\'n}ski S, Piet A, Irshad MT, Piaseczna N, Hasan MA, Li F, Nisar MA, Grzegorzek M. Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks. Sensors. 2023; 23(12):5551. https://doi.org/10.3390/s23125551 Publisher Copyright: {\textcopyright} 2023 by the authors. Publisher Copyright: {\textcopyright} 2023 by the authors.",

year = "2023",

month = jun,

day = "13",

doi = "10.3390/s23125551",

language = "English",

volume = "23",

pages = "5551",

journal = "Sensors (Basel, Switzerland)",

issn = "1424-8220",

publisher = "MDPI",

number = "12",

}

TY - JOUR

T1 - Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks

AU - Doniec, Rafał

AU - Konior, Justyna

AU - Sieciński, Szymon

AU - Piet, Artur

AU - Irshad, Muhammad Tausif

AU - Piaseczna, Natalia

AU - Hasan, Md Abid

AU - Li, Frédéric

AU - Nisar, Muhammad Adeel

AU - Grzegorzek, Marcin

N1 - Doniec R, Konior J, Sieciński S, Piet A, Irshad MT, Piaseczna N, Hasan MA, Li F, Nisar MA, Grzegorzek M. Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks. Sensors. 2023; 23(12):5551. https://doi.org/10.3390/s23125551 Publisher Copyright: © 2023 by the authors. Publisher Copyright: © 2023 by the authors.

PY - 2023/6/13

Y1 - 2023/6/13

N2 - To drive safely, the driver must be aware of the surroundings, pay attention to the road traffic, and be ready to adapt to new circumstances. Most studies on driving safety focus on detecting anomalies in driver behavior and monitoring cognitive capabilities in drivers. In our study, we proposed a classifier for basic activities in driving a car, based on a similar approach that could be applied to the recognition of basic activities in daily life, that is, using electrooculographic (EOG) signals and a one-dimensional convolutional neural network (1D CNN). Our classifier achieved an accuracy of 80% for the 16 primary and secondary activities. The accuracy related to activities in driving, including crossroad, parking, roundabout, and secondary activities, was 97.9%, 96.8%, 97.4%, and 99.5%, respectively. The F1 score for secondary driving actions (0.99) was higher than for primary driving activities (0.93–0.94). Furthermore, using the same algorithm, it was possible to distinguish four activities related to activities of daily life that were secondary activities when driving a car.

AB - To drive safely, the driver must be aware of the surroundings, pay attention to the road traffic, and be ready to adapt to new circumstances. Most studies on driving safety focus on detecting anomalies in driver behavior and monitoring cognitive capabilities in drivers. In our study, we proposed a classifier for basic activities in driving a car, based on a similar approach that could be applied to the recognition of basic activities in daily life, that is, using electrooculographic (EOG) signals and a one-dimensional convolutional neural network (1D CNN). Our classifier achieved an accuracy of 80% for the 16 primary and secondary activities. The accuracy related to activities in driving, including crossroad, parking, roundabout, and secondary activities, was 97.9%, 96.8%, 97.4%, and 99.5%, respectively. The F1 score for secondary driving actions (0.99) was higher than for primary driving activities (0.93–0.94). Furthermore, using the same algorithm, it was possible to distinguish four activities related to activities of daily life that were secondary activities when driving a car.

UR - https://www.scopus.com/pages/publications/85163964111

UR - https://www.mendeley.com/catalogue/1c1f8652-30a2-3cf7-b146-24db110e4915/

U2 - 10.3390/s23125551

DO - 10.3390/s23125551

M3 - Journal articles

SN - 1424-8220

VL - 23

SP - 5551

JO - Sensors (Basel, Switzerland)

JF - Sensors (Basel, Switzerland)

IS - 12

M1 - 5551

ER -

Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks

Abstract

UN SDGs

Research Areas and Centers

Access to Document

Other files and links

Fingerprint

Cite this