Clustering of drivers’ state before takeover situations based on physiological features using unsupervised machine learning

de Salis, Emmanuel; Meteier, Quentin; Pelletier, Colin; Capallera, Marine; Angelini, Leonardo; Sonderegger, Andreas; Khaled, Omar Abou; Mugellini, Elena; Widmer, Marino; Carrino, Stefano (2021). Clustering of drivers’ state before takeover situations based on physiological features using unsupervised machine learning In: Tareq Ahram, Redha Taiar (ed.) Human Interaction, Emerging Technologies and Future Systems V. Lecture Notes in Networks and Systems: Vol. 319 (pp. 550-555). Cham: Springer 10.1007/978-3-030-85540-6_69

[img] Text
de_Salis_clustering of drivers state.pdf - Accepted Version
Restricted to registered users only until 1 October 2022.
Available under License Publisher holds Copyright.

Download (241kB) | Request a copy

Conditionally automated cars share the driving task with the driver. When the control switches from one to another, accidents can occur, especially when the car emits a takeover request (TOR) to warn the driver that they must take the control back immediately. The driver’s physiological state prior to the TOR may impact takeover performance and as such was extensively studied experimentally. However, little was done about using Machine Learning (ML) to cluster natural states of the driver. In this study, four unsupervised ML algorithms were trained and optimized using a dataset collected in a driving simulator. Their performances for generating clusters of physiological states prior to takeover were compared. Some algorithms provide interesting insights regarding the number of clusters, but most of the results were not statistically significant. As such, we advise researchers to focus on supervised ML using ground truth labels after experimental manipulation of drivers’ states.

Item Type:

Book Section (Book Chapter)

Division/Institute:

Business School > Institute for New Work
Business School > Institute for New Work > New Forms of Work and Organisation
Business School

Name:

de Salis, Emmanuel;
Meteier, Quentin;
Pelletier, Colin;
Capallera, Marine;
Angelini, Leonardo;
Sonderegger, Andreas0000-0003-0054-0544;
Khaled, Omar Abou;
Mugellini, Elena;
Widmer, Marino;
Carrino, Stefano and
Tareq Ahram, Redha Taiar

Subjects:

B Philosophy. Psychology. Religion > BF Psychology
Q Science > QA Mathematics > QA75 Electronic computers. Computer science

ISBN:

978-3-030-85539-0

Series:

Lecture Notes in Networks and Systems

Publisher:

Springer

Language:

English

Submitter:

Andreas Sonderegger

Date Deposited:

22 Feb 2022 14:35

Last Modified:

22 Feb 2022 14:35

Publisher DOI:

10.1007/978-3-030-85540-6_69

Additional Information:

Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021, August 27–29, 2021 and the 6th IHIET: Future Systems (IHIET-FS 2021), October 28–30, 2021, France

Uncontrolled Keywords:

Automated Vehicles · Clustering · Machine Learning · Physiological state · Takeover · TOR

ARBOR DOI:

10.24451/arbor.16644

URI:

https://arbor.bfh.ch/id/eprint/16644

Actions (login required)

View Item View Item
Provide Feedback