ORIGINAL RESEARCH article
Front. Comput. Sci.
Sec. Human-Media Interaction
Volume 7 - 2025 | doi: 10.3389/fcomp.2025.1639505
This article is part of the Research TopicAdvancements in Psychophysiological User Modeling for Real-Time Adaptable Systems: Response-Adaptive Procedures and MethodsView all articles
Discomfort detection during automated driving using Temporal Transformers
Provisionally accepted
- 1Artificial Intelligence, Computer Science, Chemnitz University of Technology, Chemnitz, Germany
- 2Fraunhofer-Institut fur Werkzeugmaschinen und Umformtechnik IWU, Chemnitz, Germany
- 3eOdyn, Brest, France
- 4Materials and Surface Engineering Group, Chemnitz University of Technology, Chemnitz, Germany
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
With the recent breakthroughs in driving automation and the development of smart vehicles, human-technology interaction issues, such as detecting comfort levels in automated driving, have been gaining increasing attention. We assessed a passenger's discomfort level in a smart, automated vehicle using physiological, environmental, and vehicle automation features from different sensors. Given the evidence of discomfort levels being an evolving psychological state in time, the tracking of discomfort levels for passengers of an automated vehicle can be considered a time-varying phenomenon. Our approach is to dynamically predict discomfort levels using time-dependent models, particularly the Temporal Fusion Transformer (TFT), an advanced attention-based deep learning architecture providing an interpretable explanation of temporal dynamics as well as high-performance forecasting over multiple horizons. The models are trained and evaluated using a dataset of 100 participants of a simulated automated driving experiment, during which they signaled their level of discomfort using a manual device. Two TFT models, TFT-full and TFT-restricted, are investigated depending on which physiological, environmental, and vehicle automation signals are used as inputs. The results are compared with the auto-regressive model DeepAR. Different window sizes are used to analyze the impact of the window size on the model's performance. Among the tested models, TFT-restricted with a window size of 300-time steps (about 5 seconds) demonstrates the best performance in predicting discomfort levels on our data, with a mean absolute error (MAE) of 0.037 and a root mean square error (RMSE) of 0.131.
Keywords: Discomfort detection, Temporal Fusion Transformer, Automated vehicle, human technology interaction, time series forecasting
Received: 02 Jun 2025; Accepted: 03 Sep 2025.
Copyright: © 2025 Assarzadeh, Hartwich, Vitay, Bocklisch and Hamker. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Maha Assarzadeh, Artificial Intelligence, Computer Science, Chemnitz University of Technology, Chemnitz, Germany
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.