Abstract
Driving a vehicle is a task affected by an increasing number and a rising complexity of Driver Assistance
Systems (DAS) resulting in a raised cognitive load of the driver, and in consequence to the distraction from the main activity of driving. A number of potential
solutions have been proposed so far, however, although these techniques broaden the perception horizon (e.g. the introduction of the sense of touch as additional
information modality or the utilization of multimodal instead of unimodal interfaces), they demand the attention of the driver too. In order to cope with the
issues of workload and/or distraction, it would be essential to find a non-distracting and noninvasive solution for the emergence of information. In this work we
have investigated the application of heart rate variability (HRV) analysis to electrocardiography (ECG) data for identifying driving situations of possible threat
by monitoring and recording the autonomic arousal states of the driver. For verification we have collected ECG and global positioning system (GPS) data in more
than 20 test journeys on two regularly driven routes during a period of two weeks. First results have shown that an indicated difference of the arousal state of
the driver for a dedicated point on a route, compared to its usual state, can be interpreted as a warning sign and used to notify the driver about this, perhaps
safety critical, change. To provide evidence for this hypothesis it would be essential to conduct a large number of journeys on different times of the day, using
different drivers and different roadways, in the next step.
Original language | English |
---|---|
Title of host publication | First International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2009), September 21-22, Essen, Germany |
Editors | ACM Digital Library |
Number of pages | 8 |
Publication status | Published - Sept 2009 |
Fields of science
- 102 Computer Sciences
- 102009 Computer simulation
- 102013 Human-computer interaction
- 102019 Machine learning
- 102020 Medical informatics
- 102021 Pervasive computing
- 102022 Software development
- 102025 Distributed systems
- 202017 Embedded systems
- 211902 Assistive technologies
- 211912 Product design