ABSTRACT
There have been clear needs to address the impact of driver emotions such as anger and happiness on aggressive or distracted driving behaviors. To tackle this issue, we have developed an affect detection system for identifying a driver's emotional arousal, including the driver's physiological data and vehicle's kinematic data. Multimodal sensors are wirelessly connected to a smartphone and then, all the driver and driving data are displayed on our Android application in real-time. With the benefits of this multimodal, portable, non-intrusive, and cost-efficient system, subsequent experiments were designed to test and improve the system. After identifying significant features, various machine learning algorithms will be used to model a driver's emotional states. Our final goal is to develop an optimized classifier of specific emotional states including arousal and valence. We hope that we can spark lively discussions on driver emotions at AutoUI and use the feedback to improve our system.
- American Automobile Association, 2009. Aggressive driving: Research update. American Automobile Association Foundtion for Traffic Safety. https://aaafoundation.org/sites/default/files/AggressiveDrivingResearchUpdate2009.pdfGoogle Scholar
- B&B Electronics, 2013, OBD-II Background. http://www.obdii.com/background.htmlGoogle Scholar
- Bradley, M.M. and Lang, P.J., 1994. Measuring emotion: the self-assessment manikin and the semantic differential. Journal of behavior therapy and experimental psychiatry, 25(1), pp. 49--59.Google ScholarCross Ref
- Jeon, M., 2017. Emotions in Driving. In Emotions and Affect in Human Factors and Human-Computer Interaction (pp. 437--474).Google Scholar
- Johnson, D.A. and Trivedi, M.M., 2011, October. Driving style recognition using a smartphone as a sensor platform. In Intelligent Transportation Systems (ITSC), 2011 14th International IEEE Conference on (pp. 1609--1615). IEEE.Google Scholar
- Leng, H., Lin, Y. and Zanzi, L.A., 2007, July. An experimental study on physiological parameters toward driver emotion recognition. In International Conference on Ergonomics and Health Aspects of Work with Computers (pp. 237--246). Springer, Berlin, Heidelberg. Google ScholarDigital Library
- De Nadai, S., D'Incà, M., Parodi, F., Benza, M., Trotta, A., Zero, E., Zero, L. and Sacile, R., 2016, June. Enhancing safety of transport by road by online monitoring of driver emotions. In System of Systems Engineering Conference (SoSE), 2016 11th (pp. 1--4). IEEE.Google Scholar
- Oehl, M., Siebert, F.W., Tews, T.K., Höger, R. and Pfister, H.R., 2011, July. Improving human-machine interaction--a non invasive approach to detect emotions in car drivers. In International Conference on Human-Computer Interaction (pp. 577--585). Springer, Berlin, Heidelberg. Google ScholarDigital Library
- OpenXC, Overview - OpenXC, (2018). http://openxcplatform.com/overview/index.htmlGoogle Scholar
- Pauzié, A., 2008. A method to assess the driver mental workload: The driving activity load index (DALI). IET Intelligent Transport Systems, 2(4), pp. 315--322.Google ScholarCross Ref
- Royal, D., 2004. National survey of speeding and unsafe driving attitudes and behaviors: 2002. United States. National Highway Traffic Safety Administration. https://www.nhtsa.gov/people/injury/drowsy_driving1/speed_volII_finding/SpeedVolumeIIFindingsFinal.pdfGoogle Scholar
- Russell, J.A., Lewicka, M. and Niit, T., 1989. A cross-cultural study of a circumplex model of affect. Journal of personality and social psychology, 57(5), p.848.Google ScholarCross Ref
Index Terms
- In-Vehicle Affect Detection System: Identification of Emotional Arousal by Monitoring the Driver and Driving Style
Recommendations
Automatic detection of learner's affect from conversational cues
We explored the reliability of detecting a learner's affect from conversational features extracted from interactions with AutoTutor, an intelligent tutoring system (ITS) that helps students learn by holding a conversation in natural language. Training ...
Broadening the Scope of Affect Detection Research
I propose to broaden the scope of affect detection research in three related directions. First, the task definition should be broadened from the detection of affects to the inference of mental states. Second, the detection process should be ...
Toward an Affect-Sensitive AutoTutor
Emotions (affective states) are inextricably bound to the learning process, as are cognition, motivation, discourse, action, and the environment. Augmenting an intelligent tutoring system with the ability to incorporate such states into its pedagogical ...
Comments