Design of a Speed Assistant to Minimize the Driver Stress

  • Víctor Corcoba Magaña
    University Carlos III vcorcoba[at]
  • Mario Muñoz Organero
    University Carlos III
  • Juan Antonio Álvarez-García
    University of Seville
  • Jorge Yago Fernández Rodríguez
    University of Seville


Stress is one of the most important factors in traffic accidents. When the driver is in this mental state, their skills and abilities are reduced. In this paper, we propose an algorithm to estimate the optimal speed to minimize stress levels on upcoming road segments when driving. The prediction model is based on deep learning. The stress level estimation considers the previous driver's driving behavior before reaching the road section to be assessed, the road state (weather and traffic), and the previous drives made by the driver. We use this algorithm to build a speed assistant. The solution provides an optimum average speed for each road segment that minimizes the stress. A validation experiment has been conducted in a real setting using two different types of vehicles. The proposal is able to predict the stress levels given the average speed by 84.20% on average. On the other hand, the speed assistant reduces the stress levels (estimated from the driver’s heart rate signal) and the aggressiveness of driving regardless of the vehicle type. The proposed solution is implemented on Android mobile devices and uses a heart rate chest strap.
  • Referencias
  • Cómo citar
  • Del mismo autor
  • Métricas
AAAFoundation, 2009. Aggressive driving: Research update. April 2009. Last access: October 2015. Available at

Biding T., and Lind G., 2002. Intelligent Speed Adaptation (ISA): Results of Large Scale Trials in Borlänge, Lidköping, Lund and Umeå during the Period 1999–2002. Publication 2002:89 E Swedish National Road Administration, Borlänge, Sweden (2002).

Carsten, O. M. J. and Tate, F. N., 2005) «Intelligent speed adaptation: accident savings and cost–benefit analysis,» Accident Anal. Prev., vol. 37, no. 3, pp. 407–416, May 2005.

Frank F., Carsten O., and Tate F., 2012. «How much benefit does Intelligent Speed Adaptation deliver: An analysis of its potential contribution to safety and environment». Accident Analysis & Prevention 48 (2012): 63-72.

González R. et al., 2014 «Modeling and detecting aggressiveness from driving signals». Intelligent Transportation Systems, IEEE Transactions on 15.4 (2014): 1419-1428.

Haworth, N., and Symmons M., 2001. «The relationship between fuel economy and safety outcomes,» Monash Univ., Melbourne, VIC, Australia, 2001.

Hill, J.D., and Boyle, L.N., 2007. Driver stress as influenced by driving maneuvers and road-way conditions. Transportation Research Part F: Traffic Psychology and Behaviour, 2007. 10(3): p. 177-186.

Kennedy, J., Eberhart R., 1995. «Particle swarm optimization. Neural Networks». Proceedings, IEEE International Conference on, vol.4, no., pp.1942, 1948 vol.4, Nov/Dec 1995. doi: 10.1109/ICNN.1995.488968.

Letty, A., and Van Schagen, I., 2006. «Driving speed and the risk of road crashes: A review». Accident Analysis & Prevention 38.2 (2006): 215-224. 5.

Liu, R., Tate, J., Boddy, R., 1999. Simulation Modelling on the Network Effects of EVSC. Deliverable 11.3 of External Vehicle Speed Control Project. Institute for Transport Studies, University of Leeds, UK.

Mimura, Y., Obayashi, F., Ono, T., Nakatani, S., Ando, R., Kozuka, K., & Ozawa, S., 2015. Effects of Intelligent Speed Adaptation on Elderly Drivers’ Driving Behaviors and Mental Workloads. International Journal of Intelligent Transportation Systems Research, 1-10.

Oei H. and Polak P., «Intelligent Speed Adaptation (ISA) and Road Safety», Journal of International Association of Traffic and Safety Sciences (IATSS) Research, Volume 26, No. 2, pp. 45–51, 2002.

Regan, M., Triggs, T., Young, K., Tomasevic, N., Mitsopoulos, E., Stephan, K., Tingvall, C., 2006. «On-road evaluation of intelligent speed adaptation, following distance warning and seat belt reminder systems: Final Results of the Australian TAC SafeVehicle Project».MUARC Report No. 253, Clayton.

Solovey, E. T., et al. «Classifying driver workload using physiological and driving performance data: Two field studies». Proceedings of the SIGCHI Conference on Hu-man Factors in Computing Systems. ACM, 2014. [x2]

Saad, F., and Malaterre, G., 1982. La Régulation de la Vitesse: Analyse des Aides au Contrôle de la Vitesse. Internal Report, ONSER, France.

Sun N et al., 2014. «Person/vehicle classification based on deep belief networks,» in Natural Computation (ICNC), 2014 10th Interna-tional Conference on , vol., no., pp.113–117, 19-21 Aug. 2014. doi: 10.1109/ICNC.2014.6975819.

UK Transport Department, 2014. Department for Transport. Reported road casualties in Great Britain: main results 2014
Corcoba Magaña, V., Muñoz Organero, M., Álvarez-García, J. A., & Fernández Rodríguez, J. Y. (2017). Design of a Speed Assistant to Minimize the Driver Stress. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 6(3), 45–56.


Download data is not yet available.