Abstract
There is a limit to the accuracy with which we can predict a person's state of alertness from their behaviour. Driver behaviour and alertness are, however, clearly related, and this should allow us to build a predictive model. For such a model to be of use it must be very general in its ability. Such generality is available at the expense of accuracy and a trade-off between overall error rate and quantity of usable predictions must consequently be made. This paper discusses a set of methods which were applied to the task of building a neural network based system for predicting driver alertness from steering behaviour. We show how an acceptable level of generality was achieved and how the trade-off between error rate and quantity of usable predictions was managed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Elman JL. Finding structure in time.Cognitive Sci. 1990; 14: 179–211
Williams RJ, Zipser D. A learning algorithm for continually running fully recurrent neural networks.Neural Computation, 1989; 1: 270–280
Swingler KM. Sequence categorisation using multiple recurrent layers to create many trajectories through network state space. In M Marinara and G Morasso (eds)Proc ICANN, vol 2 1994: 1025–1028. Springer-Verlag, Berlin, Germany
Waibel A. Modular construction of time delay neural networks for speech recognition.Neural Computation 1989; 1(1): 39–46
Refenes AN, Azema-Barac M. Neural network applications in financial asset management.J Neurocomputing Applic, 1994; 2(1): 13–39
Weigend AS, Huberman BA, Rummelhart DE. Predicting sunspots and exchange rates with connectionist networks. In: M Casdagli and S Eubank (eds),Nonlinear Modeling and Forecasting, SFI Studies in the Sciences of Complexity Proc. Vol. XII, 1992
Mozer MC. Neural net architectures for temporal sequence processing. In: AS Weigend and NA Gershenfeld (eds)Time Series Prediction. Forecasting the Future and Understanding the Past, 243–264. Addison-Wesley, Reading, MA, 1993
Tarrier C, Chaput D, Petit-Poilvert C. Research to prevent the driver from falling asleep behind the wheel.Peugeot SAIRenault France, Technical report 88055
Hecht-Neilson R.Neurocomputing. Addison-Wesley, Reading, MA, 1990
Upadhyaya BR, Eryurek E. Application of neural networks for sensor validation and plant monitoring.Neural Technology 1992; (97): 170–176
Baum EB, Haussler D. What net size gives valid generalisation?Neural Computation 1989; (1): 151–160
Hansen LK, Liisberg C, Salamon P. The error-reject tradeoff. Technical report, Technical University of Denmark, 1994
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Swingler, K., Smith, L.S. Producing a neural network for monitoring driver alertness from steering actions. Neural Comput & Applic 4, 96–104 (1996). https://doi.org/10.1007/BF01413745
Issue Date:
DOI: https://doi.org/10.1007/BF01413745