Neural Computation
January 1, 1999, Vol. 11, No. 1, Pages 229-242
(doi: 10.1162/089976699300016890)
Modeling and Prediction of Human Behavior
Article PDF (95.57 KB)
Abstract
We propose that many human behaviors can be accurately described as a set of dynamic models (e.g., Kalman filters) sequenced together by a Markov chain. We then use these dynamic Markov models to recognize human behaviors from sensory data and to predict human behaviors over a few seconds time. To test the power of this modeling approach, we report an experiment in which we were able to achieve 95% accuracy at predicting automobile drivers' subsequent actions from their initial preparatory movements.