%0 Journal Article
%T Modeling and prediction of human behavior
%J Neural computation
%D 1999
%A Liu, Aizhong
%A Pentland, A.
%V 11
%N 1
%P 229-242
%X We propose that many human behaviors can be accurately described as a set of dynamic modes (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.<p /> <p>Language: en</p>
%G en
%I MIT Press
%@ 0899-7667
%U http://dx.doi.org/