ML Anthology

Modeling and Prediction of Human Behavior

Alex Pentland, Andrew Liu
NeCo 1999 pp. 229-242
doi:10.1162/089976699300016890 /neco/1999/pentland1999neco-modeling/

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.

NeCo Semantic Scholar

Cite

Text

Pentland and Liu. "Modeling and Prediction of Human Behavior." Neural Computation, 1999. doi:10.1162/089976699300016890

Markdown

[Pentland and Liu. "Modeling and Prediction of Human Behavior." Neural Computation, 1999.](https://mlanthology.org/neco/1999/pentland1999neco-modeling/) doi:10.1162/089976699300016890

BibTeX

@article{pentland1999neco-modeling,
  title     = {{Modeling and Prediction of Human Behavior}},
  author    = {Pentland, Alex and Liu, Andrew},
  journal   = {Neural Computation},
  year      = {1999},
  pages     = {229-242},
  doi       = {10.1162/089976699300016890},
  volume    = {11},
  url       = {https://mlanthology.org/neco/1999/pentland1999neco-modeling/}
}