Monitoring of human activities using a trainable system based on Hidden Markov modelling technology

In order to facilitate proper interpretation of long measurements involving large data sets a novel data classifier was implemented and tested. The method is based on Hidden Markov modelling technique, the basic tool in speech recognition. Tests performed used motion data and yielded a activity recognition score of up to 95.5 ± 1.9% on a set of 8 different human activities.

[1]  Dimitris N. Metaxas,et al.  Parallel hidden Markov models for American sign language recognition , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.