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