Improved estimation of starting times of human activities using Hidden Markov modeling based activity classification?

Wassink, R.G.V. and Baten, C.T.M. and Smeding, J.H. and Hermens, H.J. and Veltink, P.H. (2008) Improved estimation of starting times of human activities using Hidden Markov modeling based activity classification? In: International conference on ambulatory monitoring of physical activity and movement, conference book, 21-24 may 2008, Rotterdam.

Preview

PDF
33Kb

Abstract:	Automated classification of human activities should help the researcher, or the physician, with the interpretation of data. In a previous study a novel activity classifier based on Hidden Markov Models was successfully implemented and tested on ambulatory obtained of human activities. The estimated starting times were not accurate. Here the addition of timing information to perform isolated activity training as initialization of the HMM's is proposed to more accurately estimate the starting times of activities.
Item Type:	Conference or Workshop Item
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Biomedical Signals and Systems (BSS)
Link to this item:	http://purl.utwente.nl/publications/62427
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 251139