Journals
Publish with us
Publishing partnerships
About us
Blog
Computational Intelligence and Neuroscience
Journal overview
For authors
For reviewers
For editors
Table of Contents
Special Issues
Computational Intelligence and Neuroscience
/
2011
/
Article
/
Tab 4
/
Research Article
Accelerometry-Based Classification of Human Activities Using Markov Modeling
Table 4
Classification accuracy averaged over the seven subjects available in the
sit-stand-walk
dataset. The values are reported as mean ± standard deviation.
Sit-stand-walk dataset
M
= 1
M
= 2
M
= 3
M
= 4
M
= 5
Without rejection of spurious data
GMM
94.1 ± 1.8
93.7 ± 4.1
94.8 ± 2.4
95.5 ± 1.9
95.8 ± 2.1
HMM (1st level)
95.2 ± 7.0
96.8 ± 3.0
98.5 ± 1.0
98.3 ± 1.1
98.1 ± 1.1
HMM (1st + 2nd level)
95.2 ± 7.0
97.4 ± 2.9
97.9 ± 2.4
97.0 ± 2.9
98.5 ± 1.0
With rejection of spurious data
GMM
94.0 ± 1.8
95.6 ± 1.5
95.8 ± 2.3
95.6 ± 1.7
95.6 ± 1.5
HMM (1st level)
99.0 ± 1.0
98.6 ± 1.0
98.8 ± 1.0
98.8 ± 1.1
98.6 ± 1.1
HMM (1st + 2nd level)
99.0 ± 1.0
98.8 ± 1.0
98.8 ± 1.0
98.7 ± 1.1
98.7 ± 1.0