Improved activity recognition via Kalman smoothing and multiclass linear discriminant analysis

Improving activity recognition, with special focus on fall-detection, is the subject of this study. We show that Kalman smoothed in-painting of missing pose information and task-specific dimensionality reduction of activity feature vectors leads to significantly improved activity classification perf...

Full description

Saved in:
Bibliographic Details
Published in2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society Vol. 2014; pp. 582 - 585
Main Authors Dhir, Neil, Wood, Frank
Format Conference Proceeding Journal Article
LanguageEnglish
Published United States IEEE 01.01.2014
Subjects
Acceleration
Accuracy
Algorithms
Data models
Discriminant Analysis
Humans
Kalman filters
Legged locomotion
Pattern Recognition, Automated
Smoothing methods
Time Factors
Vectors
Walking
Online AccessGet full text
ISSN1094-687X
1557-170X
DOI10.1109/EMBC.2014.6943658

Cover

More Information
Summary:Improving activity recognition, with special focus on fall-detection, is the subject of this study. We show that Kalman smoothed in-painting of missing pose information and task-specific dimensionality reduction of activity feature vectors leads to significantly improved activity classification performance. We illustrate our findings by applying common classification algorithms to dimensionally reduced feature vectors, and compare our accuracy to previous work. In part two we investigate our methods on a small subset of the data, in order to ascertain what accuracy performance is achievable with the smallest amount of information available.
ISSN:1094-687X
1557-170X
DOI:10.1109/EMBC.2014.6943658