Real time recognition of human activities from wearable sensors by evolving classifiers

A new approach to real-time human activity recognition (HAR) using evolving self-learning fuzzy rule-based classifier (eClass) will be described in this paper. A recursive version of the principle component analysis (PCA) and linear discriminant analysis (LDA) pre-processing methods is coupled with...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011) pp. 2786 - 2793
Main Authors Andreu, Javier, Baruah, Rashmi Dutta, Angelov, Plamen
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2011
Subjects
Acceleration
Accelerometers
evolving systems
fuzzy rule-based classifiers
human activity recognition
Humans
Principal component analysis
Real time systems
Wearable sensors
Online AccessGet full text
ISBN9781424473151
1424473152
ISSN1098-7584
DOI10.1109/FUZZY.2011.6007595

Cover

More Information
Summary:A new approach to real-time human activity recognition (HAR) using evolving self-learning fuzzy rule-based classifier (eClass) will be described in this paper. A recursive version of the principle component analysis (PCA) and linear discriminant analysis (LDA) pre-processing methods is coupled with the eClass leading to a new approach for HAR which does not require computation and time consuming pre-training and data from many subjects. The proposed new method for evolving HAR (eHAR) takes into account the specifics of each user and possible evolution in time of her/his habits. Data streams from several wearable devices which make possible to develop a pervasive intelligence enabling them to personalize/tune to the specific user were used for the experimental part of the paper.
ISBN:9781424473151
1424473152
ISSN:1098-7584
DOI:10.1109/FUZZY.2011.6007595