Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities

Inês Machado, Ricardo Gomes, Hugo Gamboa, Vítor Paixão

2014

Abstract

The demand for objectivity in clinical diagnosis has been one of the greatest challenges in Biomedical Engineering. The study, development and implementation of solutions that may serve as ground truth in physical activity recognition and in medical diagnosis of chronic motor diseases is ever more imperative. This paper describes a human activity recognition framework based on feature extraction and feature selection techniques where a set of time, statistical and frequency domain features taken from 3-dimensional accelerometer sensors are extracted. In this paper, unsupervised learning is applied to the feature representation of accelerometer data to discover the activities performed by different subjects. A feature selection framework is developed in order to improve the clustering accuracy and reduce computational costs. The features which best distinguish a particular set of activities are selected from a 180th- dimensional feature vector through machine learning algorithms. The implemented framework achieved very encouraging results in human activity recognition: an average person-dependent Adjusted Rand Index (ARI) of 99:29%0:5% and a person-independent ARI of 88:57%4:0% were reached.

Paper Citation

in Harvard Style

Machado I., Gomes R., Gamboa H. and Paixão V. (2014). Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2014) ISBN 978-989-758-011-6, pages 155-162. DOI: 10.5220/0004749801550162

in Bibtex Style

@conference{biosignals14,
author={Inês Machado and Ricardo Gomes and Hugo Gamboa and Vítor Paixão},
title={Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2014)},
year={2014},
pages={155-162},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004749801550162},
isbn={978-989-758-011-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2014)
TI - Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities
SN - 978-989-758-011-6
AU - Machado I.
AU - Gomes R.
AU - Gamboa H.
AU - Paixão V.
PY - 2014
SP - 155
EP - 162
DO - 10.5220/0004749801550162