Authors:
Inês Machado
1
;
Ricardo Gomes
1
;
Hugo Gamboa
2
and
Vítor Paixão
3
Affiliations:
1
FCT-UNL, Portugal
;
2
FCT-UNL and PLUX - Wireless Biosignals, Portugal
;
3
Champalimaud Foundation, Portugal
Keyword(s):
Physical Activity Recognition, Signal Processing, Feature Extraction, Feature Selection, Unsupervised
Learning.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
Devices
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Human-Computer Interaction
;
Informatics in Control, Automation and Robotics
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Real-Time Systems
;
Sensor Networks
;
Signal Processing, Sensors, Systems Modeling and Control
;
Soft Computing
;
Time and Frequency Response
;
Time-Frequency Analysis
;
Wearable Sensors and Systems
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.
(More)