• Submit to Sensors Login Register
• MDPI
• Journals A-Z
• For Authors
• For Editors
• For Librarians
• About
• Open Access Policy

• Abstract
• Full-Text PDF [561 KB]
• Full-Text XML
• Article Versions Notes

• Article Statistics
• PubMed/Medline
• Google Scholar
• Order Reprints

• Cite this article
• Export to BibTeX
• Export to EndNote

• [+] on DOAJ
• Banos, O
• Damas, M
• Pomares, H
• Rojas, I
• [+] on Google Scholar
• Banos, O
• Damas, M
• Pomares, H
• Rojas, I
• [+] on PubMed
• Banos, O
• Damas, M
• Pomares, H
• Rojas, I

•  CiteULike
•  Facebook
•  Mendeley
•  Twitter
• More services

Open AccessThis article is

• freely available
• re-usable

Sensors 2012, 12(6), 8039-8054; doi:10.3390/s120608039

Article

On the Use of Sensor Fusion to Reduce the Impact of Rotational and Additive Noise in Human Activity Recognition

Oresti Banos * , Miguel Damas, Hector Pomares and Ignacio Rojas

Department of Computer Architecture and Computer Technology, University of Granada, C/ Periodista Daniel Saucedo Aranda s/n, Granada E18071, Spain

* Author to whom correspondence should be addressed.

Received: 19 March 2012; in revised form: 5 June 2012 / Accepted: 6 June 2012 / Published: 11 June 2012

(This article belongs to the Special Issue Select papers from UCAmI 2011 - the 5th International Symposium on Ubiquitous Computing and Ambient Intelligence (UCAmI'11))

Download PDF Full-Text [561 KB, uploaded 11 June 2012 09:06 CEST]

Abstract: The main objective of fusion mechanisms is to increase the individual reliability of the systems through the use of the collectivity knowledge. Moreover, fusion models are also intended to guarantee a certain level of robustness. This is particularly required for problems such as human activity recognition where runtime changes in the sensor setup seriously disturb the reliability of the initial deployed systems. For commonly used recognition systems based on inertial sensors, these changes are primarily characterized as sensor rotations, displacements or faults related to the batteries or calibration. In this work we show the robustness capabilities of a sensor-weighted fusion model when dealing with such disturbances under different circumstances. Using the proposed method, up to 60% outperformance is obtained when a minority of the sensors are artificially rotated or degraded, independent of the level of disturbance (noise) imposed. These robustness capabilities also apply for any number of sensors affected by a low to moderate noise level. The presented fusion mechanism compensates the poor performance that otherwise would be obtained when just a single sensor is considered.

Keywords: activity recognition; rotational noise; additive noise; metaclassifier; accelerometer; sensor fusion

Article Statistics

Citations to this Article

Cite This Article