Missing values in user activity classification applications utilizing wireless sensors

Authors:
Ivan Avdouevski;Riitta Kerminen;Jarmo Makkonen;Ari Visa
Affiliations:
Tampere University of Technology, Tampere, Finland;Tampere University of Technology, Tampere, Finland;Tampere University of Technology, Tampere, Finland;Tampere University of Technology, Tampere, Finland
Venue:
Proceedings of the 6th ACM international symposium on Mobility management and wireless access
Year:
2008

Citing 8
Cited 0

Data mining: concepts and techniques

Data mining: concepts and techniques
Context-Aware Telephony Over WAP

Personal and Ubiquitous Computing
Activity and Location Recognition Using Wearable Sensors

IEEE Pervasive Computing
A Robust Subspace Classifier

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
Context Awareness by Analysing Accelerometer Data

Context Awareness by Analysing Accelerometer Data
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Activity classification using realistic data from wearable sensors

IEEE Transactions on Information Technology in Biomedicine
Detection of Daily Activities and Sports With Wearable Sensors in Controlled and Uncontrolled Conditions

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Wireless sensor networks offer a new and inexpensive way to gather data. Unfortunately, the short communication range together with distortions cause corruption in data transmission. In this paper a novel approach is proposed to deal with missing data due to transmission problems in wireless sensor networks for user activity classification. The proposed method was tested on data gathered by a sensor network consisting of two sensors and a GPS receiver. It was capable of performing classification with a 1% drop in accuracy when data from the more informative sensor was missing in 2-minute bursts. For 5-minute bursts of missing data, the drop in accuracy was 5%.