Missing values in user activity classification applications utilizing wireless sensors

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%.

[1]  C. Randell,et al.  Context awareness by analysing accelerometer data , 2000, Digest of Papers. Fourth International Symposium on Wearable Computers.

[2]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[3]  Ilkka Korhonen,et al.  Detection of Daily Activities and Sports With Wearable Sensors in Controlled and Uncontrolled Conditions , 2008, IEEE Transactions on Information Technology in Biomedicine.

[4]  James J. Little,et al.  A Boosted Particle Filter: Multitarget Detection and Tracking , 2004, ECCV.

[5]  Erkki Oja,et al.  Subspace methods of pattern recognition , 1983 .

[6]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[7]  Horst Bischof,et al.  A robust subspace classifier , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[8]  Jussi Collin,et al.  Investigations of self-contained sensors for personal navigation , 2006 .

[9]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[10]  Kenji Mase,et al.  Activity and Location Recognition Using Wearable Sensors , 2002, IEEE Pervasive Comput..

[11]  Johannes Peltola,et al.  Activity classification using realistic data from wearable sensors , 2006, IEEE Transactions on Information Technology in Biomedicine.

[12]  Albrecht Schmidt,et al.  Context-Aware telephony over WAP , 2000, Personal Technologies.

[13]  R. Suganya,et al.  Data Mining Concepts and Techniques , 2010 .