When monitoring sensory data (e.g., from a wearable device) the context oftentimes changes abruptly: people move from one situation (e.g., working quietly in their office) to another (e.g., being interrupted by one's manager). These context changes can be treated like concept shifts, since the underlying data generator (the concept) changes while moving from one context situation to another. We present an entropy based measure for data streams that is suitable to detect concept shifts in a reliable, noise-resistant, fast, and computationally efficient way. We assess the entropy measure under different concept shift conditions. To support our claims we illustrate the concept shift behavior of the stream entropy. We also present a simple algorithm control approach to show how useful and reliable the information obtained by the entropy measure is compared to a ensemble learner as well as an experimentally inferred upper limit. Our analysis is based on three large synthetic data sets representing real, virtual, and a combination of both concept drifts under different noise conditions (up to 50%). Last but not least, we demonstrate the usefulness of the entropy based measure context switch indication in a real world application in the context-awareness/wearable computing domain.
[1]
Ronald L. Rivest,et al.
Learning Time-Varying Concepts
,
1990,
NIPS.
[2]
Gerhard Widmer,et al.
Effective Learning in Dynamic Environments by Explicit Context Tracking
,
1993,
ECML.
[3]
Philip S. Yu,et al.
Mining concept-drifting data streams using ensemble classifiers
,
2003,
KDD '03.
[4]
Marcus A. Maloof,et al.
Dynamic weighted majority: a new ensemble method for tracking concept drift
,
2003,
Third IEEE International Conference on Data Mining.
[5]
Philip M. Long,et al.
Tracking drifting concepts by minimizing disagreements
,
2004,
Machine Learning.
[6]
Alexey Tsymbal,et al.
The problem of concept drift: definitions and related work
,
2004
.
[7]
Peter Vorburger,et al.
Entropy-based detection of real and virtual concept shifts
,
2006
.
[8]
Abraham Bernstein,et al.
A scenario-based approach for direct interruptability prediction on wearable devices
,
2007,
Int. J. Pervasive Comput. Commun..