Abstract
For evaluating activity recognition results still classical error metrics like Accuracy, Precision, and Recall are being used. They are well understood and widely accepted but entail fundamental problems: They can not handle fuzzy event boundaries, or parallel activities, and they over-emphasize decision boundaries. We introduce more generic performance metrics as replacement, allowing for soft classification and annotation while being backward compatible. We argue that they can increase the expressiveness and still allow more sophisticated methods like event and segment analysis.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Minnen, D., Westeyn, T., Starner, T.: Performance metrics and evaluation issues for continuous activity recognition. In: Proceedings of Performance Metrics for Intelligent Systems (PerMis 2006), Gaithersburg, MD (2006)
Ward, J.A., Lukowicz, P., Gellersen, H.W.: Performance metrics for activity recognition. Transactions on Information Systems and Technology (TIST) 2(1) (2011)
van Rijsbergen, C.J.: Information retrieval, 2nd edn. Butterworths, London (1979)
Ward, J.A., Lukowicz, P., Tröster, G.: Evaluating performance in continuous context recognition using event-driven error characterisation. In: Hazas, M., Krumm, J., Strang, T. (eds.) LoCA 2006. LNCS, vol. 3987, pp. 239–255. Springer, Heidelberg (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hein, A., Kirste, T. (2011). Generic Performance Metrics for Continuous Activity Recognition. In: Bach, J., Edelkamp, S. (eds) KI 2011: Advances in Artificial Intelligence. KI 2011. Lecture Notes in Computer Science(), vol 7006. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24455-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-24455-1_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24454-4
Online ISBN: 978-3-642-24455-1
eBook Packages: Computer ScienceComputer Science (R0)