Abstract
Density-based methodology that exploits k-neighborhood of a data point has many good features. For instance, it is independent of the distribution of the data and is capable of detecting isolated objects. However it has some shortcomings:
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
In this illustration, LOF suffers the same deficiency when k is 6, 7, or 8. For example, LOF assigns outlierness value 1.5122 to ‘B’ and 1.1477 to ‘A’, and it fails to identify ‘A’ as the most significant outlier.
References
H. Huang, K. Mehrotra, C.K. Mohan, “Rank-based outlier detection.” J. Stat. Comput. Simul. 82, 1–14 (2011)
Y. Tao, D. Pi, “Unifying density-based clustering and outlier detection,” in 2009 Second International Workshop on Knowledge Discovery and Data Mining, Paris, France, pp. 644–647, 2009
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Mehrotra, K.G., Mohan, C.K., Huang, H. (2017). Rank Based Approaches. In: Anomaly Detection Principles and Algorithms. Terrorism, Security, and Computation. Springer, Cham. https://doi.org/10.1007/978-3-319-67526-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-67526-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67524-4
Online ISBN: 978-3-319-67526-8
eBook Packages: Computer ScienceComputer Science (R0)