- Title
- Improving iForest with relative mass
- Creator
- Aryal, Sunil; Ting, Kaiming; Wells, Jonathan; Washio, Takashi
- Date
- 2014
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/160042
- Identifier
- vital:12082
- Identifier
-
https://doi.org/10.1007/978-3-319-06605-9_42
- Identifier
- ISBN:0302-9743
- Abstract
- iForest uses a collection of isolation trees to detect anomalies. While it is effective in detecting global anomalies, it fails to detect local anomalies in data sets having multiple clusters of normal instances because the local anomalies are masked by normal clusters of similar density and they become less susceptible to isolation. In this paper, we propose a very simple but effective solution to overcome this limitation by replacing the global ranking measure based on path length with a local ranking measure based on relative mass that takes local data distribution into consideration. We demonstrate the utility of relative mass by improving the task specific performance of iForest in anomaly detection and information retrieval tasks.
- Relation
- 18th Pacific-Asia Conference, PAKDD 2014: Advances in Knowledge Discovery and Data Mining; Tainan, Taiwan; 13th-16th May 2014; published in Lecture Notes in Artificial Intelligence (subseries of Lecture Notes in Computer Science) Vol. 8444, p. 510-521
- Rights
- Copyright © Springer International Publishing Switzerland 2014
- Rights
- This metadata is freely available under a CCO license
- Subject
- Anomaly Detection; Iforest; Refeat; Relative Mass
- Reviewed
- Hits: 1100
- Visitors: 1058
- Downloads: 1
Thumbnail | File | Description | Size | Format |
---|