@inproceedings{0d9514dca4e14246808d5ea4c87d4277,
title = "Online anomaly detection using random forest",
abstract = "In this paper, we focus on how to use random forests based methods to improve the anomaly detection rate for streaming datasets. The key concept in a current work [12] is to build a random forest where in any tree, at any internal node, a feature is randomly selected and the associated data space is partitioned in half. However, the model parameters were pre-defined and the efficiency on applying this model for various conditions is not discussed. In this paper, we first give mathematical justification of required tree height and number of trees by casting the problem as a classical coupon collector problem. Then we design a majority voting score combination strategy to combine the results from different anomaly detection trees. Finally, we apply feature clustering to group the correlated features together in order to find the anomalies jointly determined by subsets of features.",
author = "Zhiruo Zhao and Mehrotra, {Kishan G.} and Mohan, {Chilukuri K.}",
note = "Publisher Copyright: {\textcopyright} 2018, Springer International Publishing AG, part of Springer Nature.; 31st International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems IEA/AIE 2018 ; Conference date: 25-06-2018 Through 28-06-2018",
year = "2018",
doi = "10.1007/978-3-319-92058-0_13",
language = "English (US)",
isbn = "9783319920573",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "135--147",
editor = "{Ait Mohamed}, Otmane and Malek Mouhoub and Samira Sadaoui and Moonis Ali",
booktitle = "Recent Trends and Future Technology in Applied Intelligence - 31st International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2018, Proceedings",
}