Unsupervised Distance-Based Anomaly disclosure in RNN
DOI:
https://doi.org/10.26438/ijcse/v6i3.439441Keywords:
High-Dimensional Data, Anomaly Detection, Reverse Nearest Neighbors (RNN), Distance ConcentrationAbstract
Anomaly discovery in high-dimensional information presents different difficulties coming about because of the "scourge of dimensionality." A common view is that separation fixation, i.e., the propensity of separations in high-dimensional information to wind up garbled, blocks the location of anomalies by making separation based strategies name all focuses as similarly great exceptions. In this paper, we give confirm supporting the conclusion that such a view is excessively straightforward, by exhibiting that separation based strategies can deliver all the more differentiating exception scores in high-dimensional settings. By assessing the great k-NN technique, the density-based local anomaly factor and impacted frameworks strategies, and anti-hub strategies with respect to different manufactured and genuine informational collections, we offer novel knowledge into the value of turn around neighbor checks in unsupervised exception recognition.
References
V.Chandola, et al, “Anomaly detection: A survey”, ACM /computSuro, vol 41,no. 3,p. 15,20090
A. Zimek, et al, “A survey on unsupervised outlier detection in high-dimensional numerical data,” Statist. Anal. Data Mining, vol. 5, no. 5, 2012
C. C. Aggarwal et al, “Outlier detection for high dimensional data,” in Proc. 27th ACM SIGMOD Int. Conf. Manage. Data, 2001,
Srinivasa Rao, “A Review on Multivariate Mutual Information”, University of Notre Dame, vol. 2, 2005
Shu Wu, et al, “Information-Theoretic Outlier Detection for Large-Scale Categorical Data”, IEEE Explorer vol. 25, No. 3.
Markus M. et al, “Institute for computer science. Department of Computer Science” University of British Columbia.
A. Hinneburg, et al, “On the surprising behavior of distance metrics in high dimensional spaces,” in Proc 8thIntConf on Database Theory (ICDT), 2001.
Jayshree S.Gosavi, http://www.rroij.com
Random key algorithm https://dzone.com/articles/random-number-generation-in-java
KNN-Algorithm http://www.saedsayad.com/k_nearest_neighbors.htm
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
