UNSUPERVISED DISTANCE-BASED OUTLIER DETECTION IN HIGH DIMENSIONAL DATA

N. Srujana, G. Srinivasa Rao, Dr. M. V. Sivaprasad

Abstract


The attention in anomaly is difficult since they include important and actionable data in lots of domains, for example invasion and recognition of fraud furthermore to medical diagnosis. It had been in recent occasions observed that distribution of point reverse-neighbour counts become skewed in high dimensions that results within phenomenon referred to as hubness. We offer a unifying vision of role concerning reverse nearest neighbour counts within problems strongly related not viewed anomaly recognition, and concentrate on high dimensionality effects on not viewed anomaly-recognition techniques in addition to hubness phenomenon. The feel of anti-hubs happens because high dimensionality when neighbourhood dimension is small in comparison with data size. These anti-hubs occurrence is strongly associated with anomaly in high-dimensional furthermore to low dimensional data.

 


Keywords


Anomaly; Hubness; High-Dimensional; Unsupervised; Nearest Neighbour; Anomaly-Detection; Anti-Hubs;

References


E. Achtert, S. Goldhofer, H.-P. Kriegel, E. Schubert, and A. Zimek, “Evaluation of clusterings—metrics and visual support,” in Proc. 28th Int. Conf. Data Eng., 2012, pp. 1285–1288.

E. M€uller, M. Schiffer, and T. Seidl, “Statistical selection of relevant subspace projections for outlier ranking,” in Proc. 27th IEEE Int. Conf. Data Eng., 2011, pp. 434–445.

Y. Tao, M. L. Yiu, and N. Mamoulis, “Reverse nearest neighbour search in metric spaces,” IEEE Trans. Knowl. Data Eng., vol. 18, no. 9, pp. 1239–1252, Sep. 2006.

C. Lijun, L. Xiyin, Z. Tiejun, Z. Zhongping, and L. Aiyong, “A data stream outlier delection algorithm based on reverse k nearest neighbors,” in Proc. 3rd Int. Symp. Comput. Intell. Des., 2010, pp. 236–239.

W. Jin, A. K. H. Tung, J. Han, and W. Wang, “Ranking outliers using symmetric neighborhood relationship,” in Proc 10th Pacific- Asia Conf. Adv. Knowl. Discovery Data Mining, 2006, pp. 577–593.

M. Breunig, H.-P. Kriegel, R. Ng, and J. Sander, “LOF: Identifying density-based local outliers,” in Proc. ACM Int. Conf. Manage. Data, 2000, pp. 93–104.


Full Text: PDF

Refbacks

  • There are currently no refbacks.




Copyright © 2012 - 2018, All rights reserved.| ijitr.com

Creative Commons License
International Journal of Innovative Technology and Research is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJITR , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.