DWOF: A Robust Density-Based Outlier Detection Approach
The problem of unsupervised outlier detection is challenging, especially when the structure of data is unknown. This paper presents a new density-based outlier detection technique that detects the top-n outliers. It overcomes the limitations of existing approaches, like low accuracy and high sensitivity to parameters. Our approach provides a score to each object called Dynamic-Window Outlier Factor (DWOF). DWOF improves Resolution-based Outlier Factor method (ROF) to consider varying-density clusters, which improves outliers’ ranking even when providing same outliers. Experiments show that DWOF’s average accuracy is better than existing approaches and less sensitive to its parameter.
KeywordsUnsupervised Outlier Detection Density-Based Outlier Factor Resolution-Based Outlier Factor
Unable to display preview. Download preview PDF.
- 4.Hawkins, D.M.: Identification of outliers, vol. 11. Chapman and Hall, London (1989)Google Scholar
- 7.Knorr, E.M., Ng, R.T.: Algorithms for mining distance-based outliers in large datasets. In: Proceedings of the International Conference on Very Large Data Bases, pp. 392–403. Citeseer (1998)Google Scholar
- 8.Tan, P.N., Steinbach, M., Kumar, V., et al.: Introduction to data mining. Pearson, Addison Wesley, Boston (2006)Google Scholar
- 9.Tukey, J.W.: Exploratory data analysis, Reading, MA (1977)Google Scholar
- 10.Yoursi, N.A.: A validity index for outlier detection. In: 2010 10th International Conference on Intelligent Systems Design and Applications (ISDA), pp. 325–329. IEEE (2010)Google Scholar
- 12.ELKI framework, http://elki.dbs.ifi.lmu.de/
- 13.Letter Recognition dataset in UCI repository, http://archive.ics.uci.edu/ml/datasets/Letter+Recognition