Surprise Detection in Multivariate Astronomical Data
Astronomers systematically study the sky with large sky surveys. A common feature of modern sky surveys is that they produce hundreds of terabytes (TB) up to 100 (or more) petabytes (PB) both in the image data archive and in the object catalogs. For example, the LSST will produce a 20–40 PB catalog database. Large sky surveys have enormous potential to enable countless astronomical discoveries. Such discoveries will span the full spectrum of statistics: from rare one-in-a-billion (or one-in-a-trillion) object types, to complete statistical and astrophysical specifications of many classes of objects (based upon millions of instances of each class). The growth in data volumes requires more effective knowledge discovery and extraction algorithms. Among these are algorithms for outlier (novelty/surprise/anomaly) detection. Outlier detection algorithms enable scientists to discover the most “interesting” scientific knowledge hidden within large and high-dimensional datasets: the “unknown unknowns”. Effective outlier detection is essential for rapid discovery of potentially interesting and/or hazardous events. Emerging unexpected conditions in hardware, software, or network resources need to be detected, characterized, and analyzed as soon as possible for obvious system health and safety reasons, just as emerging behaviors and variations in scientific targets should be similarly detected and characterized promptly in order to enable rapid decision support in response to such events. We have developed a new algorithm for outlier detection (KNN-DD: K-Nearest Neighbor Data Distributions). We have derived results from preliminary experiments in terms of the algorithm’s precision and recall for known outliers, and in terms of its ability to distinguish between characteristically different data distributions among different classes of objects.
KeywordsData Stream Outlier Detection Elliptical Galaxy Fundamental Plane Distance Distribution Function
This research is supported in part by NASA AISR grant number NNX07AV70G and in part by NASA through the American Astronomical Society’s Small Research Grant Program.
- 1.M. J. Bayarri and J. O. Berger. Measures of Surprise in Bayesian Analysis. Downloaded from http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.6365, 1997.
- 2.M. J. Bayarri and J. O. Berger. Quantifying Surprise in the Data and Model Verification. Downloaded from http://citeseer.ist.psu.edu/old/401333.html, 1998.
- 3.B. Berriman, D. Kirkpatrick, R. Hanisch, A. Szalay, and R. Williams. Discovery of Brown Dwarfs with Virtual Observatories. IAU Joint Discussion 8: Large Telescopes and Virtual Observatory: Visions for the Future. http://adsabs.harvard.edu/abs/2003IAUJD...8E..60B
- 4.K. Borne. Scientific Data Mining in Astronomy. Next Generation Data Mining. CRC Press: Taylor & Francis, Boca Raton, FL, pp. 91–114, 2009.Google Scholar
- 5.K. Borne. Effective Outlier Detection using K-Nearest Neighbor Data Distributions: Unsupervised Exploratory Mining of Non-Stationarity in Data Streams. Submitted to the Machine Learning Journal, March 2010.Google Scholar
- 7.K. Das, K. Bhaduri, S. Arora, W. Griffin, K. Borne, C. Giannella, and H. Kargupta. Scalable Distributed Change Detection from Astronomy Data Streams using Eigen-Monitoring Algorithms. 2009 SIAM International Conference on Data Mining (SDM09), 2009.Google Scholar
- 10.P. Dhaliwal, M. Bhatia, and P. Bansal, P. A Cluster-based Approach for Outlier Detection in Dynamic Data Streams (KORM: K-median OutlieR Miner). Journal of Computing, vol. 2, pp. 74–80, 2010.Google Scholar
- 12.A. Dressler, D. Lynden-Bell, D. Burstein, R. L. Davies, S. M. Faber, R. Terlevich, and G. Wegner. Spectroscopy and Photometry of Elliptical Galaxies. I - A New Distance Estimator. Astrophysical Journal, vol. 313, pp. 42–58, 1987.Google Scholar
- 13.H. Dutta. Empowering Scientific Discovery by Distributed Data Mining on the Grid Infrastructure. Ph.D. dissertation, UMBC, 2007.Google Scholar
- 14.H. Dutta, C. Giannella, K. Borne, and H. Kargupta. Distributed Top-K Outlier Detection from Astronomy Catalogs using the DEMAC System. 2007 SIAM International Conference on Data Mining, 2007.Google Scholar
- 15.H. Dutta, C. Giannella, K. Borne, H. Kargupta, and R. Wolff. Distributed Data Mining for Astronomy Catalogs. IEEE Transactions in Knowledge and Data Engineering, 2009.Google Scholar
- 17.A. Freitas On Objective Measures of Rule Surprisingness. LNCC, 1510, pp. 1–9, 1998.Google Scholar
- 18.V. Hautamaki, I. Karkkainen, and P. Franti. Outlier Detection Using k-Nearest Neighbour Graph. Proceedings of the 17th International Conference on Pattern Recognition (ICPR’04), 2004.Google Scholar
- 19.C. R. Johnson, M. Glatter, W. Kendall, J. Huang, and F. Hoffman. Querying for Feature Extraction and Visualization in Climate Modeling. ICCS 2009, Part II, LNCS 5545, pp. 416–425, 2009.Google Scholar
- 24.D. Pokrajac, A. Lazarevic, and L. Latecki, L. Incremental Local Outlier Detection for Data Streams. IEEE Symposium on Computational Intelligence and Data Mining (CIDM), 2007.Google Scholar
- 30.P. Smyth and R. M. Goodman. Rule Induction Using Information Theory. Knowledge Discovery in Databases, pp 159–176, AAAI/MIT Press, 1991.Google Scholar
- 31.S. Srinoy and W. Kurutach. Anomaly Detection Model Based on Bio-Inspired Algorithm and Independent Component Analysis. TENCON 2006, IEEE Region 10 Conference proceedings, pp. 1–4, 2006.Google Scholar
- 32.Weaver’s Surprise Index. Encyclopedia of Statistical Sciences (Wiley), vol. 9, pp. 104–109, 1988.Google Scholar
- 33.N. Zakamska, et al. Candidate Type II Quasars from the Sloan Digital Sky Survey. I. Selection and Optical Properties. Astronomical Journal, vol. 126, pp. 2125–2143, 2003.Google Scholar