autonlab.org

Discovering Complex Anomalous Patterns

Research Project funded by the National Science Foundation under Grant NSF IIS-0911032

Project Description

Many of the most interesting and valuable discoveries that can be made from data arise not from the evaluation of single records, but from identifying a set of records that are anomalous in some interesting way. Together they may indicate for example the emergence of a disease outbreak or new patterns of criminal activity. One can view pattern discovery as an interactive process between data analysis algorithms and human users who have expertise in the domain. This research will develop an integrated framework of probabilistic methods to interact with the user in detecting, characterizing, explaining, and learning anomalous patterns over groups of records. The focus is on the many situations where the data (and the probabilistic patterns to be discovered) are not appropriate for using other existing techniques, such as graph mining or frequent sets. The proposed methods will search over arbitrary subsets of records and evaluate their correspondence to known, potentially very complex, probabilistic patterns, or their failure to match baseline data under various learned statistical models. These methods will assist the user in understanding and modeling the discovered, previously unknown anomalies to be identifiable as a known pattern when encountered in the future.

Project Summary

Project Page at NSF

Project Personnel

Faculty

Graduate Students

Research Staff

Journal Publications and Book Chapters Resulting from Project Activities

Dubrawski A. (2010). Detection of Events in Multiple Streams of Surveillance Data. In Infectious Disease Informatics and Biosurveillance, Eds. D. Zeng, H. Chen, C. Castillo-Chavez, W. Lober, and M. Thurmond. Springer-Verlag, 2010. In press.  http://www.springer.com/public+health/book/978-1-4419-6891-3

Dubrawski A, "The Role of Data Aggregation in Public Health and Food Safety Surveillance", (2010). Book chapter, Published Editor(s): T. Kass-Hout; X. Zhang Collection: Biosurveillance: Methods and Case Studies Bibliography: Taylor & Francis

Skyler Speakman, Sriram Somanchi, Edward McFowland III, and Daniel B. Neill, "Scalable detection of anomalous subgraphs", (2013). Book chapter, Accepted  Editor(s): R. Alhajj and J. Rokne Collection: Encyclopedia of Social Network Analysis and Mining

Edward McFowland III, Skyler Speakman, and Daniel B. Neill, "Scalable detection of anomalous patterns with connectivity constraints", IEEE Transactions on Knowledge and Data Engineering, p. , vol. , (2012). Submitted

Sverchkov Y, Jiang X, Cooper GF, "Spatial cluster detection using dynamic programming", BMC Medical Informatics & Decision Making, p. vol. 12, (2012). Published, 10.1186/1472-6947-12-22, http://www.biomedcentral.com/1472-6947/12/22/

Edward McFowland III, Skyler Speakman, and Daniel B. Neill, "Fast generalized subset scan for anomalous pattern detection", Journal of Machine Learning Research, p. , vol. , (2012). Submitted

Daniel B. Neill, Edward McFowland III, and Huanian Zheng, "Fast subset scan for multivariate event detection", Statistics in Medicine, p. , vol., (2012). Submitted

Wei W; Visweswaran S; Cooper GF, "The application of naive Bayes model averaging to predict Alzheimer's disease from genome-wide data", Journal of the American Medical Informatics Association, p. 370, vol. 18(4), (2011). Published

Shen Y; Cooper GF, "Multivariate Bayesian modeling of known and unknown causes of events - An application to biosurveillance", Journal of Computer Methods and Programs in Biomedicine, p. , vol. , (2010). Published, 10.1016/j.cmpb.2010.11.015

Fiterau M., Dubrawski A., Ye C., "Monitoring Vital Signs for Clinical Alarm Preemption", Emerging Health Threats Journal, p. , vol. , (2011),published

Lonkar, RD., Dubrawski, A., Fiterau, M., Garnett, R., "Mining Intensive Care Vitals for Leading Indicators of Adverse Health Events", Emerging Health Threats Journal, p. , vol. , (2011). Published

DB Neill; Y Liu, "Generalized fast subset sums for Bayesian detection and visualization", Emerging Health Threats Journal, p. 43, vol. 4,(2011). Published

DB Neill, E McFowland III, and H Zheng, "Fast subset scan for multivariate spatial biosurveillance", Emerging Health Threats Journal, p. 42,vol. 4, (2011). Published

Yandong Liu and Daniel B. Neill, "Detecting previously unseen outbreaks with novel symptom patterns", Emerging Health Threats Journal, p.11074, vol. , (2011). Published

Sriram Somanchi and Daniel B. Neill, "Fast graph structure learning from unlabeled data for outbreak detection", Emerging Health Threats Journal, p. 11017, vol. , (2011). Published

Gopalakrishnan V, Lustgarten J, Visweswaran S, Cooper GF. (2010). Bayesian rule learning for biomedical data mining. Bioinformatics 26:668-675, 2010.  http://bioinformatics.oxfordjournals.org/content/26/5/668.abstract

Neill, DB and Cooper, GF. (2010). A multivariate Bayesian scan statistic for early event detection and characterization. Machine Learning, p. 261, vol. 79, 2010.  http://www.cs.cmu.edu/~neill/papers/MBSS.pdf

Neill, DB., "Fast subset scan for spatial pattern detection", Journal of the Royal Statistical Society, Series B - Statistical Methodology, p. 3, vol. 74, (2011). Published, 10.1111/j.1467-9868.2011.01014, http://onlinelibrary.wiley.com/doi/10.1111/j.1467-9868.2011.01014.x/abstract

Neill, DB., "Fast Bayesian scan statistics for multivariate event detection and visualization", Statistics in Medicine, p. 45, vol. 30, (2011). Published,http://onlinelibrary.wiley.com/doi/10.1002/sim.3881/abstract

Oliveira, D., Neill, DB., Garrett JH. Jr, and Soibelman, L., "Detection of patterns in water distribution pipe breakage using spatial scan statistics for point events in a physical network", Computing in Civil Engineering, p. , vol. 25, (2011). Published,. http://scitation.aip.org/getabs/servlet/GetabsServlet?prog=normal&id=JCCEXX000001000001000048000001&idtype=cvips&gifs=yes&ref=no

Waidyanatha, N., Sampath, C., Dubrawski, A., Prashant, S., Ganesan, M., Gow, G. (2010b). Affordable system for rapid detection and mitigation of emerging diseases. International Journal on E-Health and Medical Communications. In press. http://www.irma-international.org/viewtitle/51622/

Weerasinghe, C., Waidyanatha, N., Dubrawski, A., Baysek, M., Ganesan M. (2010). T-Cube Web Tool for rapid detection of disease outbreaks in India and Sri Lanka. Sri Lankan Journal of Biomedical Informatics. In press. http://www.autonlab.org/autonweb/19958.html

Reviewed Conference Publications Resulting from Project Activities

Chen L., Dubrawski A., Dunham, A., Huckabee, M., Kelley L. (2009a) Using Network Diagrams in Support of Food Safety Investigations. Proceedings of the 2009 International Society for Disease Surveillance Annual Conference. Available online at www.syndromic.org.

Chen L., Dubrawski A., Sorokina, D. (2009b) Multivariate Analysis for Predicting Risk of Microbial Contamination of Food. Proceedings of the 2009 International Society for Disease Surveillance Annual Conference. Available online at www.syndromic.org.

Cooper GF, Hennings-Yeomans P, Visweswaran S, Barmada M. (2010) An efficient Bayesian method for predicting clinical outcomes from genome-wide data. Proceedings of the Fall Symposium of the American Medical Informatics Association (November, 2010).

Dubrawski A., Chen L., Sarkar P. (2009a) Efficient Visualization of Dynamic Networks in Food Safety Analysis. Proceedings of the 2009 International Society for Disease Surveillance Annual Conference. Available online at www.syndromic.org.

Dubrawski A., Sabhnani M., Fedorka-Cray P., Kelley L., Gerner-Smidt P., Williams I., Huckabee M., Dunham A. (2009c). Discovering Possible Linkages between Food-borne Illness and the Food Supply Using an Interactive Analysis Tool. Proceedings of the 2009 International Society for Disease Surveillance Annual Conference. Available online at www.syndromic.org.

Neill DB. (2009) Fast subset sums for multivariate Bayesian scan statistics, Proceedings of the 2009 International Society for Disease Surveillance Annual Conference.  Available online at www.syndromic.org.

Sabhnani M., Dubrawski A., Schneider J. (2009a) Detection of Disjunctive Anomalous Patterns in Multidimensional Data. Proceedings of the 2009 International Society for Disease Surveillance Annual Conference. Available online at www.syndromic.org.

Sabhnani M., Dubrawski A., Waidyanatha N. (2009b) T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka. Proceedings of the 2009 International Society for Disease Surveillance Annual Conference. Available online at www.syndromic.org.

Speakman, S. and Neill, DB. (2009). Fast graph scan for scalable detection of arbitrary connected clusters, Proceedings of the 2009 International Society for Disease Surveillance Annual Conference. Available online at www.syndromic.org.

Sverchkov Y, Cooper GF. (2010). Spatial cluster detection using two-dimensional dynamic programming. (submitted and currently under review by a conference).

Waidyanatha, N., Prashant, S., Ganesan, M., Dubrawski, A., Chen, L., Baysek, M., Careem, M., Damendra, P., Kaluarachchi, M. (2010a) Real-Time Biosurveillance Pilot in India and Sri Lanka, IEEE-Healthcom 2010, Lyon, France, July 2010.  http://lirneasia.net/wp-content/uploads/2009/11/Waidyanatha_eAsia2009_web_paper.pdf

Waidyanatha, N., Sampath, C., Dubrawski, A., Sabhnani, M., Chen, L., Ganesan, M., Vincy, P. (2010c) T-Cube Web Interface as a tool for detecting disease outbreaks in real-time: A pilot in India and Sri Lanka. IEEE-RIVF 2010 International Conference on Computing and Telecommunication Technologies, Hanoi, Vietnam, November 2010.

Xiong, L., Chen, X., Huang, T-K., Schneider, J. and Carbonell. J. (2010). Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization. Proceedings of SIAM Data Mining Conference (SDM), Columbus, OH, April 2010.  http://www.cs.cmu.edu/~xichen/images/Xi Chen SDM 2010.pdf

Zhang, Y., Schneider, J. and Dubrawski, A. (2010a) Learning Compressible Models. Proceedings of SIAM Data Mining Conference (SDM), Columbus, OH, April 2010.  http://www.ml.cmu.edu/current_students/DAP_zhang.pdf

Zhang, Y. and Schneider, J. (2010b). Projection Penalties: Dimension Reduction without Loss, International Conference on Machine Learning (ICML), Haifa, Israel, June 2010.  http://www.icml2010.org/papers/481.pdf

Waidyanatha, N., Sampath, C., Dubrawski, A., Sabhnani, M., Chen, L., Ganesan, M., Vincy, P., "T-Cube Web Interface as a tool for detecting disease outbreaks in real-time: A pilot in India and Sri Lanka", (2010). Conference proceedings, Published Collection: IEEE-RIVF 2010 International  Conference on Computing and Telecommunication Technologies Bibliography: Hanoi, Vietnam, November 2011, http://www.autonlab.org/autonweb/19958.html

S Somanchi; DB Neill, "Fast Graph Structure Learning from Unlabeled Data for Event Detection", (2011). Conference proceedings, Submitted Collection: IEEE International Conference on Data Mining Bibliography: Vancouver, Canada, December 2011

Chen L; Dubrawski A; Waidyanatha N; Weerasinghe C, "Automated Detection of Data Entry Errors in a Real Time Surveillance System", (2010). Conference proceedings, Published  Collection: Advances in Disease Surveillance Bibliography: Available online at www.syndromic.org

Weerasinghe C; Waidyanatha N; Dubrawski A; Baysek M, "Challenges of Introducing Disease Surveillance Technology in Developing Countries: Experiences from India and Sri Lanka", (2010). Conference proceedings, Published Collection: Advances in Disease Surveillance Bibliography: Available online at www.syndromic.org

Sabhnani M; Dubrawski A; Schneider J, "Detection of Multiple Overlapping Anomalous Clusters in Categorical Data", (2010). Book, Published Collection: Advances in Disease Surveillance Bibliography: Available online at www.syndromic.org

Dubrawski A; Sondheimer N, "Techniques for for Early Warning of Systematic Failures of Aerospace Components", (2011). Conference proceedings, Published Collection: IEEE Aerospace Conference Bibliography: Big Sky, Montana, March 2011, 

Poczos B; Schneider J, "On the Estimation of alpha-Divergences", (2011). Conference proceedings, Published Collection: Proceedings of AISTATS Bibliography: Ft. Lauderdale, Florida, April 2011, http://jmlr.csail.mit.edu/proceedings/papers/v15/poczos11a.html

Poczos B; Xiong L; Schneider J, "Nonparametric Divergence Estimation with Applications to Machine Learning on Distributions", (2011). Conference proceedings, Published Collection: International Conference on Uncertainty in Artificial Intelligence UAI 2011  Bibliography: Barcelona, Spain, July 2011, http://uai.sis.pitt.edu/papers/11/p599-poczos.pdf

Sverchkov Y, Visweswaran S, Clermont G, Hauskrecht M, Cooper GF, "A multivariate probabilistic method for comparing two clinical datasets", (2012). Conference proceedings, 2012 ACM International Health Informatics Symposium, submitted

Xiong L; Poczos B; Schneider J; Connolly A; VanderPlas J, "Hierarchical Probabilistic Models for Group Anomaly Detection", (2011).Published Collection: Proceedings of AISTATS Bibliography: Ft. Lauderdale, Florida, April 2011 

Zhang Y; Schneider J, "Learning Multiple Tasks with a Sparse Matrix-Normal Penalty", (2010). Conference proceedings, Published Collection: Neural Information Processing Systems Bibliography: Vancouver, Canada, December 2010, 

Zhang Y; Schneider J, "Multi-label Output Codes using Canonical Correlation Analysis", (2011). Conference proceedings, Published Collection: Proceedings of AISTATS Bibliography: Ft. Lauderdale, Florida, April 2011,

Cooper GF, Hennings-Yeomans P, Visweswaran S, Barmada M, "An efficient Bayesian method for predicting clinical outcomes from genome-wide data", (2010). Conference proceedings, Published Collection: Porceedings of AMIA Bibliography: Available online at proceedings.amia.org/127f4h/1

Valko M, Kveton B, Valizadegan H, Cooper GF, Hauskrecht M., "Conditional anomaly detection with soft harmonic functions", (2011). Conference proceedings, Proceedings of the International Conference on Data Mining

Sverchkov Y, Visweswaran S, Clermont G, Hauskrecht M, Cooper GF., "A multivariate probabilistic method for comparing two clinical datasets", (2012). Conference proceedings, Published Collection: Proceedings of the ACM International Health Informatics Symposium
Bibliography: DOI=10.1145/2110363.21104600 

Kan Shao, Yandong Liu, and Daniel B. Neill, "A generalized fast subset sums framework for Bayesian event detection", (2011). Conference proceedings,  Proceedings of the 11th IEEE International Conference on Data Mining 

Ermakov V., Dubrawski A., Hodgins J., Dohi T., and Savage A., "Mining Sea Turtle Nests - An Amplitude Independent Feature Extraction Method for GPR Data", (2012). Conference proceedings ,14th IEEE International Conference on Ground Penetrating Radar

Fiterau M. and Dubrawski A., "Projection Retrieval for Classification", (2012). Conference proceedings, Submitted

Poczos B. and Schneider J., "Nonparametric Estimation of Conditional Information and Divergences", (2012). Conference proceedings, AISTATS

Poczos B., Ghahramani Z. and Schneider J., "Copula-based Kernel Dependency Measures", (2012). Conference proceedings, International Conference on Machine Learning

Poczos B. , Xiong L., Sutherland D., and Schneider J., "Support Distribution Machines", (2012). Conference proceedings,SDM

Poczos B. , Xiong L., Sutherland D., and Schneider J., "Nonparametric Kernel Estimators for Image Classification", (2012).  IEEE Conference on Computer Vision and Pattern Recognition

Xiong. L., Poczos, B., and Schneider, J., "Group Anomaly Detection using Flexible Genre Models", (2011). Conference proceedings, Neural Information Processing Systems 

Zhang Y. and Schneider J., "Maximum Margin Output Coding Analysis", (2011). Conference proceedings,International Conference on Machine Learning

Other Publications Resulting from Project Activities

Sabhnani, M. (2010). Disjunctive Anomaly Detection: Identifying Complex Anomalous Patterns. Ph.D. Thesis Proposal. Machine Learning Department, Carnegie Mellon University, August 2010.

Sarkar, P. (2010). Tractable Algorithms for Proximity Search on Large Graphs. Ph.D. Thesis, Machine Learning Department, Carnegie Mellon University, May 2010.  http://reports-archive.adm.cs.cmu.edu/anon/ml2010/CMU-ML-10-107.pdf

Zhang Yi, "Learning with Limited Supervision by Input and Output Coding", (2012). Thesis, Published Bibliography: Ph.D. Thesis, Machine Learning Department, CMU http://reports-archive.adm.cs.cmu.edu/anon/ml2011/CMU-ML-12-102.pdf

Emily Kennedy, "Predictive Patterns of Sex Trafficking Online", (2012).  Honors Thesis, Carnegie Mellon University, Department of History

Our test applications and external partners (in no particular order):

Predictive Analytics Group, Chicago Police Department, http://www.chicagopolice.org/

We look at spatio-temporal mapping of crime records in order to detect complex patters which may be predictive of future crime activity.

Ottawa Heart Institute, Canada, http://www.ottawaheart.ca/

We try our pattern detection methods on public health surveillance data collected through a few projects throughout Canada in order to reliably identify emerging epidemics.

LIRNEAsia, Sri Lanka, http://lirneasia.net/, and the Health Department of Wayamba Province, Sri Lanka

We built an analytic system for public health surveillance which includes our complex anomalous pattern detection technology to identify emerging trends in demand for health services due to escalating infectious, non-infectious and chronic diseases. We use field data collected through that systems in experimental evaluations of algorithms developed in the scope of our project.

Rural Technology and Business Incubator of the Indian Institute of Technology, Madras, India, http://www.rtbi.in/

A variant of the system mentioned above is also being deployed and tested in Tamil Nadu state of India.

Systems Lifecycle Integrity Management initiative, Headquarters, United States Air Force, http://www.af.mil/

Anomalous patterns of maintenance and logistics activity involving fleets of aircraft may be and often are indicative of emerging crises in supply which may limit availability of equipment and increase costs of operations due to expediting. Our anomalous pattern detection technology is helping to detect such crises in their early stages in order to limit their negative impact.

Department of Astronomy, University of Washington, http://www.astro.washington.edu/,  and Department of Physics and Astronomy, Johns Hopkins University, http://physics-astronomy.jhu.edu/

We support scientific discovery by enabling detection of anomalous groups of celestial objects in telescope observations and in astrophysical simulation data.

Department of Civil and Environmental Engineering, Carnegie Mellon University, http://www.ce.cmu.edu/

We support analyses of water distribution systems by detecting clusters of apparent pipe breakages in water consumption data.

MIMIC II (Multiparameter Intelligent Monitoring in Intensive Care) database http://www.physionet.org/mimic2/

This database contains comprehensive clinical data from tens of thousands of Intensive Care Unit (ICU) patients. We use an extract from it as a primary test-bed for the analytic algorithms we develop.

Outreach activities

We are actively involved in disseminating results of our work, with the particular attention to reaching out to audiences of possible future collaborators outside of the area of computer science. The resulting presentations are listed below in the chronological order.

  1. Interactive Analysis of Multiple Streams of Data in Public Health and Food Safety Applications. Dubrawski, A. and Kelly L., PulseNet/OutbreakNet Annual Meeting, Snowbird, UT, September 23, 2009.
  2. Browsing and Analysis of Multidimensional Crisis Data at Interactive Speeds. Dubrawski, A. International Conference on Crisis Mapping, Cleveland, OH, October 16th, 2009.
  3. Trade-offs between Agility and Reliability of Predictions in Dynamic Social Networks Used to Model Risk of Microbial Contamination of Food, Dubrawski, A. Lawrence Livermore National Laboratory, October 2009.
  4. Fast subset sums for multivariate Bayesian scan statistics. Neill, D.B. International Society for Disease Surveillance Annual Conference, Miami, FL, December 2009.
  5. Interactive Analysis of Multidimensional Data for Adverse Event Detection, Dubrawski, A. University of Peradeniya, Sri Lanka, December 21st, 2009.
  6. Fast graph scan for scalable detection of arbitrary connected clusters. Speakman, S. and Neill, D.B. International Society for Disease Surveillance Annual Conference, Miami, FL, December 2009.
  7. Bayesian Outbreak Detection and Characterization. Cooper, G., International Society for Disease Surveillance Webinar on Applications of Bayesian Statistics for Biosurveillance, January 28, 2010.
  8. Analytics and Business Intelligence Current Trends, Opportunities, and Challenges. Dubrawski, A., The Emergent Technologies Program, CMU Tepper School of Business, February 2010.
  9. Fast subset scanning for multivariate event detection. Neill, D.B. ENAR 2010 Annual Meeting, New Orleans, LA, March 2010.
  10. GIVAS Analytics: Conceptual, Technical and Strategic Opportunities. Dubrawski, A. United Nations Global Impact and Vulnerability Alert System Blue Sky Thinkers Workshop, Bellagio, Italy, April 2010.
  11. An Efficient Bayesian Method for Predicting Clinical Outcomes from Genome-Wide Data. Cooper, G., Department of Human Genetics Spring Seminar Series. April 16, 2010.
  12. Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization. L. Xiong, SIAM Data Mining Conference (SDM), Columbus, OH, April 2010.
  13. Learning Compressible Models, Zhang, Y. SIAM Data Mining Conference (SDM), Columbus, OH, April 2010.
  14. Rapid Detection of Emerging Crises. Dubrawski A., The 11th Annual International Conference on Digital Government Research, Puebla, Mexico, May 2010.
  15. Projection Penalties: Dimension Reduction without Loss, Zhang, Y. International Conference on Machine Learning (ICML), Haifa, Israel, June 2010.
  16. Fast Generalized Scan for Anomalous Pattern Detection. McFowland III, E. 16th Conference for African American Researchers in the Mathematical Sciences, Baltimore, MD, June 2010.
  17. T-Cube Web Interface in RTBP: A Review of R&D Challenges, Dubrawski, A., RTBP Workshop, Chennai, India, July 7th 2010.
  18. Fast subset sums for scalable Bayesian detection and visualization. Neill, D.B. Fifth International Workshop on Applied Probability, Madrid, Spain, July 2010.
  19. Fast generalized subset scan for anomalous pattern detection. McFowland III, E., Speakman, S., and Neill, D.B. INFORMS 2010, Austin, TX, November 7th 2010.
  20. Discovering Complex Anomalous Clusters using Disjunctive Anomaly Detection Algorithm, Sabhnani, M., Dubrawski A., and Schneider J., INFORMS 2010, Austin, TX, November 7th 2010.
  21. Scalable Detection of Anomalous Patterns with Connectivity Constraints. Speakman, S., McFowland III, E., and Neill, D.B. INFORMS 2010, Austin, TX, November 7th 2010.
  22. G. Cooper, “Identifying Unexpected Clinical Care from Clinical Free-Text Reports”, Workshop on Machine Learning for Clinical Data Analysis, which was held in association with the International Conference on Machine Learning at Edinburgh, Scotland, July 2012.
  23. Ermakov V., Dubrawski A., Hodgins J., Dohi T., and Savage A. Mining Sea Turtle Nests - An Amplitude Independent Feature Extraction Method for GPR Data, 14th IEEE International Conference on Ground Penetrating Radar, Shanghai, China, June 2012.
  24. A. Dubrawski, “Applying Predictive Trending within CAMEO: Exploration and Explanation of Anomalous Patterns”, Condition-Based Maintenance+ Action Group,The Pentagon, Washington, DC, June 13, 2012 (invited presentation, delivered with N. Sondheimer of UMass Amherst)
  25. A. Dubrawski, “Machine Learning Can Support Understanding of Nuclear Threat”, 2012 IEEE International Intelligence and Security Informatics Conference ISI 2012, Washington, DC, June 12, 2011 (invited lecture).
  26. D.B. Neill and E. McFowland III. Fast generalized subset scan for anomalous pattern detection. Sixth International Workshop on Applied Probability, Jerusalem, Israel, June 2012.
  27. D.B. Neill, Speakman S., E. McFowland III, and S. Somanchi. Efficient subset scanning with soft constraints. Sixth International Workshop on Applied Probability, Jerusalem, Israel, June 2012.
  28. Speakman S., E. McFowland III, and D.B. Neill. Scalable detection of anomalous patterns with connectivity constraints. 29th Quality and Productivity Research Conference, Long Beach, CA, June 2012.
  29. Sverchkov, “A Multivariate Probabilistic Method for Comparing Datasets”, Statistics Seminar at the University of Maryland, College Park, MD, March 2012.
  30. D.B. Neill. Analytical methods for large scale surveillance of unstructured data. International Conference on Digital Disease Detection, Boston, MA, February 2012.
  31. A. Dubrawski, “Detection of Informative Patterns in Multi-Dimensional Transaction Data”, Singapore Management University, Singapore, January 10th, 2012.
  32. A. Dubrawski “Mining for Informative Patterns in Large Transactional Data”, Warsaw University of Life Sciences, Warsaw, Poland, January 5th, 2012.
  33. A. Dubrawski, “Affordable System for Rapid Detection and Mitigation of Emerging Diseases”, IBM Research, Bangalore, India, December 21st, 2011.
  34. A. Dubrawski, “Mining Health Data for Informative Patterns”, Indian Institute of Science, Bangalore, India, December 18th, 2011 (upon invitation to Large Scale Data Analytics and Intelligent Services Indo-US Workshop).
  35. R. Lonkar, A. Dubrawski, M. Fiterau, R. Garnett “Mining Intensive Care Vitals for Leading Indicators of Adverse Health Events”, International Syndromic Disease Conference, Atlanta, December 2011.
  36. E. McFowland III and Neill D.B., 'Efficient methods for anomalous pattern detection in general datasets', INFORMS Annual Conference, Charlotte, NC, November 2011.
  37. S. Somanchi and Neill D.B., 'Fast learning of graph structure from unlabeled data for anomalous pattern detection', INFORMS Annual Conference, Charlotte, NC,November 2011.
  38. Speakman S. and D.B. Neill. Dynamic pattern detection with connectivity and temporal consistency constraints. INFORMS Annual Conference, Charlotte, NC, November 2011.
  39. A. Dubrawski, “Making detection of complex anomalous patterns more feasible and more rewarding”, Public Health Program Office Seminar, CDC, Atlanta, August 4th, 2011.
  40. A. Dubrawski, “Machine Learning Can Help Nuclear Detection, Domestic Nuclear Detection Office”, Department of Homeland Security, August 1st, 2011.
  41. Neill D.B., 'Fast multivariate subset scanning for scalable cluster detection', Joint Statistical Meetings 2011, Miami, FL, August 2011.
Copyright 2010, Carnegie Mellon University, Auton Lab. All Rights Reserved.