Aleksandar Lazarevic

Aleksandar Lazarevic

Address: 401 South First Street, Apt. 420, Minneapolis MN 55401

Phone: (612) 659 – 1355 (home), (612) 626-8906 (office)

EDUCATION

Ph.D., Computer Science Temple University, Philadelphia, PA 2001

GPA: 3.96 Washington State University (WSU), Pullman, WA 1997-2000

Qualifying exam passed September 1998. Preliminary exam passed May 2000.

Thesis Title: Integration of Multiple Prediction Models in Centralized and Distributed Knowledge Discovery in Databases

M.S. Computer Science and Computer Engineering University of Belgrade, Yugoslavia 1994-1997

GPA: 10.0 (on 10.0 scale)

Thesis Title: A new method of data dependence determination for programming loops in parallel computers

B.S., Computer Science and Computer Engineering University of Belgrade, Yugoslavia 1989-1994

GPA: 9.22 (on 10.0 scale)

Thesis Title: A simulator of a VLIW processor

RESEARCH EXPERIENCE

· Research assistant 1998 - 2000 Washington State University

2000 - present, Temple University

Research Interests:

- Data Mining Applications for Network Intrusion Detection

- Machine Learning: combining predictors (ensemble methods, mixture of experts), supervised and unsupervised learning, algorithms for prediction in heterogeneous data

- Distributed and Parallel Data Mining

- Spatial Data Analysis and Modeling

- Brain Image Classification, Microarray Data Analysis

- Knowledge Discovery in Business Valuation, Web Mining, E-Commerce Applications

- Neural Networks, Radial Basis Functions

- Parallel Processing in Superscalar and VLIW Architectures

Research Projects:

Data Mining for Network Intrusion Detection. Applications of data mining and machine learning to intrusion detection. Misuse Detection (Learning from Rare classes) vs. Anomaly/Outlier Detection.

Data Reduction for Spatial-Temporal Knowledge Discovery. Reduction of spatial and spatial-temporal attributes through a spatial statistical and spatial-temporal analysis, Data compression through controllable sampling and model sensitivity analysis, Discovery of predictable geospatial subsets (project funded by INEEL, Department of Energy).

Classification of brain image data. Classification regions of interest in brain images using measures of dissimilarity and neural networks.

Business valuation. Intangible assets analysis and identifying enterprise value drivers, time-series data analysis, e-commerce applications (project funded by ValueMiner Inc. )

Spatial Data and Knowledge Discovery. Crop Yield Prediction, Fertilizer Recommendation (project funded by INEEL)

TEACHING EXPERIENCE

- Graduate Teaching Assistant for several computer science courses including Visual Basic, C, Fortran, Algorithmics.

Washington State University, August 1997 – December 1998

WORK EXPERIENCE

· System programmer March 1995 - August 1997 Institute of Applied Mathematics

and Electronics, Yugoslavia

Applied Cryptography. The development of encryption algorithms, cryptographic applications in network environment.

TECHNICAL SKILLS:

- System Administration for Linux and Windows operating systems

- Programming Languages: C/C++ (Visual C++, Borland C++), Visual Basic, Delphi, Pascal, Fortran 90, ADA, 80xx assembler, PDP-11 assembler, HTML

- Operating Systems: Windows NT/98/2000, Linux, Unix, VAX/VMS

- Software Packages:

o Mathematical and statistical packages: MATLAB, S-PLUS, SAS

o Data Mining packages: Clementine

o Visual Matcom (MATLAB Compiler)

o Database packages: MS Access, Postgress, MS SQL Server

o VLSI Packages: N2.ISP, VHDL, MAXPLUS, Orcad, Tanner

o Electrical Engineering packages: Spice

o General computer skills: MS Front Page, Latex, CorelDraw!, Visio, MS Office

PUBLICATIONS

Journal papers

Lazarevic, A. and Obradovic, Z.: (in press) "Boosting Algorithms for Parallel and Distributed Learning", Distributed and Parallel Databases Journal, Special Issue on Parallel and Distributed Data Mining.

Lazarevic, A. and Obradovic, Z.: (in press) "Boosting Specialized Classifiers in Heterogeneous and Spatial Databases", Intelligent Data Analysis, Vol. 5, pp. 1-24, 2001.

Lazarevic, A. and Obradovic, Z.: (in press) "Knowledge Discovery in Multiple Spatial Databases", Journal of Neural Computing and Applications.

Pokrajac, D., Lazarevic, A., Obradovic, Z.: "Exporation-Explotation Trade-off in Machine Learning", Facta Universitatis, Vol. 14, No. 1, April 2001.

Selected conference papers

Lazarevic, A., Ramnani, H., Ertoz, L., Srivastava, J., Kumar, V.: "Evaluation of Outlier Detection Schemes for Detecting Network Intrusions", in review

Chawla, N., Lazarevic, A., Hall, L., Bowyer, K.: "SMOTEBoost: Improving the Prediction of Minority Class in Boosting", in review.

Pokrajac, D., Lazarevic, A., Megalooikonomou, V., Obradovic, Z.: "Effective Classification of 3-D Image Data Using Partitioning Methods”, Proc. SPIE Conference on Visualization and Data Analysis, San Jose, January 2002.

Hoskinson, R., Pokrajac, D., Obradovic, Z., Lazarevic, A.: "The Unpredictability of Soil Fertility across Space and Time", 6th International Conference on Precision Agriculture and other Precision Resources Management, Minneapolis, MN, 2002.

Pokrajac, D., Hoskinson, R., Lazarevic, A., Obradovic, Z.: "Spatial-Temporal Techniques for Prediction and Compression of Soil Fertility Data", 6th International Conference on Precision Agriculture and other Precision Resources Management, Minneapolis, MN, 2002.

Lazarevic, A., Obradovic, Z.: (in press) "Data Reduction Using Multiple Models Integration", Proc. 5th European Conference on Principles and Practice of Knowledge Discovery in Databases, Freiburg, Germany, September 2001.

Lazarevic, A., Obradovic, Z.: "The Distributed Boosting Algorithm", 7th International Conference on Knowledge Discovery and Data Mining, San Francisco, pp. 311-316, August, 2001.

Lazarevic, A., Obradovic, Z.: "The Effective Pruning of Neural Network Ensembles", IEEE International Joint Conference on Neural Networks, pp. 796-801, July 2001.

Lazarevic, A., Pokrajac, D., Megalooikonomou, V., Obradovic, Z.: "Distinguishing Among 3-D Distributions for Brain Image Data Classification," 4th International Conference on Neural Networks and Expert Systems in Medicine & Healthcare, June 2001.

Pokrajac, D., Lazarevic, A.,, Megalooikonomou, V., Obradovic, Z.: "Classification of Brain Image Data using measures of distributional distance," 7th Annual Meeting of the Organization for Human Brain Mapping, June 2001.

Lazarevic, A., Obradovic, Z.: "Boosting Localized Classifiers in Heterogeneous Databases", First SIAM International Conference on Data Mining, Chicago, April 2001.

Lazarevic, A., Pokrajac, D., Obradovic, Z.: "An E-commerce System for Mining Distributed Spatial Databases," International Conference on Advances in Infrastructure for Electronic Business, Science, and Education on the Internet, SSGRR (Scuola Superiore Guglielmo Reiss Romoli), l`Aquila, Italy, August 2000.

Lazarevic, A., Pokrajac, D., and Obradovic, Z.: "Distributed Clustering and Local regression for Knowledge Discovery in Multiple Spatial Databases,'' Proc. 8th European Symposium on Artificial Neural Networks, Bruges, Belgium, pp. 129-134, April 2000.

Lazarevic, A. Fiez, T. and Obradovic, Z.: "Adaptive Boosting for Spatial Functions with Unstable Driving Attributes.'' Proc. Pacific-Asia Conf. on Knowledge Discovery and Data Mining, Kyoto, Japan, pp. 329-341, April 2000.

Lazarevic, A., Fiez, T. and Obradovic, Z.: "A Software Tool for Spatial Data Analysis and Modeling.'' Proc. Data Mining Minitrack at the IEEE Hawaii Int'l Conference on System Sciences, IEEE Computer Society Press, January 2000.

Pokrajac, D., Lazarevic, A., Vucetic, S., Fiez T. and Obradovic Z.: "Image Processing in Precision Agriculture," Proc. IEEE Int'l Conf. On Telecommunications in Modern Satellite, Cable and Broadcasting Services, Nis, Yugoslavia, October 1999.

Lazarevic, A., Xu, X., Fiez, T. and Obradovic, Z.: "Clustering-Regression-Ordering Steps for Knowledge Discovery in Spatial Databases", Proc. IEEE/INNS Int'l Conf. on Neural Neural Networks, Washington, D.C., July 1999.

PATENTS:

- Zoran Obradovic, Tim Fiez, Aleksandar Lazarevic, Slobodan Vucetic, Dragoljub Pokrajac: B-094, “Systems and methods for knowledge discovery in spatial data”, Patent disclosure filed January 2001, Reference: S/N 09/753,363

HONORS AND ACTIVITIES:

- Publicity Chair, Third SIAM International Conference on Data Mining, San Francisco, CA, May 1-3, 2003

- Workshop Chair, Data Mining for Cyber Threat Analysis, IEEE International Conference on Data Mining, Maebashi TERRSA, Maebashi City, Japan, December 9 - 12, 2002

- Program Committee Member, IEEE International Conference on Data Mining, Maebashi TERRSA, Maebashi City, Japan, December 9 - 12, 2002

- ACM SIGKDD 2001 Student Travel Award, Seventh International Conference on Data Mining and Knowledge Discovery, August 2001

- Graduate Student Research Award, College of Science and Technology, Temple University, May 2001

- SIAM Student Travel Award, First SIAM Conference on Data Mining, April 2001

- Fellowship from Serbian Department for Science and Technology, 1993 - 1994

- Scholarship from Serbian Academy of Science Fund, 1994 - 1997

- Scholarship from Serbian Academy of Science and Arts, 1994 - 1995

- A fourth prize on Serbian High School Student’s competition in Mathematics, 1986

- Member of City Brass Orchestra (clarinet), Yugoslavia, 1982 – 1989

- Fluent in Serbian. Have knowledge of German

- Personal Interests: Traveling, Sport (tennis, chess, basketball), Movies, Music