Dr. Dan A. Simovici

Professor of Computer Science

University of Massachusetts Boston

Department of Computer Science

Education

• Ph.D., July 1974, University of Bucharest, Romania
• M.S. in Mathematics, June 1970, University of Iasi, Romania
• M.S. in E.E., June 1965, Polytechnical Institute of Iasi, Romania

Professional Affiliations

• IEEE and the Computer Society of IEEE
• Association for Computing Machinery
• AAAI
• American Mathematical Society

Academic Career

• 1985 - present: Professor of Computer Science, UMB
• January 2006: Visiting Professor of Computer Science, University of Science and Technology, Lille, France
• 1998: Visiting Professor of Computer Science, Tohoku University, Sendai, Japan
• 1984 - present: Director of the Computer Science Graduate Program, UMB
• 1982 - 1985: Associate Professor of Computer Science, UMB
• 1981 - 1982: Associate Professor of Computer Science, University of Miami, Florida

Research Interests

• Information-Theoretical Methods in Data Mining
• Semantic Models in Databases
• Algebraic Aspects of Multiple-Valued Logic

Other Activities

• Vice-Chair the Program Committees for ISPA'07 for Databases and Data Mining
• Member of Program Committees for major datamining conferences: KDD, PKDD, DAWAK, EGC.
• General Chairman of the 32nd International Symposium for Multiple-Valued Logic, Boston, Massachusetts, 15-18 May 2002.
• Managing Editor of Journal for Multiple-Valued Logic and Soft Computing
• Editor of International Journal for Parallel, Emergent, and Distributed Systems
• Editor of International Journal for Software and Information Technologies
• General Co-Chairman of the 26th International Symposium for Multiple-Valued Logic, Santiago de Compostela, Spain, May 1996.
• General Chairman of the 24th International Symposium for Multiple-Valued Logic, Boston, Massachusetts, May 1994.
• Chairman of the Technical Committee of the Computer Society/IEEE (elected at the 19th annual meeting, May 1988, Spain).
• General Chairman of the 17th International Symposium for Multiple-Valued Logic, Boston, Massachusetts.
• Reviewer for the Computer Science Accreditation Board of IEEE/ACM.

Ph.D. Students

• Dana Cristofor (graduated 2002)
• Laurentiu Cristofor (graduated 2002)
• Szymon Jaroszewicz (graduated 2003)
• Richard Butterworth (graduated 2006)
• Selim Mimaroglu (graduated 2008)

Books

• Mathematical Tools for Data Mining , Springer-Verlag 2008 by Dan A. Simovici and C. Djeraba
• Theory of Formal Languages with Applications by Dan Simovici and Richard Tenney, World Scientific, 1999
• Relational Database Systems by Dan Simovici and Richard Tenney, Academic Press, 1995
• Mathematical Foundations of Computer Science. vol. I: Sets, Relations, Induction in Computer Science (with Peter Fejer), Springer Verlag, New York, 1990
• Logical Foundations of Computer Science (with Peter Fejer), in preparation for Springer-Verlag, New York
• Introduction aux Structures Algébriques, (2 vols.), ERPI, Montreal, Canada, 1992
• Formal Languages and Compiling Techniques, Editura Didactica si Pedagogica, Bucharest, Romania, 1978

Recent Publications

• Structural Classification of XML Documents Using Multisets (with S. Iyer), International Journal on Artificial Intelligence Tools, vol. 17, no.5, pp.1003-1022 (pdf file)
• Approximate Computation of Object Distances by Locally-Sensitive Hashing (with S. Mimaroglu), to appear in Proceedings of DBMIN'08, Las Vegas, August 2008 (pdf file)
• Metric-Entropy Pairs on Lattices, Journal of Universal Computer Science (Springer-Verlag), vol. 13, no.11, 2007,pp. 1767-1778 (pdf file)
• Scalable pattern mining with Bayesian networks, Data Mining and Knowledge Discovery, (Springer-Verlag), (with S. Jaroszewicz and T. Scheffer) (pdf file)
• Betweenness, Metrics and Entropies in Lattices, Proceedings of ISMVL 2008, Dallas, TX, May 2008; the posted version is a pre-print that will appear in the Journal for Multiple-Valued Logic and Soft Computing (pdf file)
• Detecting Eye Fixations by Projection Clustering (with T. Urruty, S. Lew, N. Ihadaddene) ACM Transactions on Multimedia Computing, Communications and Applications, vol. 3, no.4, December 2007, (pdf file)
• Metric Methods in Data Mining, a chapter in Data Mining Patterns - New Methods and Applications, P. Poncelet. M. Teisseire, F. Masseglia (eds.), Information Science Reference, Hershey, 2007, pp. 1-31.
• Structure Inference of Bayesian Networks from Data: A New Approach Based on Generalized Conditional Entropy (with Saaid Baraty), Proceedings of ECG 2008, Sophia Antipolis, France, Revue des Nouvelles Technologies et de l'Information, RNTI-E-11, 2008, pp. 337-342 (pdf file)
• Multisets and Clustering XML Documents (with Swami Iyer) Proceedings of ICTAI, October 2007, Patras, Greece, IEEE CS Press, pp.267-274 (pdf file)
• Clustering and Approximate Identification of Frequent Item Sets (with S. Mimaroglu) Proceedings of FLAIRS 2007, Key West, May 2007, pp. 502-506 (pdf file)
• Clustering by Random Projections (with T. Urruty and C. Djeraba), ICDM 2007, Leipzig (pdf file), Lecture Notes in Artificial Intelligence, no. 4597, pp. 107-119
• On the Axiomatization of Generalized Entropic Distances, accepted at ISMVL 2007, Oslo, May 2007 (pdf file) An extended version in the Journal of Multivalued Logic and Soft Computing, v. 13, f.4-6,pp.295-320 is (pdf file)
• Model detection for User Behavior in Video Sessions (with Sylvain Mongy and Chabane Djeraba), DMIN, June 2007, Las Vegas (pdf file), Proceedings of DMIN 2007, CSREA Press, pp. 99-103
• A New Metric Splitting Criterion for Decision Trees(with Szymon Jaroszewicz) (pdf file) Journal of Parallel, Emerging and Distributed Computing, vol.21, no.4, pp. 239-256, 2006.
• On Feature Extraction through Clustering (with Richard Butterworth and Gregory Piatetsky-Shapiro) (pdf file) Proceedings of ICDM 2005, pp. 581--584 Houston, Texas, November 2005.
• Biclustering of Gene Expression Data Based on Local Nearness (with J. Aguilar-Ruiz and Domingo Savio Rodriguez) (pdf file) Proceedings of EGC 2006, Lille, France, January 2006, pp. 681--692.
• On the Ranges of Algebraic Functions in Lattices (with S. Rudeanu) (pdf file) Studia Logica, vol. 84, no.3, pp. 451--483, December 2006.
• Semi-Supervised Incremental Clustering of Categorical Data (with N. Singla), Proceedings of EGC 2005, Paris, France, pp. 189-200.
• An Abstract Axiomatization of the Notion of Entropy (with Ivo Rosenberg), Proceedings of ISMVL, May 2005, Calgary, Canada (pdf file) .
• Metric Incremental Clustering of Nominal Data (with N. Singla and M. Kuperberg), Proceedings of ICDM 2004, Brigton, UK, pp. 523-527 (pdf file)
• Interestingness of Frequent Itemsets Using Bayesian Networks as Background Knowledge (with S. Jaroszewicz), Proceedings of KDD 2004, Seattle, pp. 178--186. (pdf file)
• A Greedy Algorithm for Supervised Discretization (with R. Butterworth, D. S. Santos and Lucila Ohno-Machado), Journal of Biomedical Informatics, vol. 37(4), pp. 285--292. (pdf file)
• Measures on Boolean polynomials and their applications in data mining (with S. Jaroszewicz and I. G. Rosenberg), Applied Discrete Mathematics, volume on Discrete Mathematics and Data Mining, vol. 144,1, pp. 123--139 (pdf file)
• A Metric Approach to Building Decision Trees Based on Goodman-Kruskal Association Index (with S. Jaroszewicz), PAKDD 2004, Sydney, Australia, May 2004, LNAI 3056, Springer-Verlag, pp. 181--190 (pdf file)
• A Graph-Theoretical Approach to Boolean Interpolation of Non-Boolean Functions (with S. Rudeanu), Proceedings of the 34th International Symposium for Multiple-Valued Logic, Toronto, May 2004, published by IEEE Computer Society, pp. 245--250 (pdf file)
• Evolutionary Strategy for Learning Multiple-Valued Logic Functions (with A. Ngom and I. Stojmenovic), Proceedings of the 34th International Symposium for Multiple-Valued Logic, Toronto, May 2004, published by IEEE Computer Society, pp. 154--160
• A Metric Approach to Supervised Discretization (with R. Butterworth), EGC 2004, Clermont-Ferrand, France, January 2004, Revue des Nouvelles Technologies de l'Information, RNTI-E-2, vol. 1, pp. 197--203
• The Goodman-Kruskal Coefficient and Its Applications in the Genetic Diagnosis of Cancer (with S. Jaroszewicz, W. Kuo and L. Ohno-Machado), IEEE Transactions on Biomedical Engineering, vol. 51, no. 7, pp. 1095--1102, July 2004. (pdf file)
• Generating an Informative Cover for Association Rules (with L. Cristofor), Proceedings of the 2002 IEEE International Conference on Data Mining, pp. 597-600 (pdf file)
• Approximation of Non-Boolean Functions by Boolean Functions and Applications in Non-standard Computing, in Proceedings of the 2002 International Symposium on New Paradigm Computing, December 2002, Sendai, Japan, pp. 27--31 (invited talk) (pdf file)
• Several Remarks on Non-Boolean Functions over Boolean Algebras, Proc. of the International Symposium for Multiple-Valued Logic, Meiji University, Tokyo, May 2003, pp. 163--168 (pdf file)
• An Algebraic Approach to Entropy in Beyond Two: Theory and Applications of Multiple-Valued Logic, M. Fitting and E. Orlowska (editors), Springer-Verlag, Heidelberg, New York, 2003, pp. 101-115.
• Generalized Entropy and Decision Trees, EGC 2003 - Journees francophones d'Extraction et de Gestion de Connaissances, January 2003, Lyon, France (with S. Jaroszewicz), pp. 369-380 (ps file) (pdf file)
• Support Approximations using Bonferroni-Type Inequalities (with S. Jaroszewicz), Principles of Data Mining and Knowledge Discovery, PKDD 2002, Helsinki, August 2002, Lecture Notes in Artificial Intelligence, vol. 2431, pp. 212--224, Springer Verlag, Berlin, 2002. (ps file) (pdf file)
• Generating Informative Cover Rules (with Laurentiu Cristofor), International Conference on Data Mining, Maebashi, Japan, December 2002. (ps file) (pdf file)
• Finding Median Partitions Using Information-Theoretical Algorithms (with D. Cristofor), Journal of Universal Computer Science, vol 8, no.2, 153--172. (ps file) (pdf file)
• An Inclusion-Exclusion Result for Boolean Polynomials and Its Applications in Data Mining (with S. Jaroszewicz and I. Rosenberg), Proceedings of the Discrete Mathematics and Data Mining Workshop, Washington, April, 2002 (SIAM DM Meeting), pp. 165-173. (ps file) (pdf file)
• An Information-Theoretical Approach to Clustering Categorical Databases Using Genetic Algorithms (with Dana Cristofor), Proceedings of the Workshop on Clustering High-Dimensional Data and Its Applications, Washington, April, 2002 (SIAM DM Meeting), pp. 37-46. (ps file) (pdf file)
• On Functions Defined on Free Boolean Algebras (with I. Rosenberg and S. Jaroszewicz), Proceedings of the ISMVL 2002, Boston, Massachusetts, IEEE Computer Society, Los Alamitos, California, pp. 192--201. (ps file) (pdf file)
• Mining for Purity Dependencies in Relational Databases (with L. Cristofor and D. Cristofor), EGC 2000, Montpellier, January 19-23 (ps file) (pdf file) (best paper award received from AFIA (The French Association for Artificial Intelligence).
• An Axiomatization of Partition Entropy (with S. Jaroszewicz) Transactions on Information Theory, July 2002, vol. 48 (7), pp. 2138--2142 (a preliminary form appeared in the Proceedings of the 31st ISMVL,.Warsaw, Poland, May 2001, pp. 259-266).
• Impurity Measures in Databases (with L. Cristofor and D. Cristofor), Acta Informatica, 38 (2002), pp. 307-324.
• Prunning Redundant Association Rules Using Maximum Entropy Principle (with S. Jaroszewicz), Proceedings of PAKDD, Taipei, May 2002, Lecture Notes in Artificial Intelligence, vol. 2336, Springer Verlag, pp. 135--147. (ps file) (pdf file)
• A General Measure of Rule Interestingness (with S. Jaroszewicz) in Principles of Data Mining and Knowledge Discovery, the 5th European Conference, PKDD 2001, Freiburg, September 2001, Lecture Notes in Artificial Intelligence, vol. 2168, Springer-Verlag, pp. 253-266.
• Mining Association Rules in Entity-Relationship Modeled Databases (with Laurentiu Cristofor), Technical Report, UMB, TR 2001-1 (pdf file)
• An Information-Theoretical Approach to Genetic Algorithms for Clustering (with Dana Cristofor), Technical Report, UMB, TR 2001-2
• Generalized Entropy and Projection Clustering of Categorial Data (with D. Cristofor, L. Cristofor) in Principles of Data Mining and Knowledge Discovery, the 4th European Conference, PKDD 2000, Lyon, Lecture Notes in Artificial Intelligence, 1910, Springer-Verlag, pp. 619--625
• Impurity Measures and Applications to Classification and Clustering, (with Dana and Laurentiu Cristofor) presented at the Int. Conf. on Advances in Infrastructure for Electronic Bussiness, Science, and Education, Scuola Superiore G.R. Romoli (Telecom -- Italia), Aquila, Italy, August 2000
• Data Mining of Weak Functional Decompositions (with S. Jarosiewicz) in the Proceedings of the 30th International Symposium for Multiple-Valued Logic, Portland, Oregon, pp. 77-82
• On Information-Theoretical Aspects of Relational Databases (with S. Jarosewicz), in Finite vs. Infinite, Springer-Verlag, pp. 301--322
• Galois Connections and Data Mining, (with L. Cristofor and D. Cristofor), Journal of Universal Computer Sciene, Springer Verlag, vol.6, no.1, pp. 60-74
• Boolean Completeness in Two-valued Set Logic, (with I. Stojmenovic and R. Tosic) Multi. Val. Logic, 2000, vol. 5, pp. 267--280
• On Axiomatization of Conditional Entropy of Functions between Finite Sets, (with S. Jarosiewicz) Proc.of the 29th ISMVL, Freiburg, Germany, pp. 24--31
• Automatic Data Restructuring (with S. Ginsburg and Nan Shu) Journal of Universal Computer Sciene, vol. 5, no, 4, pp. 243-286
• Learning with Permutably Homogeneous Perceptrons, (with A. Ngom, I. Stojenovic, C. Reischer) Proc.of the 28th ISMVL, Fukuoka, Japan, pp. 161--167
• Functional Entropy and Decision Trees, (with V. Shmerko, V. Cheushev, S. Yanushkiewicz) Proc.of the 28th ISMVL, Fukuoka, Japan, pp. 257--264
• Completeness Criteria in Set-Valued Logic Under Composition with Union and Intersection, Proceedings of the 27th International Symposium for Multiple-Valued Logic, May 1997, pp. 75--82.
• A Characterization of the Information Content of a Classification (with K. Baclawski), Information Processing Letters, vol 57 (1996), pp. 211--214.
• Several Remarks on the Complexity of Set-Valued Switching Functions, (with C. Reisher) Proceedings of the 26th International Symposium for Multiple-Valued Logic, Santiago de Compostela, Spain, 1996
• A Categorial Approach to Database Semantics, (with K. Baclawski and W. White) Math. Struct. in Computer Science (1994), v. 4, pp. 147-183

Recent Talks

• Linear Methods in Data Mining, Siemens Doctoral Summer School at the University of Iasi, Romania, June 20, 2009 (pdf file)
• Hereditary Families of Sets in Data Mining, University of Bucharest, Romania, June 25, 2009 (pdf file)
• Metric Methods in Data Mining, IDA 2006, Iasi, Romania, June 16, 2006, (pdf file)
• Metric Methods in Mining, Dana Farber Cancer Institute, Boston, February 27, 2004, (pdf file)
• Wavelets and Applications (MIT, April 27, 2004) (pdf file)
• Research Directions in Data Mining (in Romanian, October 2004, Universities of Bucharest and Iasi, Romania) (pdf file)
• Metrics on Partitions of Finite Sets and Data Mining Applications (UMB, May 11, 2005) (pdf file)
• An Abstract Axiomatization of the Notion of Entropy (Calgary, May 19, 2005) (pdf file)

His 4-Legged Friends:

Handouts for cs724: