Boris G. Mirkin

• Tenured Professor
• School of Applied Mathematics and Information Science | Department of Data Analysis and Artificial Intelligence: Professor
• International Laboratory of Decision Choice and Analysis: Leading Research Fellow
• Laboratory of Algorithms and Technologies for Networks Analysis (HSE Branch in Nizhny Novgorod): Chief Research Fellow

Education and degrees

Area of expertise

Mathematical methods of cluster analysis and decision making, based on experimental and textual information and applied to sociology, bioinformatics, organizational systems, development of interpreting systems

2010 research results

• A method for pattern recognition utilizing information of the structure of pattern neighborhood both for a single classifier and multiple classifiers (in collaboration with Zacharias Voulgaris, Birkbeck College Ph.D. Student; published in 2010)
• Experimental assessment of the author-proposed “intelligent” version of the popular K-means clustering method (iK-Means). It is experimentally shown that the iK-means method outperforms seven other methods in various conditions (in collaboration with Ming-Tso Chiang, Birkbeck College Ph.D. Student; published in 2010)
• A method for representation of  research organization’s activities by means of optimal lifting over a taxonomy of the domain under consideration (in collaboration with Prof. T. Fenner, Birkbeck University of London, UK and Dr. S. Nascimento, New University of Lisbon, Portugal, partially published in 2010)
• A system and description of data analysis main methods (published as a textbook, Core Concepts in Data Analysis: Summarization, Correlation, Visualization, Springer, 2011, 388 p.)

Current research

• An additive spectral method for cluster analysis of similarity matrices, its experimental verification and application (in collaboration with Dr. S. Nascimento, New University of Lisbon, Portugal).
• Stopping criteria for divisive hierarchical clustering algorithms (in collabortion with E.Kovaleva, HSE student)
• Approximate tri-clusters (in collabortion with A. Kramarenko, HSE student)
• Methods for interpretation of thematic clusters over hierarchical taxonomies and other cognitive structures (in collaboration with Prof. T. Fenner, Birkbeck University of London, UK, and Dr. S. Nascimento, New University of Lisbon, Portugal)
• Methods for analysis and classification of a corpus of unstructured text documents by using the techniques of annotated suffix trees and taxonomies of specific domains. These methods are to be applied to programmes of teaching courses, taught in HSE (in collaboration with E.Chernyak, O.Chugunova, J.Askarova, HSE students). This work is part of the research project “Teacher–Students: Development and adaptation of cluster analysis methods to automate the analysis of textual information by using a specific domain’s ontology”. Six students of the School of Applied Mathematics and Informatics take part in this project, supported by the HSE Research Foundation 2011-2012. 

 

Participation in conferences in 2010 – 2011

• 11th Russian national symposium “Strategy planning and enterprises development”, April 2010, CEMI of RAS, invited plenary talk “Representing research organization activities, considering the structure of the research area domain: the cluster-lift method”
• 4th International Conference “Knowledge Science, Engineering and Management”, September 2010, Belfast, Northern Ireland, UK. Paper: Constructing and mapping fuzzy thermatic clusters to higher ranks in a taxonomy (jointly with S. Nascimento, T. Fenner, and L.M. Pereira) has been selected among six others to have been published in International Journal of Software and Informatics, 2010. № 4(3). C. 257—275.
• 13th International Conference on Rough Sets, Data Mining, Fuzzy Sets and Granular Computing (RSFDGrC-2011), Moscow HSE June 2011 – General Chair
• 4th International Conference on Pattern Recognition and Machine Intelligence (PReMI-2011), Moscow HSE June 2011, Invited plenary talk.
• International Conference on Classifications, Glasgow UK, July 2011 – Member of the organizing committee, a paper
• Biannual conference of International Federation of Classification Societies, Frankfurt, Germany, August 2011 – Member of the Program Committee, a paper
• 2011 meeting of the European Mathematical Psychology Group, August 2011, Telecom, Paris, France – Member of the Scientific Committee  

Recent funded projects

HSE grant for individual research projects 2009: 09-01-0071 "Interrelation between spectral and approximation approaches to cluster analysis"

 

HSE grant  11-04-0019 “Teacher–Students: Development and adaptation of cluster analysis methods to automate the analysis of textual information by using a specific domain’s ontology”  (Six students of the School of Applied Mathematics and Informatics take part in this project)

Publications

2012

2011

2010

1974