Main areas of scientific interests are information technologies, inductive modeling, multilayered GMDH algorithms.
Basic scientific results:
Was developed the interrelated processes systems constructing methodology for the aim-forecasting problem which is based on statistical cause-effect relation identification between every possible processes pair .
Basic practical results:
- The Two-Stage Division Modeling Algorithm (TSDMA) has been offered, implemented and applied for solving the medicines effectiveness estimation task .
- The impact of different initial sample division algorithms and forecasting models constructing schemes in the TSDMA on accuracy of obtained models has been investigated for solving the medicines effectiveness estimation task [3,2];
- Took part in designing process for the fan decisions multilayered algorithm (FDMA) ;
- The adaptive forecasting inductive algorithm with sample division optimization in the sliding data window has been implemented .
Participating in seminars and conferences:
International seminars and conferences on an inductive modeling Prague, 2007; Kyiv, 2008, annual summer school-seminar "Inductive modeling: theory and application" (Zhukin, Kiev oblast, 2007-2009);
General amount of publications is 12, all the papers were published in scientific specialized editions, 4 papers among them were published in foreign scientific editions.
List of the most essential publications:
- Alexender Pavlov, Andrey Pavlov "GMDH as an instrument for multidimensional process interrelations analysis " // Inductive modeling for complex systems. Coll. of scientific papers. Kyiv: IRTC ITS, 2009, p 149-164. (in Russian)
- «GMDH-based Forecasting for the Estimation of Medicines Efficiency» authors: Nina. Kondrashova, Andriy. Pavlov // In Proc. of IWIM 2009. 3-rd International Workshop on Inductive modeling, Sep. 14-19 Krynica, Poland - p.60-67
- N. Kondrashova, A. Pavlov. «GMDH-based Forecasting of the Test Results of Blood Samples in Task of the Effective Medicines Estimation». - In Proc. of ISIM 2008. 2nd International conference on inductive modeling, Sept.15-19,2008. Kyiv, p. 295-299, ISBN 978-966-02-4889
- «Sample division with sliding interval as a method of increase of accuracy for time series forecasting», authors: N. Kondrashova, A. Pavlov, Ya. Pavlov. // In Proc. of ISIM 2008. 2nd International conference on inductive modeling, Sept.15-19,2008. Kyiv, p. 250-254, ISBN 978-966-02-4889
- Kondrashova N., Pavlov A., Pavlov Ya., Optimization of forecasting models for testing blood samples by estimation of tiol-disulfide diagrams. - In Proc. of IWIM 2007. International workshop on inductive modeling, CTU in Prague, p. 160-164. ISBN 978-80-01-03881-9
- Kondrashova N.V., Pavlov V. A., Pavlov A.V. Multilayer algorithm for a fan decisions. - // Bulletin of the National Technical University of Ukraine "KPI". Series: economics, management and computing. - K.: «Vek+», 2006, 45. - P. 218-227.(in Russian)