Vladimir I. Tsurkov

Vladimir I. Tsurkov serves as Head of the Department of Complex Systems at the Dorodnitsyn Computing Centre, part of the Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences in Moscow, Russia. His research expertise spans operations research, optimal control, large-scale optimization, and computational applications, with recent work focusing on neural network architectures and machine learning applications across diverse domains including emotion recognition, recommender systems, image processing, and psychophysiological signal analysis.

In the field of polygraph science, Tsurkov and his collaborators proposed a machine learning approach to automate polygraph examiner's work using neural network architectures from the scikit-learn library based on Voting Classification architecture and a transformer, which increases the efficiency of polygraph testing, provides matching by features, and decreases the number of erroneous conclusions on testee's answers. Their 2022 study utilized electrodermal resistance (galvanic skin response), blood vessel capacity (plethysmogram), and respiratory rhythms as input channels for the machine learning-based scoring system. This work represents part of a broader research program applying neural networks to psychophysiological data analysis, including related 2022 publications on emotion identification from audio recordings and video-based emotion detection with the same collaborative team.

Working frequently with co-authors L.A. Derevyagin, V.V. Makarov, A.Yu. Molchanov, and A.N. Yakovlev, Tsurkov's research team has published multiple studies in 2022 applying neural networks to pattern recognition problems, positioning their polygraph work within a systematic exploration of how machine learning can enhance automated analysis of human behavioral and physiological signals. His broader collaboration network includes over 50 co-authors from institutions including the Steklov Mathematical Institute of RAS and Lomonosov Moscow State University.

Beyond deception detection, Tsurkov's research portfolio demonstrates interdisciplinary breadth spanning computational mathematics, optimization theory, network models, hypergraph algorithms, and most recently, deep learning applications for recommender systems, visual perception testing, and software technical debt detection. His polygraph research reflects the application of advanced computational methods from computer science to the challenge of automating and improving the reliability of psychophysiological credibility assessment.